modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-08-31 06:26:39
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 530
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-08-31 06:26:13
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
joemaatouk/donut-base-sroie
|
joemaatouk
| 2023-09-28T13:36:07Z | 9 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:ez_pass-dataset",
"base_model:naver-clova-ix/donut-base",
"base_model:finetune:naver-clova-ix/donut-base",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-09-11T17:56:59Z |
---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- ez_pass-dataset
model-index:
- name: donut-base-sroie
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# donut-base-sroie
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the ez_pass-dataset dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
TheBloke/leo-hessianai-13B-chat-GPTQ
|
TheBloke
| 2023-09-28T13:34:46Z | 41 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"custom_code",
"en",
"de",
"dataset:LeoLM/OpenSchnabeltier",
"dataset:OpenAssistant/OASST-DE",
"dataset:FreedomIntelligence/alpaca-gpt4-deutsch",
"dataset:FreedomIntelligence/evol-instruct-deutsch",
"dataset:LeoLM/German_Poems",
"dataset:LeoLM/German_Songs",
"base_model:LeoLM/leo-hessianai-13b-chat",
"base_model:quantized:LeoLM/leo-hessianai-13b-chat",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-09-28T12:22:36Z |
---
base_model: LeoLM/leo-hessianai-13b-chat
datasets:
- LeoLM/OpenSchnabeltier
- OpenAssistant/OASST-DE
- FreedomIntelligence/alpaca-gpt4-deutsch
- FreedomIntelligence/evol-instruct-deutsch
- LeoLM/German_Poems
- LeoLM/German_Songs
inference: false
language:
- en
- de
library_name: transformers
license: llama2
model_creator: LAION LeoLM
model_name: Leo Hessianai 13B Chat
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Leo Hessianai 13B Chat - GPTQ
- Model creator: [LAION LeoLM](https://huggingface.co/LeoLM)
- Original model: [Leo Hessianai 13B Chat](https://huggingface.co/LeoLM/leo-hessianai-13b-chat)
<!-- description start -->
## Description
This repo contains GPTQ model files for [LAION LeoLM's Leo Hessianai 13B Chat](https://huggingface.co/LeoLM/leo-hessianai-13b-chat).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GGUF)
* [LAION LeoLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/LeoLM/leo-hessianai-13b-chat)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 8.01 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 13.66 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/leo-hessianai-13B-chat-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/leo-hessianai-13B-chat-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `leo-hessianai-13B-chat-GPTQ`:
```shell
mkdir leo-hessianai-13B-chat-GPTQ
huggingface-cli download TheBloke/leo-hessianai-13B-chat-GPTQ --local-dir leo-hessianai-13B-chat-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir leo-hessianai-13B-chat-GPTQ
huggingface-cli download TheBloke/leo-hessianai-13B-chat-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir leo-hessianai-13B-chat-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir leo-hessianai-13B-chat-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/leo-hessianai-13B-chat-GPTQ --local-dir leo-hessianai-13B-chat-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/leo-hessianai-13B-chat-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/leo-hessianai-13B-chat-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/leo-hessianai-13B-chat-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `leo-hessianai-13B-chat-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/leo-hessianai-13B-chat-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: LAION LeoLM's Leo Hessianai 13B Chat
# LAION LeoLM: **L**inguistically **E**nhanced **O**pen **L**anguage **M**odel
Meet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2.
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.
Thanks to a compute grant at HessianAI's new supercomputer **42**, we release two foundation models trained with 8k context length,
[`LeoLM/leo-hessianai-7b`](https://huggingface.co/LeoLM/leo-hessianai-7b) and [`LeoLM/leo-hessianai-13b`](https://huggingface.co/LeoLM/leo-hessianai-13b) under the [Llama-2 community license](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt) (70b also coming soon! 👀).
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.
Read our [blog post]() or our paper (preprint coming soon) for more details!
*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*
## LeoLM Chat
`LeoLM/leo-hessianai-13b-chat` is a German chat model built on our foundation model `LeoLM/leo-hessianai-13b` and finetuned on a selection of German instruction datasets.
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench-DE scores:
```
{
"first_turn": 6.525,
"second_turn": 5.15,
"categories": {
"writing": 6.925,
"roleplay": 6.7,
"reasoning": 4.55,
"math": 3.25,
"coding": 3.45,
"extraction": 5.4,
"stem": 7.55,
"humanities": 8.875
},
"average": 5.8375
}
```
## Model Details
- **Finetuned from:** [LeoLM/leo-hessianai-13b](https://huggingface.co/LeoLM/leo-hessianai-7b)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English and German
- **Demo:** [Web Demo]()
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [LAION Discord](https://discord.com/invite/eq3cAMZtCC) or [Björn Plüster](mailto:bjoern.pl@outlook.de)
## Use in 🤗Transformers
First install direct dependencies:
```
pip install transformers torch sentencepiece
```
If you want faster inference using flash-attention2, you need to install these dependencies:
```bash
pip install packaging ninja
pip install flash-attn==v2.1.1 --no-build-isolation
pip install git+https://github.com/HazyResearch/flash-attention.git@v2.1.1#subdirectory=csrc/rotary
```
Then load the model in transformers:
```python
from transformers import pipeline
import torch
system_prompt = """<|im_start|>system
Dies ist eine Unterhaltung zwischen einem intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt ausführliche, hilfreiche und ehrliche Antworten.<|im_end|>
"""
prompt_format = "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
prompt = "Erkläre mir wie die Fahrradwegesituation in Hamburg ist."
generator = pipeline(model="LeoLM/leo-hessianai-13b-chat", device="cuda", torch_dtype=torch.float16, trust_remote_code=True) # True for flash-attn2 else False
print(generator(prompt_format.format(prompt=prompt), do_sample=True, top_p=0.95, max_length=8192))
```
"*Hamburg verfügt über ein umfangreiches Netzwerk an Radwegen, das ein effizientes und angenehmes Radfahren in der ganzen Stadt ermöglicht. Die Radwege variieren in Bezug auf ihre Qualität, wobei einige erstklassig mit eigens für Radfahrer reservierten Spuren sind, während andere einfache Fahrradsymbole auf dem Boden haben, die anzeigen, dass Radfahrer abwechselnd mit dem Autoverkehr auf der Straße fahren sollten. Einige Nebenstraßen haben auch spezielle Fahrradspuren, wobei einige mit Bordsteinabsenkungen zur Seite der Autospuren markiert sind. Zusätzlich haben viele Hauptstraßen, insbesondere in Nebenstraßen, fahrradfreundliche Abstände zwischen den geparkten Autos und dem Gehweg, was ein bequemes Fahren auf der Straße ermöglicht. Der Bau von Radschnellwegen, die schnelles und effizientes Radfahren in und aus der Stadt ermöglichen, ist im Gange und wird in den kommenden Jahren fortgesetzt. Insgesamt sind die Radwege in Hamburg weitläufig und gut ausgeschildert, was es zu einem angenehmen Ort macht, um mit dem Fahrrad zu fahren.*"
## Prompting / Prompt Template
Prompt dialogue template (ChatML format):
```
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
```
The model input can contain multiple conversation turns between user and assistant, e.g.
```
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
```
## Ethical Considerations and Limitations
LeoLM has been tested in English and German, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of `LeoLM/leo-hessianai-13b-chat` cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-13b-chat`, developers should
perform safety testing and tuning tailored to their specific applications of the model.
Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
## Finetuning Details
| Hyperparameter | Value |
|---|---|
| Num epochs | 3 |
| Examples per epoch | 131214 |
| Global batch size | 256 |
| Learning rate | 3e-5 |
| Warmup steps | 100 |
| LR scheduler | Cosine |
| Adam betas | (0.9, 0.95) |
## Dataset Details
```
## Stats for 'Subset of OpenAssistant/OASST-DE' (3534 samples (100.0%))
-----------------
Accepted: 3534/3534 (100.0%)
Accepted tokens: 2259302
Skipped: 0 (0.0%)
Min tokens per sample: 29
Max tokens per sample: 2484
Avg tokens per sample: 639.3044708545557
-----------------
## Stats for 'Subset of FreedomIntelligence/evol-instruct-deutsch' (57841 samples (100.0%))
-----------------
Accepted: 57841/57841 (100.0%)
Accepted tokens: 42958192
Skipped: 0 (0.0%)
Min tokens per sample: 33
Max tokens per sample: 5507
Avg tokens per sample: 742.6944900675991
-----------------
## Stats for 'Subset of FreedomIntelligence/alpaca-gpt4-deutsch' (48969 samples (100.0%))
-----------------
Accepted: 48969/48969 (100.0%)
Accepted tokens: 13372005
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 1359
Avg tokens per sample: 273.07082031489307
-----------------
## Stats for 'Subset of LeoLM/OpenSchnabeltier' (21314 samples (100.0%))
-----------------
Accepted: 21314/21314 (100.0%)
Accepted tokens: 8134690
Skipped: 0 (0.0%)
Min tokens per sample: 25
Max tokens per sample: 1202
Avg tokens per sample: 381.65947264708643
-----------------
## Stats for 'Subset of LeoLM/German_Poems' (490 samples (100.0%))
-----------------
Accepted: 490/490 (100.0%)
Accepted tokens: 618642
Skipped: 0 (0.0%)
Min tokens per sample: 747
Max tokens per sample: 1678
Avg tokens per sample: 1262.534693877551
-----------------
## Stats for 'Subset of LeoLM/German_Songs' (392 samples (100.0%))
-----------------
Accepted: 392/392 (100.0%)
Accepted tokens: 187897
Skipped: 0 (0.0%)
Min tokens per sample: 231
Max tokens per sample: 826
Avg tokens per sample: 479.3290816326531
-----------------
## Stats for 'total' (132540 samples (100.0%))
-----------------
Accepted: 132540/132540 (100.0%)
Accepted tokens: 67530728
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 5507
Avg tokens per sample: 509.51205673758864
-----------------
```
|
Aliki/Llama-2-13b-chat-german-areto26-test1
|
Aliki
| 2023-09-28T13:32:14Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T13:32:05Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
corrius/cross-encoder-mmarco-mMiniLMv2-L12-H384-v1
|
corrius
| 2023-09-28T13:31:41Z | 1,708 | 2 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-21T09:31:28Z |
# Model Name: mmarco-mMiniLMv2-L12-H384-v1
This model is a re-upload of the `mmarco-mMiniLMv2-L12-H384-v1` from the `cross-encoder` user on HuggingFace. The intent is to provide continued access to the community after its original removal from HuggingFace Model Hub.
## Original Model Information
- **Author**: cross-encoder
- **Model Hub URL**: https://huggingface.co/cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
- **Description**: This model was originally designed for re-ranking. For details on architecture, training data, and other specifics, it's recommended to refer to the original documentation or publications related to the model.
## License
This model is licensed under the Apache License 2.0. You can find the license text in the `LICENSE` file in this repository or [online here](https://www.apache.org/licenses/LICENSE-2.0).
## Attribution
All credit for the original creation and training of this model goes to the `cross-encoder` user and any associated researchers or organizations. If you use this model, please attribute the original authors.
|
CyberHarem/hagozaki_riko_yagatekimininaru
|
CyberHarem
| 2023-09-28T13:05:47Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/hagozaki_riko_yagatekimininaru",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T12:55:06Z |
---
license: mit
datasets:
- CyberHarem/hagozaki_riko_yagatekimininaru
pipeline_tag: text-to-image
tags:
- art
---
# Lora of hagozaki_riko_yagatekimininaru
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4420, you need to download `4420/hagozaki_riko_yagatekimininaru.pt` as the embedding and `4420/hagozaki_riko_yagatekimininaru.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4420**, with the score of 0.902. The trigger words are:
1. `hagozaki_riko_yagatekimininaru`
2. `brown_hair, brown_eyes, short_hair, smile`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.851 | [Download](5100/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| 4760 | 0.823 | [Download](4760/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| **4420** | **0.902** | [**Download**](4420/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.791 | [Download](4080/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.797 | [Download](3740/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.759 | [Download](3400/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.606 | [Download](3060/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.839 | [Download](2720/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.871 | [Download](2380/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.701 | [Download](2040/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.722 | [Download](1700/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.706 | [Download](1360/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.575 | [Download](1020/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.415 | [Download](680/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.547 | [Download](340/hagozaki_riko_yagatekimininaru.zip) |  |  |  |  | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
CyberHarem/hoto_mocha_istheorderarabbit
|
CyberHarem
| 2023-09-28T12:59:48Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/hoto_mocha_istheorderarabbit",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T12:48:09Z |
---
license: mit
datasets:
- CyberHarem/hoto_mocha_istheorderarabbit
pipeline_tag: text-to-image
tags:
- art
---
# Lora of hoto_mocha_istheorderarabbit
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 4760, you need to download `4760/hoto_mocha_istheorderarabbit.pt` as the embedding and `4760/hoto_mocha_istheorderarabbit.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 4760**, with the score of 0.592. The trigger words are:
1. `hoto_mocha_istheorderarabbit`
2. `long_hair, brown_hair, blush, bangs, indoors, smile, closed_mouth, purple_eyes`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 5100 | 0.545 | [Download](5100/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](5100/previews/bikini.png) | [<NSFW, click to see>](5100/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5100/previews/nude.png) | [<NSFW, click to see>](5100/previews/nude2.png) |  |  |
| **4760** | **0.592** | [**Download**](4760/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](4760/previews/bikini.png) | [<NSFW, click to see>](4760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4760/previews/nude.png) | [<NSFW, click to see>](4760/previews/nude2.png) |  |  |
| 4420 | 0.549 | [Download](4420/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](4420/previews/bikini.png) | [<NSFW, click to see>](4420/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4420/previews/nude.png) | [<NSFW, click to see>](4420/previews/nude2.png) |  |  |
| 4080 | 0.512 | [Download](4080/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](4080/previews/bikini.png) | [<NSFW, click to see>](4080/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4080/previews/nude.png) | [<NSFW, click to see>](4080/previews/nude2.png) |  |  |
| 3740 | 0.505 | [Download](3740/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](3740/previews/bikini.png) | [<NSFW, click to see>](3740/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3740/previews/nude.png) | [<NSFW, click to see>](3740/previews/nude2.png) |  |  |
| 3400 | 0.530 | [Download](3400/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](3400/previews/bikini.png) | [<NSFW, click to see>](3400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3400/previews/nude.png) | [<NSFW, click to see>](3400/previews/nude2.png) |  |  |
| 3060 | 0.447 | [Download](3060/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](3060/previews/bikini.png) | [<NSFW, click to see>](3060/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3060/previews/nude.png) | [<NSFW, click to see>](3060/previews/nude2.png) |  |  |
| 2720 | 0.381 | [Download](2720/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](2720/previews/bikini.png) | [<NSFW, click to see>](2720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2720/previews/nude.png) | [<NSFW, click to see>](2720/previews/nude2.png) |  |  |
| 2380 | 0.395 | [Download](2380/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](2380/previews/bikini.png) | [<NSFW, click to see>](2380/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2380/previews/nude.png) | [<NSFW, click to see>](2380/previews/nude2.png) |  |  |
| 2040 | 0.300 | [Download](2040/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](2040/previews/bikini.png) | [<NSFW, click to see>](2040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2040/previews/nude.png) | [<NSFW, click to see>](2040/previews/nude2.png) |  |  |
| 1700 | 0.293 | [Download](1700/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](1700/previews/bikini.png) | [<NSFW, click to see>](1700/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1700/previews/nude.png) | [<NSFW, click to see>](1700/previews/nude2.png) |  |  |
| 1360 | 0.369 | [Download](1360/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](1360/previews/bikini.png) | [<NSFW, click to see>](1360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1360/previews/nude.png) | [<NSFW, click to see>](1360/previews/nude2.png) |  |  |
| 1020 | 0.211 | [Download](1020/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](1020/previews/bikini.png) | [<NSFW, click to see>](1020/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1020/previews/nude.png) | [<NSFW, click to see>](1020/previews/nude2.png) |  |  |
| 680 | 0.207 | [Download](680/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](680/previews/bikini.png) | [<NSFW, click to see>](680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](680/previews/nude.png) | [<NSFW, click to see>](680/previews/nude2.png) |  |  |
| 340 | 0.130 | [Download](340/hoto_mocha_istheorderarabbit.zip) |  |  |  |  |  | [<NSFW, click to see>](340/previews/bikini.png) | [<NSFW, click to see>](340/previews/bondage.png) |  |  |  | [<NSFW, click to see>](340/previews/nude.png) | [<NSFW, click to see>](340/previews/nude2.png) |  |  |
|
joejoequte/test
|
joejoequte
| 2023-09-28T12:58:28Z | 1 | 0 |
transformers
|
[
"transformers",
"endpoints_compatible",
"region:us"
] | null | 2023-09-28T12:57:18Z |
# v2ray_for_Huggingface
在Huggingface搭建v2ray节点配置，Caddy+V2ray实现
需修改密码见config.json
|
ayoubkirouane/billsum-BART-base-cnn
|
ayoubkirouane
| 2023-09-28T12:56:18Z | 110 | 1 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"summarization",
"en",
"dataset:billsum",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-09-28T12:11:45Z |
---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: summarization
datasets:
- billsum
---
+ **Model Name**: billsum-BART-base-cnn
## **Description**:
This model is based on BART (Bidirectional and Auto-Regressive Transformers), originally introduced in the paper "BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension" by Lewis et al. It has been fine-tuned on the CNN Daily Mail dataset for the task of text summarization, specifically on the BillSum dataset, which consists of summaries of US Congressional and California state bills.
## Model Architecture:
BART is a transformer-based encoder-decoder (seq2seq) model with a bidirectional encoder and an autoregressive decoder. It excels in text generation tasks such as summarization and translation and is effective for comprehension tasks like text classification and question answering.
## Dataset Used:
The model has been fine-tuned on the BillSum dataset, which includes the following features:
+ **text**: The bill text.
+ **summary**: A summary of the bills.
+ **title**: The title of the bills (available for US bills only).
+ **text_len**: The number of characters in the text.
+ **sum_len**: The number of characters in the summary.
The data was collected from various sources, including the United States Government Publishing Office (GPO) and the California legislature's website.
## Uses:
+ **Text Summarization**:
This model can be used to generate concise summaries of longer text documents, making it suitable for applications like news article summarization, document summarization, and more.
## Limitations:
+ **Data Dependency**: The model's performance heavily relies on the quality and diversity of the training data. Fine-tuning on specific datasets may lead to biases or limitations inherent to those datasets.
+ **Length Constraints**: Like many sequence-to-sequence models, BART has length constraints. Longer input texts may result in truncated or incomplete summaries.
+ **Domain Specificity**: While fine-tuned on bill summaries, the model may not generalize well to other domains without further fine-tuning.
## Ethical Considerations:
+ **Bias**: Models like BART can inherit biases present in their training data. Care should be taken to evaluate and mitigate biases in generated content, especially when dealing with legal or legislative documents.
+ **Privacy**: When summarizing text, ensure that sensitive or private information is not inadvertently disclosed in the summaries.
+ **Accessibility**: Consider making model outputs accessible to individuals with disabilities, such as providing summaries in accessible formats.
## Usage :
```python
from transformers import pipeline
# Create a text generation pipeline with the specified model
pipe = pipeline("text2text-generation", model="ayoubkirouane/billsum-bart-base")
# Input text for summarization
input_text = """
Shields a business entity from civil liability relating to any injury or death occurring at a facility of that entity in connection with a use of such facility by a nonprofit organization if: (1) the use occurs outside the scope of business of the business entity; (2) such injury or death occurs during a period that such facility is used by such organization; and (3) the business entity authorized the use of such facility by the organization. Makes this Act inapplicable to an injury or death that results from an act or omission of a business entity that constitutes gross negligence or intentional misconduct, including misconduct that: (1) constitutes a hate crime or a crime of violence or act of international terrorism for which the defendant has been convicted in any court; or (2) involves a sexual offense for which the defendant has been convicted in any court or misconduct for which the defendant has been found to have violated a Federal or State civil rights law. Preempts State laws to the extent that such laws are inconsistent with this Act, except State law that provides additional protection from liability. Specifies that this Act shall not be construed to supersede any Federal or State health or safety law. Makes this Act inapplicable to any civil action in a State court against a business entity in which all parties are citizens of the State if such State, citing this Act's authority and containing no other provision, enacts a statute declaring the State's election that this Act shall not apply to such action in the State.
"""
# Generate the summary
summary = pipe(input_text, max_length=1024)
# Print the generated summary
print(summary[0]['summary_text'])
```
|
milaidy/jardepoz
|
milaidy
| 2023-09-28T12:53:54Z | 2 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T12:41:34Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### jardepoz Dreambooth model trained by milaidy with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
shahzain/whisper-sm-urdu-finetuned
|
shahzain
| 2023-09-28T12:52:20Z | 113 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-19T04:07:53Z |
---
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-sm-urdu-finetuned
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# whisper-sm-urdu-finetuned
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [Common Voice 13.0](https://huggingface.co/datasets/mozilla-foundation/common_voice_13_0/viewer/ur/train) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1777
- Wer: 36.0220
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.4017 | 0.18 | 1000 | 0.2591 | 65.3388 |
| 0.3963 | 0.36 | 2000 | 0.2135 | 43.6355 |
| 0.3162 | 0.54 | 3000 | 0.1880 | 35.8573 |
| 0.3479 | 0.72 | 4000 | 0.1777 | 36.0220 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
sjrhuschlee/flan-t5-large-squad2
|
sjrhuschlee
| 2023-09-28T12:43:10Z | 203,176 | 4 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"question-answering",
"squad",
"squad_v2",
"lora",
"peft",
"custom_code",
"en",
"dataset:squad_v2",
"dataset:squad",
"base_model:google/flan-t5-large",
"base_model:adapter:google/flan-t5-large",
"license:mit",
"model-index",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-14T07:23:45Z |
---
language:
- en
license: mit
library_name: transformers
tags:
- question-answering
- squad
- squad_v2
- t5
- lora
- peft
datasets:
- squad_v2
- squad
base_model: google/flan-t5-large
model-index:
- name: sjrhuschlee/flan-t5-large-squad2
results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 86.819
name: Exact Match
- type: f1
value: 89.569
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squad
type: squad
config: plain_text
split: validation
metrics:
- type: exact_match
value: 89.357
name: Exact Match
- type: f1
value: 95.060
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: adversarial_qa
type: adversarial_qa
config: adversarialQA
split: validation
metrics:
- type: exact_match
value: 48.833
name: Exact Match
- type: f1
value: 62.555
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_adversarial
type: squad_adversarial
config: AddOneSent
split: validation
metrics:
- type: exact_match
value: 84.835
name: Exact Match
- type: f1
value: 90.245
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squadshifts amazon
type: squadshifts
config: amazon
split: test
metrics:
- type: exact_match
value: 76.722
name: Exact Match
- type: f1
value: 89.680
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squadshifts new_wiki
type: squadshifts
config: new_wiki
split: test
metrics:
- type: exact_match
value: 84.316
name: Exact Match
- type: f1
value: 92.967
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squadshifts nyt
type: squadshifts
config: nyt
split: test
metrics:
- type: exact_match
value: 86.925
name: Exact Match
- type: f1
value: 94.064
name: F1
- task:
type: question-answering
name: Question Answering
dataset:
name: squadshifts reddit
type: squadshifts
config: reddit
split: test
metrics:
- type: exact_match
value: 78.241
name: Exact Match
- type: f1
value: 89.243
name: F1
---
# flan-t5-large for Extractive QA
This is the [flan-t5-large](https://huggingface.co/google/flan-t5-large) model, fine-tuned using the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering.
**UPDATE:** With transformers version 4.31.0 the `use_remote_code=True` is no longer necessary.
This model was trained using LoRA available through the [PEFT library](https://github.com/huggingface/peft).
**NOTE:** The `<cls>` token must be manually added to the beginning of the question for this model to work properly. It uses the `<cls>` token to be able to make "no answer" predictions. The t5 tokenizer does not automatically add this special token which is why it is added manually.
## Overview
**Language model:** flan-t5-large
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** SQuAD 2.0
**Eval data:** SQuAD 2.0
**Infrastructure**: 1x NVIDIA 3070
## Model Usage
### Using Transformers
This uses the merged weights (base model weights + LoRA weights) to allow for simple use in Transformers pipelines. It has the same performance as using the weights separately when using the PEFT library.
```python
import torch
from transformers import(
AutoModelForQuestionAnswering,
AutoTokenizer,
pipeline
)
model_name = "sjrhuschlee/flan-t5-large-squad2"
# a) Using pipelines
nlp = pipeline(
'question-answering',
model=model_name,
tokenizer=model_name,
# trust_remote_code=True, # Do not use if version transformers>=4.31.0
)
qa_input = {
'question': f'{nlp.tokenizer.cls_token}Where do I live?', # '<cls>Where do I live?'
'context': 'My name is Sarah and I live in London'
}
res = nlp(qa_input)
# {'score': 0.984, 'start': 30, 'end': 37, 'answer': ' London'}
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(
model_name,
# trust_remote_code=True # Do not use if version transformers>=4.31.0
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
question = f'{tokenizer.cls_token}Where do I live?' # '<cls>Where do I live?'
context = 'My name is Sarah and I live in London'
encoding = tokenizer(question, context, return_tensors="pt")
output = model(
encoding["input_ids"],
attention_mask=encoding["attention_mask"]
)
all_tokens = tokenizer.convert_ids_to_tokens(encoding["input_ids"][0].tolist())
answer_tokens = all_tokens[torch.argmax(output["start_logits"]):torch.argmax(output["end_logits"]) + 1]
answer = tokenizer.decode(tokenizer.convert_tokens_to_ids(answer_tokens))
# 'London'
```
## Metrics
```bash
# Squad v2
{
"eval_HasAns_exact": 85.08771929824562,
"eval_HasAns_f1": 90.598422845031,
"eval_HasAns_total": 5928,
"eval_NoAns_exact": 88.47771236333053,
"eval_NoAns_f1": 88.47771236333053,
"eval_NoAns_total": 5945,
"eval_best_exact": 86.78514276088605,
"eval_best_exact_thresh": 0.0,
"eval_best_f1": 89.53654936623764,
"eval_best_f1_thresh": 0.0,
"eval_exact": 86.78514276088605,
"eval_f1": 89.53654936623776,
"eval_runtime": 1908.3189,
"eval_samples": 12001,
"eval_samples_per_second": 6.289,
"eval_steps_per_second": 0.787,
"eval_total": 11873
}
# Squad
{
"eval_HasAns_exact": 85.99810785241249,
"eval_HasAns_f1": 91.296119057944,
"eval_HasAns_total": 10570,
"eval_best_exact": 85.99810785241249,
"eval_best_exact_thresh": 0.0,
"eval_best_f1": 91.296119057944,
"eval_best_f1_thresh": 0.0,
"eval_exact": 85.99810785241249,
"eval_f1": 91.296119057944,
"eval_runtime": 1508.9596,
"eval_samples": 10657,
"eval_samples_per_second": 7.062,
"eval_steps_per_second": 0.883,
"eval_total": 10570
}
```
### Using with Peft
**NOTE**: This requires code in the PR https://github.com/huggingface/peft/pull/473 for the PEFT library.
```python
#!pip install peft
from peft import LoraConfig, PeftModelForQuestionAnswering
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model_name = "sjrhuschlee/flan-t5-large-squad2"
```
|
mHossain/bangla_idiom_generation_v3
|
mHossain
| 2023-09-28T12:36:51Z | 103 | 1 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-28T12:20:38Z |
---
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bangla_idiom_generation_v3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bangla_idiom_generation_v3
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.5201
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 10.8938
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 226 | 4.7622 | 0.0 | 0.0 | 0.0 | 0.0 | 10.5398 |
| No log | 2.0 | 452 | 4.7514 | 0.0 | 0.0 | 0.0 | 0.0 | 10.6018 |
| 5.1485 | 3.0 | 678 | 4.7347 | 0.0 | 0.0 | 0.0 | 0.0 | 11.2478 |
| 5.1485 | 4.0 | 904 | 4.7101 | 0.0 | 0.0 | 0.0 | 0.0 | 11.9912 |
| 5.0936 | 5.0 | 1130 | 4.6840 | 0.0 | 0.0 | 0.0 | 0.0 | 12.0841 |
| 5.0936 | 6.0 | 1356 | 4.6527 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1991 |
| 4.9965 | 7.0 | 1582 | 4.6199 | 0.0 | 0.0 | 0.0 | 0.0 | 12.5044 |
| 4.9965 | 8.0 | 1808 | 4.5845 | 0.0 | 0.0 | 0.0 | 0.0 | 11.8761 |
| 4.8494 | 9.0 | 2034 | 4.5543 | 0.0 | 0.0 | 0.0 | 0.0 | 11.5398 |
| 4.8494 | 10.0 | 2260 | 4.5201 | 0.0 | 0.0 | 0.0 | 0.0 | 10.8938 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
milaidy/heatherr
|
milaidy
| 2023-09-28T12:35:45Z | 3 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T12:22:52Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### heatherr Dreambooth model trained by milaidy with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
RaghadAbdulrab/ppo-LunarLander-v1
|
RaghadAbdulrab
| 2023-09-28T12:33:33Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T12:31:26Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 246.98 +/- 14.35
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
badokorach/flan-t5-small-qa-9-qa-91
|
badokorach
| 2023-09-28T12:28:24Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:badokorach/flan-t5-small-qa-9",
"base_model:finetune:badokorach/flan-t5-small-qa-9",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-28T09:51:48Z |
---
license: apache-2.0
base_model: badokorach/flan-t5-small-qa-9
tags:
- generated_from_trainer
model-index:
- name: flan-t5-small-qa-9-qa-91
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# flan-t5-small-qa-9-qa-91
This model is a fine-tuned version of [badokorach/flan-t5-small-qa-9](https://huggingface.co/badokorach/flan-t5-small-qa-9) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1084
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 343 | 0.1041 |
| 0.0207 | 2.0 | 686 | 0.1041 |
| 0.0196 | 3.0 | 1029 | 0.1057 |
| 0.0196 | 4.0 | 1372 | 0.1052 |
| 0.0186 | 5.0 | 1715 | 0.1043 |
| 0.0173 | 6.0 | 2058 | 0.1050 |
| 0.0173 | 7.0 | 2401 | 0.1079 |
| 0.0165 | 8.0 | 2744 | 0.1068 |
| 0.0161 | 9.0 | 3087 | 0.1081 |
| 0.0161 | 10.0 | 3430 | 0.1084 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3
|
CJ-gyuwonpark/ch-70b-v2
|
CJ-gyuwonpark
| 2023-09-28T12:26:00Z | 0 | 0 |
peft
|
[
"peft",
"llama",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2023-09-26T06:05:50Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ
|
TheBloke
| 2023-09-28T12:20:48Z | 41 | 4 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"custom_code",
"en",
"de",
"dataset:LeoLM/OpenSchnabeltier",
"dataset:OpenAssistant/OASST-DE",
"dataset:FreedomIntelligence/alpaca-gpt4-deutsch",
"dataset:FreedomIntelligence/evol-instruct-deutsch",
"dataset:LeoLM/German_Poems",
"dataset:LeoLM/German_Songs",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_70k",
"dataset:bjoernp/oasst25-08-23-filtered",
"base_model:LeoLM/leo-hessianai-13b-chat-bilingual",
"base_model:quantized:LeoLM/leo-hessianai-13b-chat-bilingual",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-09-28T10:56:50Z |
---
base_model: LeoLM/leo-hessianai-13b-chat-bilingual
datasets:
- LeoLM/OpenSchnabeltier
- OpenAssistant/OASST-DE
- FreedomIntelligence/alpaca-gpt4-deutsch
- FreedomIntelligence/evol-instruct-deutsch
- LeoLM/German_Poems
- LeoLM/German_Songs
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_70k
- bjoernp/oasst25-08-23-filtered
inference: false
language:
- en
- de
library_name: transformers
license: llama2
model_creator: LAION LeoLM
model_name: Leo Hessianai 13B Chat Bilingual
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Leo Hessianai 13B Chat Bilingual - GPTQ
- Model creator: [LAION LeoLM](https://huggingface.co/LeoLM)
- Original model: [Leo Hessianai 13B Chat Bilingual](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual)
<!-- description start -->
## Description
This repo contains GPTQ model files for [LAION LeoLM's Leo Hessianai 13B Chat Bilingual](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF)
* [LAION LeoLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 8.01 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 13.66 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `leo-hessianai-13B-chat-bilingual-GPTQ`:
```shell
mkdir leo-hessianai-13B-chat-bilingual-GPTQ
huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ --local-dir leo-hessianai-13B-chat-bilingual-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir leo-hessianai-13B-chat-bilingual-GPTQ
huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir leo-hessianai-13B-chat-bilingual-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir leo-hessianai-13B-chat-bilingual-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ --local-dir leo-hessianai-13B-chat-bilingual-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `leo-hessianai-13B-chat-bilingual-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: LAION LeoLM's Leo Hessianai 13B Chat Bilingual
# LAION LeoLM: **L**inguistically **E**nhanced **O**pen **L**anguage **M**odel
Meet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2.
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.
Thanks to a compute grant at HessianAI's new supercomputer **42**, we release two foundation models trained with 8k context length,
[`LeoLM/leo-hessianai-7b`](https://huggingface.co/LeoLM/leo-hessianai-7b) and [`LeoLM/leo-hessianai-13b`](https://huggingface.co/LeoLM/leo-hessianai-13b) under the [Llama-2 community license](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt) (70b also coming soon! 👀).
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.
Read our [blog post]() or our paper (preprint coming soon) for more details!
*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*
## LeoLM Chat
`LeoLM/leo-hessianai-13b-chat-bilingual` is a bilingual English-German chat model built on our foundation model `LeoLM/leo-hessianai-13b` and finetuned on a selection of German translateed instruction datasets and their English counterparts.
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench scores:
```
{
"first_turn": 6.13125,
"second_turn": 4.88125,
"categories": {
"writing": 6.75,
"roleplay": 5.55,
"reasoning": 3.3,
"math": 2.25,
"coding": 3.9,
"extraction": 5.8,
"stem": 7.55,
"humanities": 8.95
},
"average": 5.50625
}
```
## Model Details
- **Finetuned from:** [LeoLM/leo-hessianai-13b](https://huggingface.co/LeoLM/leo-hessianai-13b)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English and German
- **Demo:** [Web Demo]()
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [LAION Discord](https://discord.com/invite/eq3cAMZtCC) or [Björn Plüster](mailto:bjoern.pl@outlook.de)
## Use in 🤗Transformers
First install direct dependencies:
```
pip install transformers torch sentencepiece
```
If you want faster inference using flash-attention2, you need to install these dependencies:
```bash
pip install packaging ninja
pip install flash-attn==v2.1.1 --no-build-isolation
pip install git+https://github.com/HazyResearch/flash-attention.git@v2.1.1#subdirectory=csrc/rotary
```
Then load the model in transformers:
```python
from transformers import pipeline
import torch
system_prompt = """<|im_start|>system
Dies ist eine Unterhaltung zwischen einem intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt ausführliche, hilfreiche und ehrliche Antworten.<|im_end|>
"""
prompt_format = "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
prompt = "Erkläre mir wie die Fahrradwegesituation in Hamburg ist."
generator = pipeline(model="LeoLM/leo-hessianai-13b-chat-bilingual", device="cuda", torch_dtype=torch.float16, trust_remote_code=True) # True for flash-attn2 else False
print(generator(prompt_format.format(prompt=prompt), do_sample=True, top_p=0.95, max_length=8192))
```
"*Als KI kann ich keine persönlichen Beobachtungen teilen, aber ich kann einige allgemeine Informationen zur Fahrradwegesituation in Hamburg liefern. Im Vergleich zu vielen anderen großen Städten hat Hamburg eine hohe Anzahl von Fahrradfahrern und nimmt seine Verantwortung für nachhaltige Verkehrsmittel sehr ernst. Es gibt viele Fahrradwege und separate Fahrspuren, die Radfahrern ermöglichen, zusammen mit dem Autoverkehr zu fahren. Diese Fahrradspuren sind oft mit Markierungen gekennzeichnet und durch physische Trennungen von anderen Fahrspuren abgegrenzt. Darüber hinaus gibt es viele Fahrradstraßen, auf denen Radfahrer Vorfahrt haben und Autos langsamer fahren müssen.*
*In einigen städtischen Gebieten können Fahrradwege jedoch eng oder überfüllt sein, besonders während der Stoßzeiten. Es gibt auch viele Kreuzungen, an denen Radfahrer anhalten und auf Grün warten müssen, ähnlich wie Autofahrer. Insgesamt ist die Fahrradinfrastruktur in Hamburg ziemlich gut, aber wie überall gibt es immer Raum für Verbesserungen.*"
## Prompting / Prompt Template
Prompt dialogue template (ChatML format):
```
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
```
The model input can contain multiple conversation turns between user and assistant, e.g.
```
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
```
## Ethical Considerations and Limitations
LeoLM has been tested in English and German, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of `LeoLM/leo-hessianai-7b-chat` cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-7b-chat`, developers should
perform safety testing and tuning tailored to their specific applications of the model.
Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
## Finetuning Details
| Hyperparameter | Value |
|---|---|
| Num epochs | 3 |
| Examples per epoch | 233275 |
| Global batch size | 256 |
| Learning rate | 3e-5 |
| Warmup steps | 100 |
| LR scheduler | Cosine |
| Adam betas | (0.9, 0.95) |
| Weight decay | 0.001 |
## Dataset Details
```
## Stats for 'Subset of LeoLM/OpenSchnabeltier' (21314 samples (100.0%))
-----------------
Accepted: 21314/21314 (100.0%)
Accepted tokens: 8134690
Skipped: 0 (0.0%)
Min tokens per sample: 25
Max tokens per sample: 1202
Avg tokens per sample: 381.65947264708643
-----------------
## Stats for 'Subset of garage-bAInd/Open-Platypus' (24427 samples (100.0%))
-----------------
Accepted: 24427/24427 (100.0%)
Accepted tokens: 9549043
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5054
Avg tokens per sample: 390.9216440823679
-----------------
## Stats for 'Subset of WizardLM/WizardLM_evol_instruct_70k' (68600 samples (100.0%))
-----------------
Accepted: 68600/68600 (100.0%)
Accepted tokens: 33045040
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 481.7061224489796
-----------------
## Stats for 'Subset of FreedomIntelligence/evol-instruct-deutsch' (57841 samples (100.0%))
-----------------
Accepted: 57841/57841 (100.0%)
Accepted tokens: 42958192
Skipped: 0 (0.0%)
Min tokens per sample: 33
Max tokens per sample: 5507
Avg tokens per sample: 742.6944900675991
-----------------
## Stats for 'Subset of FreedomIntelligence/alpaca-gpt4-deutsch' (48969 samples (100.0%))
-----------------
Accepted: 48969/48969 (100.0%)
Accepted tokens: 13372005
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 1359
Avg tokens per sample: 273.07082031489307
-----------------
## Stats for 'Subset of LeoLM/German_Songs' (490 samples (100.0%))
-----------------
Accepted: 490/490 (100.0%)
Accepted tokens: 618642
Skipped: 0 (0.0%)
Min tokens per sample: 747
Max tokens per sample: 1678
Avg tokens per sample: 1262.534693877551
-----------------
## Stats for 'Subset of LeoLM/German_Poems' (392 samples (100.0%))
-----------------
Accepted: 392/392 (100.0%)
Accepted tokens: 187897
Skipped: 0 (0.0%)
Min tokens per sample: 231
Max tokens per sample: 826
Avg tokens per sample: 479.3290816326531
-----------------
## Stats for 'Subset of OpenAssistant/OASST_DE' (3646 samples (100.0%))
-----------------
Accepted: 3646/3646 (100.0%)
Accepted tokens: 2338738
Skipped: 0 (0.0%)
Min tokens per sample: 29
Max tokens per sample: 2484
Avg tokens per sample: 641.4530992868897
-----------------
## Stats for 'Subset of bjoernp/oasst25-08-23-filtered' (8922 samples (100.0%))
-----------------
Accepted: 8922/8922 (100.0%)
Accepted tokens: 4526427
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5407
Avg tokens per sample: 507.3332212508406
-----------------
## Stats for 'total' (235632 samples (100.0%))
-----------------
Accepted: 235632/235632 (100.0%)
Accepted tokens: 115862397
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 491.70909299246284
-----------------
```
|
mHossain/bangla_idiom_generation_v2
|
mHossain
| 2023-09-28T12:11:45Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:mHossain/bangla-para-v3-500000",
"base_model:finetune:mHossain/bangla-para-v3-500000",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-28T11:29:55Z |
---
base_model: mHossain/bangla-para-v3-500000
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bangla_idiom_generation_v2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bangla_idiom_generation_v2
This model is a fine-tuned version of [mHossain/bangla-para-v3-500000](https://huggingface.co/mHossain/bangla-para-v3-500000) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7655
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 10.4292
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 226 | 7.4650 | 0.0 | 0.0 | 0.0 | 0.0 | 11.1195 |
| No log | 2.0 | 452 | 7.1989 | 0.0 | 0.0 | 0.0 | 0.0 | 10.677 |
| 7.7649 | 3.0 | 678 | 6.8146 | 0.0 | 0.0 | 0.0 | 0.0 | 9.8938 |
| 7.7649 | 4.0 | 904 | 6.3650 | 0.0 | 0.0 | 0.0 | 0.0 | 9.3805 |
| 7.0991 | 5.0 | 1130 | 5.8781 | 0.0 | 0.0 | 0.0 | 0.0 | 9.2478 |
| 7.0991 | 6.0 | 1356 | 5.4460 | 0.0 | 0.0 | 0.0 | 0.0 | 9.0487 |
| 6.1699 | 7.0 | 1582 | 5.1824 | 0.0 | 0.0 | 0.0 | 0.0 | 9.3363 |
| 6.1699 | 8.0 | 1808 | 4.9930 | 0.0 | 0.0 | 0.0 | 0.0 | 10.2478 |
| 5.5395 | 9.0 | 2034 | 4.8596 | 0.0 | 0.0 | 0.0 | 0.0 | 10.5575 |
| 5.5395 | 10.0 | 2260 | 4.7655 | 0.0 | 0.0 | 0.0 | 0.0 | 10.4292 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
fsarab/ppo-Huggy
|
fsarab
| 2023-09-28T12:08:54Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-28T12:08:48Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: fsarab/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
yudiwbs/absa_elektronik_aspek_v2
|
yudiwbs
| 2023-09-28T11:52:36Z | 0 | 0 |
flair
|
[
"flair",
"pytorch",
"token-classification",
"sequence-tagger-model",
"region:us"
] |
token-classification
| 2023-09-24T13:59:16Z |
---
tags:
- flair
- token-classification
- sequence-tagger-model
widget:
- text: "Sesuai diskusi. Barang mulus walau ada hairline scratch di casing depan. Battery masih awet. Dapat bonus keyboard jp jg. Thanks gan."
---
Klasifikasi aspek dalam review laptop
### Demo: How to use in Flair
Requires:
- **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
```python
from flair.data import Sentence
from flair.models import SequenceTagger
# load tagger
tagger = SequenceTagger.load("yudiwbs/absa_elektronik_aspek_v2")
sentence = Sentence('Sesuai diskusi. Barang mulus walau ada hairline scratch di casing depan. Battery masih awet. Dapat bonus jg. Thanks gan.')
# predict
model.predict(sentence)
print(sentence.to_tagged_string())
# iterate over entities and print
for entity in sentence.get_spans('aspek'):
print(entity)
```
|
facebook/regnet-y-320-seer
|
facebook
| 2023-09-28T11:50:27Z | 213 | 2 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"regnet",
"image-feature-extraction",
"vision",
"arxiv:2202.08360",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
image-feature-extraction
| 2022-03-18T13:51:03Z |
---
license: apache-2.0
tags:
- vision
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
example_title: Palace
---
# RegNetModel
RegNetModel model was introduced in the paper [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://arxiv.org/abs/2202.08360) and first released in [this repository](https://github.com/facebookresearch/vissl/tree/main/projects/SEER).
Disclaimer: The team releasing RegNetModel did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The authors trained [RegNets](https://huggingface.co/?models=regnet) models in a self-supervised fashion on bilion of random images from the internet
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=regnet) to look for
fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
>>> from transformers import AutoFeatureExtractor, RegNetModel
>>> import torch
>>> from datasets import load_dataset
>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("zuppif/regnet-y-040")
>>> model = RegNetModel.from_pretrained("zuppif/regnet-y-040")
>>> inputs = feature_extractor(image, return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 1088, 7, 7]
```
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/regnet).
|
dss107/news6
|
dss107
| 2023-09-28T11:48:29Z | 4 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-09-28T11:47:14Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# dss107/news6
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("dss107/news6")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
hmxiong/ScanNet_Finetune_global_guidance_10epoch_bs64
|
hmxiong
| 2023-09-28T11:47:16Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-28T02:29:07Z |
每个场景使用的是全部的18个类别信息
|
hmxiong/ScanNet_Finetune_local_guidance_10epoch_bs64
|
hmxiong
| 2023-09-28T11:46:37Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-28T02:29:57Z |
训练阶段使用每个场景存在的类别
|
devdata/common_beanv2
|
devdata
| 2023-09-28T11:38:18Z | 0 | 0 |
fastai
|
[
"fastai",
"region:us"
] | null | 2023-09-27T15:55:30Z |
---
tags:
- fastai
---
# Amazing!
🥳 Congratulations on hosting your fastai model on the Hugging Face Hub!
# Some next steps
1. Fill out this model card with more information (see the template below and the [documentation here](https://huggingface.co/docs/hub/model-repos))!
2. Create a demo in Gradio or Streamlit using 🤗 Spaces ([documentation here](https://huggingface.co/docs/hub/spaces)).
3. Join the fastai community on the [Fastai Discord](https://discord.com/invite/YKrxeNn)!
Greetings fellow fastlearner 🤝! Don't forget to delete this content from your model card.
---
# Model card
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
|
massh3dpotato/Llama-2-7B-chat-GGML
|
massh3dpotato
| 2023-09-28T11:37:54Z | 8 | 0 |
transformers
|
[
"transformers",
"llama",
"facebook",
"meta",
"pytorch",
"llama-2",
"text-generation",
"en",
"arxiv:2307.09288",
"base_model:meta-llama/Llama-2-13b-chat-hf",
"base_model:finetune:meta-llama/Llama-2-13b-chat-hf",
"license:other",
"region:us"
] |
text-generation
| 2023-09-28T11:34:46Z |
---
language:
- en
license: other
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
model_name: Llama 2 13B Chat
inference: false
model_creator: Meta Llama 2
model_link: https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
model_type: llama
pipeline_tag: text-generation
quantized_by: TheBloke
base_model: meta-llama/Llama-2-13b-chat-hf
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Llama 2 13B Chat - GGML
- Model creator: [Meta Llama 2](https://huggingface.co/meta-llama)
- Original model: [Llama 2 13B Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
## Description
This repo contains GGML format model files for [Meta's Llama 2 13B-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf).
### Important note regarding GGML files.
The GGML format has now been superseded by GGUF. As of August 21st 2023, [llama.cpp](https://github.com/ggerganov/llama.cpp) no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support.
Please use the GGUF models instead.
### About GGML
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with CUDA GPU acceleration via the c_transformers backend.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML)
* [Meta Llama 2's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-llama/Llama-2-13B-chat-hf)
## Prompt template: Llama-2-Chat
```
[INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{prompt}[/INST]
```
<!-- compatibility_ggml start -->
## Compatibility
These quantised GGML files are compatible with llama.cpp between June 6th (commit `2d43387`) and August 21st 2023.
For support with latest llama.cpp, please use GGUF files instead.
The final llama.cpp commit with support for GGML was: [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa)
As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future.
## Explanation of the new k-quant methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [llama-2-13b-chat.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q2_K.bin) | q2_K | 2 | 5.51 GB| 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| [llama-2-13b-chat.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 5.66 GB| 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| [llama-2-13b-chat.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 6.31 GB| 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| [llama-2-13b-chat.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 6.93 GB| 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| [llama-2-13b-chat.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
| [llama-2-13b-chat.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 7.37 GB| 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| [llama-2-13b-chat.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 7.87 GB| 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| [llama-2-13b-chat.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_1.bin) | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| [llama-2-13b-chat.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_0.bin) | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| [llama-2-13b-chat.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 8.97 GB| 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| [llama-2-13b-chat.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 9.23 GB| 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| [llama-2-13b-chat.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_1.bin) | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| [llama-2-13b-chat.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q6_K.bin) | q6_K | 6 | 10.68 GB| 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
| [llama-2-13b-chat.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q8_0.bin) | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
Make sure you are using `llama.cpp` from commit [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) or earlier.
For compatibility with latest llama.cpp, please use GGUF files instead.
```
./main -t 10 -ngl 32 -m llama-2-13b-chat.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\nWrite a story about llamas[/INST]"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length for this model. For example, `-c 4096` for a Llama 2 model. For models that use RoPE, add `--rope-freq-base 10000 --rope-freq-scale 0.5` for doubled context, or `--rope-freq-base 10000 --rope-freq-scale 0.25` for 4x context.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Meta's Llama 2 13B-chat
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 13B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Meta’s sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software “bug,” or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
|
Pranjal12345/whisper-small-ne-pranjal
|
Pranjal12345
| 2023-09-28T11:14:22Z | 76 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ne",
"dataset:mozilla-foundation/common_voice_11_0",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-22T06:30:06Z |
---
language:
- ne
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Small Nepali - Pranjal Khadka
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Nepali - Pranjal Khadka
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0001
- eval_wer: 0.0
- eval_runtime: 5.3111
- eval_samples_per_second: 0.753
- eval_steps_per_second: 0.188
- epoch: 76.92
- step: 1000
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
TheBloke/leo-hessianai-13B-chat-bilingual-GGUF
|
TheBloke
| 2023-09-28T11:11:33Z | 288 | 6 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"en",
"de",
"dataset:LeoLM/OpenSchnabeltier",
"dataset:OpenAssistant/OASST-DE",
"dataset:FreedomIntelligence/alpaca-gpt4-deutsch",
"dataset:FreedomIntelligence/evol-instruct-deutsch",
"dataset:LeoLM/German_Poems",
"dataset:LeoLM/German_Songs",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_70k",
"dataset:bjoernp/oasst25-08-23-filtered",
"base_model:LeoLM/leo-hessianai-13b-chat-bilingual",
"base_model:quantized:LeoLM/leo-hessianai-13b-chat-bilingual",
"license:llama2",
"region:us"
] |
text-generation
| 2023-09-28T10:56:39Z |
---
base_model: LeoLM/leo-hessianai-13b-chat-bilingual
datasets:
- LeoLM/OpenSchnabeltier
- OpenAssistant/OASST-DE
- FreedomIntelligence/alpaca-gpt4-deutsch
- FreedomIntelligence/evol-instruct-deutsch
- LeoLM/German_Poems
- LeoLM/German_Songs
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_70k
- bjoernp/oasst25-08-23-filtered
inference: false
language:
- en
- de
library_name: transformers
license: llama2
model_creator: LAION LeoLM
model_name: Leo Hessianai 13B Chat Bilingual
model_type: llama
pipeline_tag: text-generation
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Leo Hessianai 13B Chat Bilingual - GGUF
- Model creator: [LAION LeoLM](https://huggingface.co/LeoLM)
- Original model: [Leo Hessianai 13B Chat Bilingual](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual)
<!-- description start -->
## Description
This repo contains GGUF format model files for [LAION LeoLM's Leo Hessianai 13B Chat Bilingual](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF)
* [LAION LeoLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/LeoLM/leo-hessianai-13b-chat-bilingual)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [leo-hessianai-13b-chat-bilingual.Q2_K.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [leo-hessianai-13b-chat-bilingual.Q3_K_S.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [leo-hessianai-13b-chat-bilingual.Q3_K_M.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [leo-hessianai-13b-chat-bilingual.Q3_K_L.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [leo-hessianai-13b-chat-bilingual.Q4_0.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [leo-hessianai-13b-chat-bilingual.Q4_K_S.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q4_K_S.gguf) | Q4_K_S | 4 | 7.42 GB| 9.92 GB | small, greater quality loss |
| [leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [leo-hessianai-13b-chat-bilingual.Q5_0.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [leo-hessianai-13b-chat-bilingual.Q5_K_S.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [leo-hessianai-13b-chat-bilingual.Q5_K_M.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [leo-hessianai-13b-chat-bilingual.Q6_K.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [leo-hessianai-13b-chat-bilingual.Q8_0.gguf](https://huggingface.co/TheBloke/leo-hessianai-13B-chat-bilingual-GGUF/blob/main/leo-hessianai-13b-chat-bilingual.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/leo-hessianai-13B-chat-bilingual-GGUF and below it, a specific filename to download, such as: leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GGUF leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/leo-hessianai-13B-chat-bilingual-GGUF leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/leo-hessianai-13B-chat-bilingual-GGUF", model_file="leo-hessianai-13b-chat-bilingual.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: LAION LeoLM's Leo Hessianai 13B Chat Bilingual
# LAION LeoLM: **L**inguistically **E**nhanced **O**pen **L**anguage **M**odel
Meet LeoLM, the first open and commercially available German Foundation Language Model built on Llama-2.
Our models extend Llama-2's capabilities into German through continued pretraining on a large corpus of German-language and mostly locality specific text.
Thanks to a compute grant at HessianAI's new supercomputer **42**, we release two foundation models trained with 8k context length,
[`LeoLM/leo-hessianai-7b`](https://huggingface.co/LeoLM/leo-hessianai-7b) and [`LeoLM/leo-hessianai-13b`](https://huggingface.co/LeoLM/leo-hessianai-13b) under the [Llama-2 community license](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt) (70b also coming soon! 👀).
With this release, we hope to bring a new wave of opportunities to German open-source and commercial LLM research and accelerate adoption.
Read our [blog post]() or our paper (preprint coming soon) for more details!
*A project by Björn Plüster and Christoph Schuhmann in collaboration with LAION and HessianAI.*
## LeoLM Chat
`LeoLM/leo-hessianai-13b-chat-bilingual` is a bilingual English-German chat model built on our foundation model `LeoLM/leo-hessianai-13b` and finetuned on a selection of German translateed instruction datasets and their English counterparts.
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench scores:
```
{
"first_turn": 6.13125,
"second_turn": 4.88125,
"categories": {
"writing": 6.75,
"roleplay": 5.55,
"reasoning": 3.3,
"math": 2.25,
"coding": 3.9,
"extraction": 5.8,
"stem": 7.55,
"humanities": 8.95
},
"average": 5.50625
}
```
## Model Details
- **Finetuned from:** [LeoLM/leo-hessianai-13b](https://huggingface.co/LeoLM/leo-hessianai-13b)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English and German
- **Demo:** [Web Demo]()
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [LAION Discord](https://discord.com/invite/eq3cAMZtCC) or [Björn Plüster](mailto:bjoern.pl@outlook.de)
## Use in 🤗Transformers
First install direct dependencies:
```
pip install transformers torch sentencepiece
```
If you want faster inference using flash-attention2, you need to install these dependencies:
```bash
pip install packaging ninja
pip install flash-attn==v2.1.1 --no-build-isolation
pip install git+https://github.com/HazyResearch/flash-attention.git@v2.1.1#subdirectory=csrc/rotary
```
Then load the model in transformers:
```python
from transformers import pipeline
import torch
system_prompt = """<|im_start|>system
Dies ist eine Unterhaltung zwischen einem intelligenten, hilfsbereitem KI-Assistenten und einem Nutzer.
Der Assistent gibt ausführliche, hilfreiche und ehrliche Antworten.<|im_end|>
"""
prompt_format = "<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
prompt = "Erkläre mir wie die Fahrradwegesituation in Hamburg ist."
generator = pipeline(model="LeoLM/leo-hessianai-13b-chat-bilingual", device="cuda", torch_dtype=torch.float16, trust_remote_code=True) # True for flash-attn2 else False
print(generator(prompt_format.format(prompt=prompt), do_sample=True, top_p=0.95, max_length=8192))
```
"*Als KI kann ich keine persönlichen Beobachtungen teilen, aber ich kann einige allgemeine Informationen zur Fahrradwegesituation in Hamburg liefern. Im Vergleich zu vielen anderen großen Städten hat Hamburg eine hohe Anzahl von Fahrradfahrern und nimmt seine Verantwortung für nachhaltige Verkehrsmittel sehr ernst. Es gibt viele Fahrradwege und separate Fahrspuren, die Radfahrern ermöglichen, zusammen mit dem Autoverkehr zu fahren. Diese Fahrradspuren sind oft mit Markierungen gekennzeichnet und durch physische Trennungen von anderen Fahrspuren abgegrenzt. Darüber hinaus gibt es viele Fahrradstraßen, auf denen Radfahrer Vorfahrt haben und Autos langsamer fahren müssen.*
*In einigen städtischen Gebieten können Fahrradwege jedoch eng oder überfüllt sein, besonders während der Stoßzeiten. Es gibt auch viele Kreuzungen, an denen Radfahrer anhalten und auf Grün warten müssen, ähnlich wie Autofahrer. Insgesamt ist die Fahrradinfrastruktur in Hamburg ziemlich gut, aber wie überall gibt es immer Raum für Verbesserungen.*"
## Prompting / Prompt Template
Prompt dialogue template (ChatML format):
```
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
```
The model input can contain multiple conversation turns between user and assistant, e.g.
```
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
```
## Ethical Considerations and Limitations
LeoLM has been tested in English and German, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of `LeoLM/leo-hessianai-7b-chat` cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of `LeoLM/leo-hessianai-7b-chat`, developers should
perform safety testing and tuning tailored to their specific applications of the model.
Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
## Finetuning Details
| Hyperparameter | Value |
|---|---|
| Num epochs | 3 |
| Examples per epoch | 233275 |
| Global batch size | 256 |
| Learning rate | 3e-5 |
| Warmup steps | 100 |
| LR scheduler | Cosine |
| Adam betas | (0.9, 0.95) |
| Weight decay | 0.001 |
## Dataset Details
```
## Stats for 'Subset of LeoLM/OpenSchnabeltier' (21314 samples (100.0%))
-----------------
Accepted: 21314/21314 (100.0%)
Accepted tokens: 8134690
Skipped: 0 (0.0%)
Min tokens per sample: 25
Max tokens per sample: 1202
Avg tokens per sample: 381.65947264708643
-----------------
## Stats for 'Subset of garage-bAInd/Open-Platypus' (24427 samples (100.0%))
-----------------
Accepted: 24427/24427 (100.0%)
Accepted tokens: 9549043
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5054
Avg tokens per sample: 390.9216440823679
-----------------
## Stats for 'Subset of WizardLM/WizardLM_evol_instruct_70k' (68600 samples (100.0%))
-----------------
Accepted: 68600/68600 (100.0%)
Accepted tokens: 33045040
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 481.7061224489796
-----------------
## Stats for 'Subset of FreedomIntelligence/evol-instruct-deutsch' (57841 samples (100.0%))
-----------------
Accepted: 57841/57841 (100.0%)
Accepted tokens: 42958192
Skipped: 0 (0.0%)
Min tokens per sample: 33
Max tokens per sample: 5507
Avg tokens per sample: 742.6944900675991
-----------------
## Stats for 'Subset of FreedomIntelligence/alpaca-gpt4-deutsch' (48969 samples (100.0%))
-----------------
Accepted: 48969/48969 (100.0%)
Accepted tokens: 13372005
Skipped: 0 (0.0%)
Min tokens per sample: 19
Max tokens per sample: 1359
Avg tokens per sample: 273.07082031489307
-----------------
## Stats for 'Subset of LeoLM/German_Songs' (490 samples (100.0%))
-----------------
Accepted: 490/490 (100.0%)
Accepted tokens: 618642
Skipped: 0 (0.0%)
Min tokens per sample: 747
Max tokens per sample: 1678
Avg tokens per sample: 1262.534693877551
-----------------
## Stats for 'Subset of LeoLM/German_Poems' (392 samples (100.0%))
-----------------
Accepted: 392/392 (100.0%)
Accepted tokens: 187897
Skipped: 0 (0.0%)
Min tokens per sample: 231
Max tokens per sample: 826
Avg tokens per sample: 479.3290816326531
-----------------
## Stats for 'Subset of OpenAssistant/OASST_DE' (3646 samples (100.0%))
-----------------
Accepted: 3646/3646 (100.0%)
Accepted tokens: 2338738
Skipped: 0 (0.0%)
Min tokens per sample: 29
Max tokens per sample: 2484
Avg tokens per sample: 641.4530992868897
-----------------
## Stats for 'Subset of bjoernp/oasst25-08-23-filtered' (8922 samples (100.0%))
-----------------
Accepted: 8922/8922 (100.0%)
Accepted tokens: 4526427
Skipped: 0 (0.0%)
Min tokens per sample: 23
Max tokens per sample: 5407
Avg tokens per sample: 507.3332212508406
-----------------
## Stats for 'total' (235632 samples (100.0%))
-----------------
Accepted: 235632/235632 (100.0%)
Accepted tokens: 115862397
Skipped: 0 (0.0%)
Min tokens per sample: 18
Max tokens per sample: 11810
Avg tokens per sample: 491.70909299246284
-----------------
```
<!-- original-model-card end -->
|
CyberHarem/natsu_megumi_istheorderarabbit
|
CyberHarem
| 2023-09-28T11:10:37Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/natsu_megumi_istheorderarabbit",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T10:50:16Z |
---
license: mit
datasets:
- CyberHarem/natsu_megumi_istheorderarabbit
pipeline_tag: text-to-image
tags:
- art
---
# Lora of natsu_megumi_istheorderarabbit
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 8400, you need to download `8400/natsu_megumi_istheorderarabbit.pt` as the embedding and `8400/natsu_megumi_istheorderarabbit.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 8400**, with the score of 0.942. The trigger words are:
1. `natsu_megumi_istheorderarabbit`
2. `red_hair, long_hair, twintails, blush, scrunchie, bangs, hair_ornament, hair_scrunchie, low_twintails, red_eyes, smile, closed_mouth, white_scrunchie`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | pattern_18 | pattern_19 | pattern_20 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:--------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| **8400** | **0.942** | [**Download**](8400/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| 7840 | 0.931 | [Download](7840/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7840/previews/nude.png) | [<NSFW, click to see>](7840/previews/nude2.png) |  |  |
| 7280 | 0.902 | [Download](7280/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7280/previews/nude.png) | [<NSFW, click to see>](7280/previews/nude2.png) |  |  |
| 6720 | 0.893 | [Download](6720/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6720/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6720/previews/nude.png) | [<NSFW, click to see>](6720/previews/nude2.png) |  |  |
| 6160 | 0.910 | [Download](6160/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6160/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6160/previews/nude.png) | [<NSFW, click to see>](6160/previews/nude2.png) |  |  |
| 5600 | 0.888 | [Download](5600/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5600/previews/nude.png) | [<NSFW, click to see>](5600/previews/nude2.png) |  |  |
| 5040 | 0.896 | [Download](5040/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5040/previews/nude.png) | [<NSFW, click to see>](5040/previews/nude2.png) |  |  |
| 4480 | 0.873 | [Download](4480/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4480/previews/nude.png) | [<NSFW, click to see>](4480/previews/nude2.png) |  |  |
| 3920 | 0.893 | [Download](3920/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3920/previews/nude.png) | [<NSFW, click to see>](3920/previews/nude2.png) |  |  |
| 3360 | 0.861 | [Download](3360/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3360/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3360/previews/nude.png) | [<NSFW, click to see>](3360/previews/nude2.png) |  |  |
| 2800 | 0.833 | [Download](2800/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2800/previews/nude.png) | [<NSFW, click to see>](2800/previews/nude2.png) |  |  |
| 2240 | 0.856 | [Download](2240/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2240/previews/nude.png) | [<NSFW, click to see>](2240/previews/nude2.png) |  |  |
| 1680 | 0.822 | [Download](1680/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1680/previews/nude.png) | [<NSFW, click to see>](1680/previews/nude2.png) |  |  |
| 1120 | 0.710 | [Download](1120/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1120/previews/nude.png) | [<NSFW, click to see>](1120/previews/nude2.png) |  |  |
| 560 | 0.265 | [Download](560/natsu_megumi_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](560/previews/nude.png) | [<NSFW, click to see>](560/previews/nude2.png) |  |  |
|
ycasc/baichuan-Medical
|
ycasc
| 2023-09-28T11:08:18Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T11:48:23Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
s3nh/stacknexus-311fontana_13b-GGUF
|
s3nh
| 2023-09-28T11:06:28Z | 4 | 1 |
transformers
|
[
"transformers",
"gguf",
"text-generation",
"zh",
"en",
"license:openrail",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-28T10:58:37Z |
---
license: openrail
pipeline_tag: text-generation
library_name: transformers
language:
- zh
- en
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGUF Format model files for [This project](https://huggingface.co/stacknexus-311fontana_13b).
### GGUF Specs
GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:
Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information.
Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models.
mmap compatibility: models can be loaded using mmap for fast loading and saving.
Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used.
Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user.
The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values.
This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for
inference or for identifying the model.
### Perplexity params
Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16
7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066
13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543
### inference
TODO
# Original model card
|
VishalCh/trained-llama2
|
VishalCh
| 2023-09-28T11:06:16Z | 2 | 0 |
transformers
|
[
"transformers",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"endpoints_compatible",
"region:us"
] | null | 2023-09-27T12:02:08Z |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: trained-llama2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# trained-llama2
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 30
### Training results
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
poisson-fish/Marcoroni-70B-v1-AWQ
|
poisson-fish
| 2023-09-28T10:59:20Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"lmdeploy",
"awq",
"marcoroni",
"70b",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-25T02:23:56Z |
---
tags:
- lmdeploy
- awq
- marcoroni
- 70b
---
This is [AIDC-ai-business/Marcoroni-70B-v1](https://huggingface.co/AIDC-ai-business/Marcoroni-70B-v1) quantized to LMDeploy 4bit AWQ with the following config:
```bash
python3 -m lmdeploy.lite.apis.auto_awq \
--model ./Marcoroni-70B-v1 \
--w_bits 4 \
--w_group_size 128 \
--work_dir ./quant
```
# Original Model Card:
# Marcoroni-70B
# Model Details
* **Trained by**: trained by AIDC AI-Business.
* **Model type:** **Marcoroni-70B** is an auto-regressive language model based on the Llama 2 transformer architecture.
* **Language(s)**: English
* **License for Marcoroni-70B base weights**: Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))
# Prompting
## Prompt Template for alpaca style
```
### Instruction:
<prompt> (without the <>)
### Response:
```
|
poisson-fish/Phind-CodeLlama-34B-v2-AWQ
|
poisson-fish
| 2023-09-28T10:58:33Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"code llama",
"lmdeploy",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-26T10:38:03Z |
---
license: llama2
model-index:
- name: Phind-CodeLlama-34B-v1
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 73.8%
verified: false
tags:
- code llama
- lmdeploy
---
This is [Phind/Phind-CodeLlama-34B-v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2) quantized to LMDeploy 4bit AWQ with the following config:
```bash
python3 -m lmdeploy.lite.apis.auto_awq \
--model ./Phind-CodeLlama-34B-v2 \
--w_bits 4 \
--w_group_size 128 \
--work_dir ./quant
```
# Original Model Card:
# **Phind-CodeLlama-34B-v2**
We've fine-tuned Phind-CodeLlama-34B-v1 on an additional 1.5B tokens high-quality programming-related data, achieving **73.8% pass@1** on HumanEval. It's the current state-of-the-art amongst open-source models.
Furthermore, this model is **instruction-tuned** on the Alpaca/Vicuna format to be steerable and easy-to-use.
More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).
## Model Details
This model is fine-tuned from Phind-CodeLlama-34B-v1 and achieves **73.8% pass@1** on HumanEval.
Phind-CodeLlama-34B-v2 is **multi-lingual** and is proficient in Python, C/C++, TypeScript, Java, and more.
## Dataset Details
We fined-tuned on a proprietary dataset of 1.5B tokens of high quality programming problems and solutions. This dataset consists of instruction-answer pairs instead of code completion examples, making it structurally different from HumanEval. LoRA was not used -- both models are a native finetune. We used DeepSpeed ZeRO 3 and Flash Attention 2 to train these models in 15 hours on 32 A100-80GB GPUs. We used a sequence length of 4096 tokens.
## How to Get Started with the Model
Make sure to install Transformers from the main git branch:
```bash
pip install git+https://github.com/huggingface/transformers.git
```
## How to Prompt the Model
This model accepts the Alpaca/Vicuna instruction format.
For example:
```
### System Prompt
You are an intelligent programming assistant.
### User Message
Implement a linked list in C++
### Assistant
...
```
## How to reproduce HumanEval Results
To reproduce our results:
```python
from transformers import AutoTokenizer, LlamaForCausalLM
from human_eval.data import write_jsonl, read_problems
from tqdm import tqdm
# initialize the model
model_path = "Phind/Phind-CodeLlama-34B-v2"
model = LlamaForCausalLM.from_pretrained(model_path, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)
# HumanEval helper
def generate_one_completion(prompt: str):
tokenizer.pad_token = tokenizer.eos_token
inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=4096)
# Generate
generate_ids = model.generate(inputs.input_ids.to("cuda"), max_new_tokens=384, do_sample=True, top_p=0.75, top_k=40, temperature=0.1)
completion = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
completion = completion.replace(prompt, "").split("\n\n\n")[0]
return completion
# perform HumanEval
problems = read_problems()
num_samples_per_task = 1
samples = [
dict(task_id=task_id, completion=generate_one_completion(problems[task_id]["prompt"]))
for task_id in tqdm(problems)
for _ in range(num_samples_per_task)
]
write_jsonl("samples.jsonl", samples)
# run `evaluate_functional_correctness samples.jsonl` in your HumanEval code sandbox
```
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
## Training details
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
- **Hardware Type:** 32x A100-80GB
- **Hours used:** 480 GPU-hours
- **Cloud Provider:** AWS
- **Compute Region:** us-east-1
|
SophiaPu/q-FrozenLake-v1-4x4-noSlippery
|
SophiaPu
| 2023-09-28T10:56:43Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T10:53:00Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="SophiaPu/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
CyberHarem/nanami_touko_yagatekimininaru
|
CyberHarem
| 2023-09-28T10:51:28Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/nanami_touko_yagatekimininaru",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T10:34:13Z |
---
license: mit
datasets:
- CyberHarem/nanami_touko_yagatekimininaru
pipeline_tag: text-to-image
tags:
- art
---
# Lora of nanami_touko_yagatekimininaru
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 6000, you need to download `6000/nanami_touko_yagatekimininaru.pt` as the embedding and `6000/nanami_touko_yagatekimininaru.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 6000**, with the score of 0.929. The trigger words are:
1. `nanami_touko_yagatekimininaru`
2. `long_hair, black_hair, bangs, bow, ribbon, grey_eyes`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9000 | 0.877 | [Download](9000/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9000/previews/nude.png) | [<NSFW, click to see>](9000/previews/nude2.png) |  |  |
| 8400 | 0.873 | [Download](8400/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| 7800 | 0.840 | [Download](7800/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7200 | 0.835 | [Download](7200/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6600 | 0.881 | [Download](6600/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| **6000** | **0.929** | [**Download**](6000/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5400 | 0.911 | [Download](5400/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5400/previews/nude.png) | [<NSFW, click to see>](5400/previews/nude2.png) |  |  |
| 4800 | 0.913 | [Download](4800/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4200 | 0.901 | [Download](4200/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4200/previews/nude.png) | [<NSFW, click to see>](4200/previews/nude2.png) |  |  |
| 3600 | 0.890 | [Download](3600/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3600/previews/nude.png) | [<NSFW, click to see>](3600/previews/nude2.png) |  |  |
| 3000 | 0.872 | [Download](3000/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2400 | 0.869 | [Download](2400/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1800 | 0.864 | [Download](1800/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1200 | 0.881 | [Download](1200/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 600 | 0.798 | [Download](600/nanami_touko_yagatekimininaru.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
|
dss107/news5
|
dss107
| 2023-09-28T10:39:29Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-09-28T10:38:23Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# dss107/news5
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("dss107/news5")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
m-aliabbas1/tiny_bert_31_erc_intents
|
m-aliabbas1
| 2023-09-28T10:37:41Z | 118 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:prajjwal1/bert-tiny",
"base_model:finetune:prajjwal1/bert-tiny",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-28T10:10:46Z |
---
license: mit
base_model: prajjwal1/bert-tiny
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny_bert_31_erc_intents
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# tiny_bert_31_erc_intents
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3615
- Accuracy: 0.9485
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| No log | 1.0 | 273 | 3.2312 | 0.2247 |
| 3.2677 | 2.0 | 546 | 3.0029 | 0.4454 |
| 3.2677 | 3.0 | 819 | 2.7765 | 0.5196 |
| 2.8826 | 4.0 | 1092 | 2.5522 | 0.6 |
| 2.8826 | 5.0 | 1365 | 2.3412 | 0.6371 |
| 2.4879 | 6.0 | 1638 | 2.1518 | 0.6577 |
| 2.4879 | 7.0 | 1911 | 1.9724 | 0.6742 |
| 2.137 | 8.0 | 2184 | 1.8147 | 0.6928 |
| 2.137 | 9.0 | 2457 | 1.6748 | 0.7216 |
| 1.8286 | 10.0 | 2730 | 1.5458 | 0.7608 |
| 1.592 | 11.0 | 3003 | 1.4381 | 0.7876 |
| 1.592 | 12.0 | 3276 | 1.3335 | 0.8 |
| 1.3969 | 13.0 | 3549 | 1.2423 | 0.8124 |
| 1.3969 | 14.0 | 3822 | 1.1551 | 0.8330 |
| 1.2209 | 15.0 | 4095 | 1.0825 | 0.8474 |
| 1.2209 | 16.0 | 4368 | 1.0141 | 0.8536 |
| 1.0896 | 17.0 | 4641 | 0.9527 | 0.8763 |
| 1.0896 | 18.0 | 4914 | 0.8963 | 0.8825 |
| 0.9763 | 19.0 | 5187 | 0.8472 | 0.8948 |
| 0.9763 | 20.0 | 5460 | 0.7968 | 0.9052 |
| 0.8742 | 21.0 | 5733 | 0.7577 | 0.9072 |
| 0.784 | 22.0 | 6006 | 0.7193 | 0.9113 |
| 0.784 | 23.0 | 6279 | 0.6834 | 0.9113 |
| 0.7159 | 24.0 | 6552 | 0.6500 | 0.9196 |
| 0.7159 | 25.0 | 6825 | 0.6224 | 0.9196 |
| 0.6496 | 26.0 | 7098 | 0.5931 | 0.9237 |
| 0.6496 | 27.0 | 7371 | 0.5679 | 0.9278 |
| 0.5962 | 28.0 | 7644 | 0.5459 | 0.9258 |
| 0.5962 | 29.0 | 7917 | 0.5243 | 0.9320 |
| 0.5553 | 30.0 | 8190 | 0.5065 | 0.9361 |
| 0.5553 | 31.0 | 8463 | 0.4888 | 0.9320 |
| 0.517 | 32.0 | 8736 | 0.4732 | 0.9340 |
| 0.4827 | 33.0 | 9009 | 0.4607 | 0.9361 |
| 0.4827 | 34.0 | 9282 | 0.4477 | 0.9381 |
| 0.4479 | 35.0 | 9555 | 0.4346 | 0.9423 |
| 0.4479 | 36.0 | 9828 | 0.4240 | 0.9423 |
| 0.4231 | 37.0 | 10101 | 0.4153 | 0.9485 |
| 0.4231 | 38.0 | 10374 | 0.4065 | 0.9464 |
| 0.4157 | 39.0 | 10647 | 0.3990 | 0.9464 |
| 0.4157 | 40.0 | 10920 | 0.3915 | 0.9464 |
| 0.3914 | 41.0 | 11193 | 0.3866 | 0.9464 |
| 0.3914 | 42.0 | 11466 | 0.3810 | 0.9443 |
| 0.3747 | 43.0 | 11739 | 0.3763 | 0.9464 |
| 0.3684 | 44.0 | 12012 | 0.3727 | 0.9505 |
| 0.3684 | 45.0 | 12285 | 0.3690 | 0.9505 |
| 0.3605 | 46.0 | 12558 | 0.3662 | 0.9505 |
| 0.3605 | 47.0 | 12831 | 0.3643 | 0.9485 |
| 0.3499 | 48.0 | 13104 | 0.3628 | 0.9485 |
| 0.3499 | 49.0 | 13377 | 0.3618 | 0.9485 |
| 0.3514 | 50.0 | 13650 | 0.3615 | 0.9485 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
RockySong/Reinforce-CartPole-v2-1600step-32hid-0.002lr
|
RockySong
| 2023-09-28T10:30:22Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T10:29:39Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v2-1600step-32hid-0.002lr
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
OreoAu/nft_gainezis
|
OreoAu
| 2023-09-28T10:22:28Z | 0 | 0 |
diffusers
|
[
"diffusers",
"music",
"art",
"text-generation-inference",
"unconditional-image-generation",
"fr",
"en",
"ht",
"dataset:Falah/image_generation_prompts_SDXL",
"dataset:pszemraj/text2image-multi-prompt",
"dataset:Doohae/modern_music_re",
"dataset:ProGamerGov/StableDiffusion-v1-5-Regularization-Images",
"dataset:lansinuote/diffusion.1.unconditional",
"dataset:daspartho/stable-diffusion-prompts",
"dataset:templates/dataset-card-example",
"dataset:mariosasko/test_imagefolder_with_metadata",
"dataset:fka/awesome-chatgpt-prompts",
"dataset:vicgalle/alpaca-gpt4",
"dataset:nomic-ai/gpt4all_prompt_generations",
"dataset:teknium/GPT4-LLM-Cleaned",
"dataset:Photolens/oasst1-langchain-llama-2-formatted",
"dataset:open-llm-leaderboard/details_mistralai__Mistral-7B-v0.1",
"arxiv:1910.09700",
"region:us"
] |
unconditional-image-generation
| 2023-09-28T08:58:42Z |
---
datasets:
- Falah/image_generation_prompts_SDXL
- pszemraj/text2image-multi-prompt
- Doohae/modern_music_re
- ProGamerGov/StableDiffusion-v1-5-Regularization-Images
- lansinuote/diffusion.1.unconditional
- daspartho/stable-diffusion-prompts
- templates/dataset-card-example
- mariosasko/test_imagefolder_with_metadata
- fka/awesome-chatgpt-prompts
- vicgalle/alpaca-gpt4
- nomic-ai/gpt4all_prompt_generations
- teknium/GPT4-LLM-Cleaned
- Photolens/oasst1-langchain-llama-2-formatted
- open-llm-leaderboard/details_mistralai__Mistral-7B-v0.1
language:
- fr
- en
- ht
metrics:
- accuracy
- character
- code_eval
- bertscore
library_name: diffusers
pipeline_tag: unconditional-image-generation
tags:
- music
- art
- text-generation-inference
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
talalH/summarizer_on_T5_base
|
talalH
| 2023-09-28T10:13:28Z | 118 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"en",
"dataset:xsum",
"dataset:quora",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-17T09:13:40Z |
---
datasets:
- xsum
- quora
language:
- en
metrics:
- rouge
pipeline_tag: text2text-generation
---
# Model
**NOTE:** **FEEL FREE TO DOWNLOAD FOR INFERENCE YOU WON'T REGRET IT :)**
<!-- Provide a quick summary of what the model is/does. -->
This model card provides information about a fine-tuned T5 base model that has been specifically trained for generating summaries. We have made some key modifications to the training process to optimize the model's performance and provide the best possible summaries, particularly supporting greater length outputs. One notable difference between this model and other similar models is that it is trained on the target output length of 512. This means that the model is explicitly trained to generate summaries that are up to 512 tokens long. By focusing on this target output length, we aim to provide summaries that are more comprehensive and informative, while still maintaining a reasonable length for large text.
**Dataset and Training:**
The fine-tuned T5 base model is trained on a carefully curated subset of the XSum and ChatGPT datasets. These datasets contain a wide range of text samples, including news articles and conversational data. By utilizing this diverse data, the model gains a broader understanding of language and improves its ability to generate accurate and coherent summaries.
**Transfer Learning for Summarization:**
Transfer learning is employed to enhance the model's performance in generating summaries. The T5 base model, pre-trained on a large corpus of text, is fine-tuned using the curated dataset mentioned above. This process allows the model to leverage its pre-existing knowledge while adapting specifically to the summarization task. By fine-tuning the model, we aim to improve its ability to capture important information and generate concise summaries.
**Enhanced Support for Greater Length Output:**
We are confident that this fine-tuned T5 model will generate the best possible summaries, particularly for supporting greater length outputs. By training the model with a specific focus on generating longer summaries, we have enhanced its ability to handle and convey more detailed information. This makes the model particularly useful in scenarios where longer summaries are required, such as summarizing lengthy documents or providing in-depth analysis.
**Conclusion:**
The fine-tuned T5 base model described in this model card offers an advanced summarization capability, with a specific emphasis on supporting greater length outputs. By utilizing a carefully curated dataset and applying transfer learning techniques, the model has been optimized to generate accurate and informative summaries. We believe that this model will be a valuable tool for a wide range of applications that require comprehensive and well-structured summaries.
## How to Get Started with the Model
Use the code below to get started with the model.
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from math import ceil
model_name = "talalH/summarizer_on_T5_base"
tokenizer = AutoTokenizer.from_pretrained(model_name, device_map='auto')
model = AutoModelForSeq2SeqLM.from_pretrained(model_name, device_map='auto')
print("-"*100)
print("\nHi !! ENTER A TEXT TO SUMMARIZE (type 'exit' to end)\n")
while True:
user_input = input("USER: ")
if user_input.lower() == "exit":
break
input_text = user_input
input_ids = tokenizer(f'summarize: {input_text}</s>', return_tensors="pt"
, max_length=512, truncation=True,).input_ids
min_len = ceil(len(input_text.split())/2)
outputs = model.generate(input_ids, temperature=0.3, repetition_penalty=10.0
, num_return_sequences=3, no_repeat_ngram_size=2
, num_beams=10, num_beam_groups=5
, min_length = min_len, max_length=512, diversity_penalty=2.0
)
sequences = tokenizer.batch_decode(outputs, skip_special_tokens=True)
print("\nOUTPUT")
try:
if len(sequences):
for seq in sequences:
print("T5: ",seq,"\n")
else:
print("T5: NO RESPONSE RETURNED")
except:
print("T5: NO RESPONSE RETURNED")
print("-"*100)
```
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Talal Hassan (talalhassan141@gmail.com)
- **Finetuned from model:** T5 BASE
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
For Text Summarization
## Training Details
epochs: 4
Warmup_steps: 50
max_step: -1
lr:5e-5
batch_size = 4
- **Hardware Type:** Tesla K80 GPUs
## Model Card Authors
Talal Hassan (talalhassan141@gmail.com)
## Model Card Contact
Talal Hassan (talalhassan141@gmail.com)
|
kakunkakun/lora-trained-xl
|
kakunkakun
| 2023-09-28T09:47:14Z | 4 | 1 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2023-09-28T01:00:03Z |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: tagi
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - kakunkakun/lora-trained-xl
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on tagi using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
ArchiveAPI/AnalogMadness
|
ArchiveAPI
| 2023-09-28T09:43:28Z | 0 | 1 | null |
[
"license:unknown",
"region:us"
] | null | 2023-09-27T23:04:25Z |
---
license: unknown
---
# AnalogMadness
#### Model Link: https://civitai.com/models/8030/analog-madness-realistic-model
#### Credit belongs to the original author. The model here only serves as an API for downloads.
# Log
- Sep-28-2023: Add v6
|
jondurbin/airoboros-c34b-2.2.1
|
jondurbin
| 2023-09-28T09:39:42Z | 1,437 | 9 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-2.2.1",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-19T20:22:58Z |
---
license: llama2
datasets:
- jondurbin/airoboros-2.2.1
---
### Overview
Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
This is essentially a minor "fix" branch of [airoboros-c34b-2.2](https://hf.co/jondurbin/airoboros-c34b-2.2) with a updates, primarily:
- [re-generated writing responses](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#re-generated-writing-responses)
- [longer contextual blocks](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#longer-contextual-blocks)
- [removal of "rp" data](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#rp-category-removed)
- [(less aggressive) de-censoring](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1#de-censoring)
- 5 epochs instead of 3
This is a fairly general purpose model, but focuses heavily on instruction following, rather than casual chat/roleplay.
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The prompt format:
```
A chat.
USER: {prompt}
ASSISTANT:
```
The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc.
Here's another example:
```
A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously.
USER: {prompt}
ASSISTANT:
```
And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf).
```
A chat between old friends: Timmy and Tommy.
{description of characters}
{setting for the chat}
Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee."
Tommy:
```
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__
### Fine tuning info
https://wandb.ai/jondurbin/airoboros-c34b-2.2.1/runs/07b08z7m?workspace=user-jondurbin
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Summarization
500 samples have been included from [this dataset](https://huggingface.co/datasets/mattpscott/airoboros-summarization), using the same format as contextual question answering, for example:
```
BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION
```
#### Getting longer responses
You can use a few techniques to get longer responses.
Detailed prompts, with explicit instruction for word count:
```
Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.
The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.
One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.
Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.
Your response should be approximately 2300 words.
```
Or, a simpler example:
```
Please create a long, detailed story about a dragon in an old growth forest who, for some reason, begins speaking the words of the source code of linux.
```
There are a few examples of next chapter completion as well, e.g.:
```
Write the next chapter of a historical fiction novel set in Paris during the 20th century.
Here's a summary of the previous chapter:
In the vibrant city of Paris, amid the tumultuous changes of the 20th century, our protagonist Margot, an aspiring fashion designer, has just secured an apprenticeship at a prestigious couture house. She meets Lucien, a charming journalist who covers the fashion industry. Together they navigate the ever-changing world of fashion and society, uncovering secrets that reveal the intricate links between style, politics, and culture. As the chapter concludes, they decide to delve deeper into the hidden corners of the fashion world to unravel its mysteries.
Requirements for the next chapter:
1. Character Development of Margot and Lucien:
- Margot's Evolution: Unfold more about Margot's past, her dreams of revolutionizing fashion, and her struggle to establish herself in a male-dominated industry. Illustrate her growing expertise, innovative ideas, and increasing dependence on Lucien.
- Lucien's Complexity: Introduce uncertainties surrounding Lucien's background and real motives. Increase suspense by suggesting undisclosed information he possesses, while also highlighting his wit and perceptiveness.
2. Exploration of Paris and the Couture House:
- Paris: Elaborate their journey through the bustling streets of Paris, including encounters with iconic figures, social unrest, and relics from different eras of French history.
- The Couture House: Expand on the grandeur of the couture house they work in, filled with artistic masterpieces, intense competition, and cryptic notes hinting at a scandalous past.
3. Emergence of the Subplot: The Lost Collection:
- Discovery: Have Margot and Lucien stumble upon a secret vault containing a lost collection designed before World War II, raising new questions about the previous owner and the influence of war on fashion.
- Revelation: Capture their shock as they realize the designs were plagiarized, the potential repercussions, and the opportunities it presents for Margot's career.
- Twist: End with a twist that suggests there are other stolen collections across Paris, setting up their new mission.
Your response should be approximately 650 words.
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.2 models are built on top of llama-2/codellama.
The llama-2 base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was mostly generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
ArchiveAPI/AnyLora
|
ArchiveAPI
| 2023-09-28T09:38:33Z | 0 | 1 | null |
[
"license:unknown",
"region:us"
] | null | 2023-09-27T23:23:36Z |
---
license: unknown
---
# AnyLora
#### Model Link: https://civitai.com/models/23900/anylora-checkpoint
#### Credit belongs to the original author. The model here only serves as API for downloads.
|
yyjun/yyjun.KoAlpaca
|
yyjun
| 2023-09-28T09:17:14Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T09:17:11Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
vaibhav9/hangman-bert-base-2
|
vaibhav9
| 2023-09-28T09:04:22Z | 177 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:vaibhav9/hangman-bert-base-2",
"base_model:finetune:vaibhav9/hangman-bert-base-2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-09-28T03:00:47Z |
---
license: apache-2.0
base_model: vaibhav9/hangman-bert-base-2
tags:
- generated_from_trainer
model-index:
- name: hangman-bert-base-2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# hangman-bert-base-2
This model is a fine-tuned version of [vaibhav9/hangman-bert-base-2](https://huggingface.co/vaibhav9/hangman-bert-base-2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0054
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0245 | 1.0 | 2609 | 2.0118 |
| 2.0108 | 2.0 | 5218 | 2.0105 |
| 2.0092 | 3.0 | 7827 | 2.0054 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
|
gtxygyzb/mt5-small-finetuned-amazon-en-es
|
gtxygyzb
| 2023-09-28T09:03:23Z | 13 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"summarization",
"generated_from_trainer",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-09-28T08:03:02Z |
---
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-amazon-en-es
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0349
- Rouge1: 17.1191
- Rouge2: 8.4119
- Rougel: 16.6388
- Rougelsum: 16.6017
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
| 7.3401 | 1.0 | 1209 | 3.3465 | 14.1778 | 6.284 | 13.8905 | 13.8872 |
| 3.9195 | 2.0 | 2418 | 3.1859 | 15.9786 | 8.1666 | 15.3933 | 15.3693 |
| 3.5975 | 3.0 | 3627 | 3.0945 | 17.5518 | 9.134 | 16.9215 | 16.8899 |
| 3.4241 | 4.0 | 4836 | 3.0913 | 16.3875 | 7.6999 | 15.8311 | 15.8004 |
| 3.3252 | 5.0 | 6045 | 3.0588 | 16.6777 | 8.1639 | 16.1058 | 16.1357 |
| 3.2442 | 6.0 | 7254 | 3.0444 | 17.141 | 8.4204 | 16.6366 | 16.6896 |
| 3.2149 | 7.0 | 8463 | 3.0355 | 17.3266 | 8.7249 | 16.9438 | 16.9154 |
| 3.184 | 8.0 | 9672 | 3.0349 | 17.1191 | 8.4119 | 16.6388 | 16.6017 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
roa7n/gpt2-human_nontata_promoters-randomized_5_layers_3e-05_lr_8_e
|
roa7n
| 2023-09-28T08:57:52Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T08:57:49Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
illuin/tiny-random-MistralForCausalLM-lora
|
illuin
| 2023-09-28T08:53:48Z | 1 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T08:53:27Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
Aples/llama-2-7b-finetune-gentest-model
|
Aples
| 2023-09-28T08:43:19Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T08:38:22Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
|
klyang/MentaLLaMA-chat-7B
|
klyang
| 2023-09-28T08:26:07Z | 2,987 | 16 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"medical",
"en",
"arxiv:2309.13567",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-26T17:41:12Z |
---
license: mit
language:
- en
metrics:
- f1
tags:
- medical
---
# Introduction
MentaLLaMA-chat-7B is part of the [MentaLLaMA](https://github.com/SteveKGYang/MentalLLaMA) project, the first open-source large language model (LLM) series for
interpretable mental health analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-7B foundation model and the full IMHI instruction tuning data.
The model is expected to make complex mental health analysis for various mental health conditions and give reliable explanations for each of its predictions.
It is fine-tuned on the IMHI dataset with 75K high-quality natural language instructions to boost its performance in downstream tasks.
We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative
methods in correctness and generates high-quality explanations.
# Ethical Consideration
Although experiments on MentaLLaMA show promising performance on interpretable mental health analysis, we stress that
all predicted results and generated explanations should only used
for non-clinical research, and the help-seeker should get assistance
from professional psychiatrists or clinical practitioners. In addition,
recent studies have indicated LLMs may introduce some potential
bias, such as gender gaps. Meanwhile, some incorrect prediction results, inappropriate explanations, and over-generalization
also illustrate the potential risks of current LLMs. Therefore, there
are still many challenges in applying the model to real-scenario
mental health monitoring systems.
## Other Models in MentaLLaMA
In addition to MentaLLaMA-chat-7B, the MentaLLaMA project includes another model: MentaLLaMA-chat-13B, MentalBART, MentalT5.
- **MentaLLaMA-chat-13B**: This model is finetuned based on the Meta LLaMA2-chat-13B foundation model and the full IMHI instruction tuning data. The training data covers 10 mental health analysis tasks.
- **MentalBART**: This model is finetuned based on the BART-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner.
- **MentalT5**: This model is finetuned based on the T5-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner.
## Usage
You can use the MentaLLaMA-chat-7B model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model:
```python
from transformers import LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained('klyang/MentaLLaMA-chat-7B')
model = LlamaForCausalLM.from_pretrained('klyang/MentaLLaMA-chat-7B', device_map='auto')
```
In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The `device_map='auto'` argument is used to automatically
use the GPU if it's available.
## License
MentaLLaMA-chat-7B is licensed under MIT. For more details, please see the MIT file.
## Citation
If you use MentaLLaMA-chat-7B in your work, please cite the our paper:
```bibtex
@misc{yang2023mentalllama,
title={MentalLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models},
author={Kailai Yang and Tianlin Zhang and Ziyan Kuang and Qianqian Xie and Sophia Ananiadou},
year={2023},
eprint={2309.13567},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
hw2942/chinese-lert-base-SSE50
|
hw2942
| 2023-09-28T08:15:38Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:hfl/chinese-lert-base",
"base_model:finetune:hfl/chinese-lert-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-28T08:09:10Z |
---
license: apache-2.0
base_model: hfl/chinese-lert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: chinese-lert-base-wallstreetcn-morning-news-market-overview-SSE50-10
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chinese-lert-base-wallstreetcn-morning-news-market-overview-SSE50-10
This model is a fine-tuned version of [hfl/chinese-lert-base](https://huggingface.co/hfl/chinese-lert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3547
- Accuracy: 0.6364
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 34 | 3.8141 | 0.6364 |
| No log | 2.0 | 68 | 3.0470 | 0.6667 |
| No log | 3.0 | 102 | 3.6099 | 0.6364 |
| No log | 4.0 | 136 | 3.5038 | 0.5758 |
| No log | 5.0 | 170 | 3.7060 | 0.6364 |
| No log | 6.0 | 204 | 3.6808 | 0.5758 |
| No log | 7.0 | 238 | 3.4109 | 0.6667 |
| No log | 8.0 | 272 | 3.9414 | 0.5455 |
| No log | 9.0 | 306 | 3.3539 | 0.6364 |
| No log | 10.0 | 340 | 3.3547 | 0.6364 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
dhrf/lora-Llama-2-7b-hf-qa-1epoch
|
dhrf
| 2023-09-28T08:06:57Z | 0 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T07:51:26Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
oshita-n/textual_inversion_11
|
oshita-n
| 2023-09-28T08:01:20Z | 36 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T07:55:56Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - oshita-n/textual_inversion_11
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
YL95/naive_chunk0
|
YL95
| 2023-09-28T07:57:39Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"region:us"
] | null | 2023-09-28T07:56:33Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
|
TexR6/q-FrozenLake-v1-4x4-noSlippery
|
TexR6
| 2023-09-28T07:57:19Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T07:57:16Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="TexR6/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
eugene6/a2c-PandaReachDense-v3
|
eugene6
| 2023-09-28T07:51:49Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T07:46:34Z |
---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.19 +/- 0.08
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
filipealmeida/Mistral-7B-Instruct-v0.1-GGUF
|
filipealmeida
| 2023-09-28T07:50:49Z | 16 | 0 | null |
[
"gguf",
"finetuned",
"text-generation",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-28T07:33:46Z |
---
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
---
# GGUF version of version of Mistral-7B-Instruct-v0.1
GGUF version of version of Mistral-7B-Instruct-v0.1 compatible with [llama.cpp](https://github.com/ggerganov/llama.cpp)
This is the unquantized fp16 version of the model.
# Model Card for Mistral-7B-Instruct-v0.1
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets.
For full details of this model please read our [release blog post](https://mistral.ai/news/announcing-mistral-7b/)
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[\INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
encodeds = tokenizer(text, return_tensors="pt", add_special_tokens=False)
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
|
shikari2917/mypic3
|
shikari2917
| 2023-09-28T07:45:30Z | 4 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-28T07:45:24Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of a sks rafeh
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
tomantonyy/ppo-LunarLander-v2
|
tomantonyy
| 2023-09-28T07:38:23Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T07:37:59Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 245.81 +/- 23.93
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
TirathP/fine-tuned
|
TirathP
| 2023-09-28T07:33:19Z | 195 | 0 |
transformers
|
[
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224",
"base_model:finetune:google/vit-base-patch16-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-28T05:11:47Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine-tuned
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fine-tuned
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the custom-huggingface dataset.
It achieves the following results on the evaluation set:
- Loss: 7.3529
- Accuracy: 0.0596
- F1: 0.0075
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.3773 | 2.54 | 1000 | 7.3529 | 0.0596 | 0.0075 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
wadoodkhan/wadood
|
wadoodkhan
| 2023-09-28T07:21:15Z | 0 | 0 | null |
[
"license:bigscience-bloom-rail-1.0",
"region:us"
] | null | 2023-09-28T07:21:14Z |
---
license: bigscience-bloom-rail-1.0
---
|
athugodage/ruDialoGPT-small_10
|
athugodage
| 2023-09-28T07:20:20Z | 211 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:t-bank-ai/ruDialoGPT-small",
"base_model:finetune:t-bank-ai/ruDialoGPT-small",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-28T07:16:40Z |
---
license: mit
base_model: tinkoff-ai/ruDialoGPT-small
tags:
- generated_from_trainer
model-index:
- name: ruDialoGPT-small_10
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ruDialoGPT-small_10
This model is a fine-tuned version of [tinkoff-ai/ruDialoGPT-small](https://huggingface.co/tinkoff-ai/ruDialoGPT-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4977
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 55 | 1.3283 |
| No log | 2.0 | 110 | 1.2672 |
| No log | 3.0 | 165 | 1.3883 |
| No log | 4.0 | 220 | 1.3489 |
| No log | 5.0 | 275 | 1.4106 |
| No log | 6.0 | 330 | 1.4384 |
| No log | 7.0 | 385 | 1.4511 |
| No log | 8.0 | 440 | 1.4744 |
| No log | 9.0 | 495 | 1.4796 |
| 0.9816 | 10.0 | 550 | 1.4977 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
SophiaPu/ppo-Huggy
|
SophiaPu
| 2023-09-28T07:18:28Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-28T07:18:21Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: SophiaPu/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Yntec/dosmixVAE
|
Yntec
| 2023-09-28T07:16:25Z | 296 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"Anime",
"Character",
"3D",
"DiaryOfSta",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T04:46:56Z |
---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
language:
- en
tags:
- Anime
- Character
- 3D
- DiaryOfSta
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
inference: true
---
This model with the zVAE baked in.
Original page: https://civitai.com/models/6250/dosmix
Sample and prompt:
CUTE LITTLE Girl, Cartoon Pretty, DETAILED CHIBI EYES, Paint bucket pouring paint in air on top of planet earth vector logo style
|
roa7n/gpt2-human_nontata_promoters-randomized_5_layers_0.0003_lr_8_e
|
roa7n
| 2023-09-28T07:08:40Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T07:08:38Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
mys/ggml_CLIP-ViT-H-14-laion2B-s32B-b79K
|
mys
| 2023-09-28T06:58:31Z | 433 | 2 | null |
[
"gguf",
"clip",
"vision",
"ggml",
"clip.cpp",
"clip-cpp-gguf",
"license:mit",
"region:us"
] | null | 2023-09-27T06:49:00Z |
---
license: mit
tags:
- clip
- vision
- ggml
- clip.cpp
- clip-cpp-gguf
---
## Converted files for use with clip.cpp
see https://github.com/monatis/clip.cpp
# Experimental
the file format is not stable yet, so expect breaking changes. I will update the files from time to time.
|
rkla/minetester-treechop_shaped-v0-ppo_fastversion_seed1-seed1
|
rkla
| 2023-09-28T06:44:52Z | 0 | 0 |
minetest-baselines
|
[
"minetest-baselines",
"tensorboard",
"minetester-treechop_shaped-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T06:44:24Z |
---
tags:
- minetester-treechop_shaped-v0
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: minetest-baselines
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: minetester-treechop_shaped-v0
type: minetester-treechop_shaped-v0
metrics:
- type: mean_reward
value: 1.09 +/- 5.46
name: mean_reward
verified: false
---
#**PPO** Agent Playing **minetester-treechop_shaped-v0**
This is a trained model of a PPO agent playing minetester-treechop_shaped-v0.
The model was trained by using
[minetest-baselines](https://github.com/EleutherAI/minetest-baselines).
## Command to reproduce the training
```bash
python -m minetest_baselines.train --algo ppo --exp-name ppo_fastversion_seed1 --seed 1 --capture-video --video-frequency 500 --track --wandb-entity rkla --save-model --upload-model --hf-entity rkla --total-timesteps 2000000 --num-envs 4
```
# Hyperparameters
```python
{'anneal_lr': True,
'batch_size': 512,
'capture_video': True,
'clip_coef': 0.1,
'cuda': True,
'ent_coef': 0.01,
'env_id': 'minetester-treechop_shaped-v0',
'exp_name': 'ppo_fastversion_seed1',
'gae_lambda': 0.95,
'gamma': 0.99,
'hf_entity': 'rkla',
'learning_rate': 0.00025,
'max_grad_norm': 0.5,
'minibatch_size': 128,
'norm_adv': True,
'num_envs': 4,
'num_minibatches': 4,
'num_steps': 128,
'num_updates': 3906,
'save_model': True,
'seed': 1,
'target_kl': None,
'torch_deterministic': True,
'total_timesteps': 2000000,
'track': True,
'update_epochs': 4,
'upload_model': True,
'vf_coef': 0.5,
'video_frequency': 500,
'wandb_entity': 'rkla',
'wandb_project_name': 'minetest-baselines'}
```
|
CyberHarem/saito_kaede_encouragementofclimb
|
CyberHarem
| 2023-09-28T06:39:51Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/saito_kaede_encouragementofclimb",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T06:17:48Z |
---
license: mit
datasets:
- CyberHarem/saito_kaede_encouragementofclimb
pipeline_tag: text-to-image
tags:
- art
---
# Lora of saito_kaede_encouragementofclimb
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 8400, you need to download `8400/saito_kaede_encouragementofclimb.pt` as the embedding and `8400/saito_kaede_encouragementofclimb.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 8400**, with the score of 0.972. The trigger words are:
1. `saito_kaede_encouragementofclimb`
2. `black_hair, glasses, blush, long_hair, hairclip, hair_ornament, blue_eyes, smile`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | pattern_18 | pattern_19 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:----------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9000 | 0.940 | [Download](9000/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9000/previews/pattern_19.png) | [<NSFW, click to see>](9000/previews/bikini.png) | [<NSFW, click to see>](9000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9000/previews/nude.png) | [<NSFW, click to see>](9000/previews/nude2.png) |  |  |
| **8400** | **0.972** | [**Download**](8400/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/pattern_19.png) | [<NSFW, click to see>](8400/previews/bikini.png) | [<NSFW, click to see>](8400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| 7800 | 0.938 | [Download](7800/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/pattern_19.png) | [<NSFW, click to see>](7800/previews/bikini.png) | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7200 | 0.955 | [Download](7200/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/pattern_19.png) | [<NSFW, click to see>](7200/previews/bikini.png) | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6600 | 0.937 | [Download](6600/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/pattern_19.png) | [<NSFW, click to see>](6600/previews/bikini.png) | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| 6000 | 0.939 | [Download](6000/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6000/previews/pattern_19.png) | [<NSFW, click to see>](6000/previews/bikini.png) | [<NSFW, click to see>](6000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5400 | 0.934 | [Download](5400/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5400/previews/pattern_19.png) | [<NSFW, click to see>](5400/previews/bikini.png) | [<NSFW, click to see>](5400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5400/previews/nude.png) | [<NSFW, click to see>](5400/previews/nude2.png) |  |  |
| 4800 | 0.941 | [Download](4800/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/pattern_19.png) | [<NSFW, click to see>](4800/previews/bikini.png) | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4200 | 0.940 | [Download](4200/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4200/previews/pattern_19.png) | [<NSFW, click to see>](4200/previews/bikini.png) | [<NSFW, click to see>](4200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4200/previews/nude.png) | [<NSFW, click to see>](4200/previews/nude2.png) |  |  |
| 3600 | 0.910 | [Download](3600/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3600/previews/pattern_19.png) | [<NSFW, click to see>](3600/previews/bikini.png) | [<NSFW, click to see>](3600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3600/previews/nude.png) | [<NSFW, click to see>](3600/previews/nude2.png) |  |  |
| 3000 | 0.929 | [Download](3000/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3000/previews/pattern_19.png) | [<NSFW, click to see>](3000/previews/bikini.png) | [<NSFW, click to see>](3000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2400 | 0.935 | [Download](2400/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/pattern_19.png) | [<NSFW, click to see>](2400/previews/bikini.png) | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1800 | 0.909 | [Download](1800/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1800/previews/pattern_19.png) | [<NSFW, click to see>](1800/previews/bikini.png) | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1200 | 0.887 | [Download](1200/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1200/previews/pattern_19.png) | [<NSFW, click to see>](1200/previews/bikini.png) | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 600 | 0.681 | [Download](600/saito_kaede_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](600/previews/pattern_19.png) | [<NSFW, click to see>](600/previews/bikini.png) | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
|
jordyvl/EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-26_ent_gates_exitloss
|
jordyvl
| 2023-09-28T06:37:13Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"text-classification",
"generated_from_trainer",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-26T12:54:11Z |
---
license: cc-by-nc-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-26_ent_gates_exitloss
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# EElayoutlmv3_jordyvl_rvl_cdip_100_examples_per_class_2023-09-26_ent_gates_exitloss
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1687
- Accuracy: 0.695
- Exit 0 Accuracy: 0.11
- Exit 1 Accuracy: 0.11
- Exit 2 Accuracy: 0.3625
- Exit 3 Accuracy: 0.6375
- Exit 4 Accuracy: 0.69
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Exit 0 Accuracy | Exit 1 Accuracy | Exit 2 Accuracy | Exit 3 Accuracy | Exit 4 Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:---------------:|:---------------:|:---------------:|:---------------:|
| No log | 0.96 | 4 | 2.7393 | 0.1175 | 0.06 | 0.0925 | 0.085 | 0.0625 | 0.0625 |
| No log | 1.96 | 8 | 2.6761 | 0.1625 | 0.07 | 0.0925 | 0.085 | 0.0625 | 0.0625 |
| No log | 2.96 | 12 | 2.6336 | 0.1825 | 0.0775 | 0.1 | 0.09 | 0.0625 | 0.0625 |
| No log | 3.96 | 16 | 2.6046 | 0.21 | 0.065 | 0.105 | 0.0775 | 0.0625 | 0.0625 |
| No log | 4.96 | 20 | 2.6355 | 0.17 | 0.0675 | 0.105 | 0.06 | 0.115 | 0.0875 |
| No log | 5.96 | 24 | 2.5487 | 0.1925 | 0.0725 | 0.1075 | 0.09 | 0.13 | 0.1075 |
| No log | 6.96 | 28 | 2.4605 | 0.275 | 0.0875 | 0.1075 | 0.0925 | 0.1675 | 0.13 |
| No log | 7.96 | 32 | 2.3986 | 0.2475 | 0.09 | 0.1125 | 0.0925 | 0.22 | 0.215 |
| No log | 8.96 | 36 | 2.3182 | 0.3 | 0.1 | 0.1125 | 0.1075 | 0.2475 | 0.29 |
| No log | 9.96 | 40 | 2.2072 | 0.35 | 0.1025 | 0.1125 | 0.1175 | 0.295 | 0.36 |
| No log | 10.96 | 44 | 2.1187 | 0.425 | 0.1025 | 0.1125 | 0.1275 | 0.3175 | 0.4025 |
| No log | 11.96 | 48 | 2.0086 | 0.455 | 0.0975 | 0.11 | 0.16 | 0.3675 | 0.4475 |
| No log | 12.96 | 52 | 1.9037 | 0.4775 | 0.095 | 0.11 | 0.1725 | 0.4025 | 0.465 |
| No log | 13.96 | 56 | 1.8088 | 0.515 | 0.0925 | 0.11 | 0.1875 | 0.4425 | 0.49 |
| No log | 14.96 | 60 | 1.7198 | 0.5475 | 0.095 | 0.1075 | 0.2125 | 0.475 | 0.525 |
| No log | 15.96 | 64 | 1.6502 | 0.5825 | 0.095 | 0.105 | 0.225 | 0.4825 | 0.5425 |
| No log | 16.96 | 68 | 1.5650 | 0.58 | 0.0975 | 0.12 | 0.235 | 0.5175 | 0.5625 |
| No log | 17.96 | 72 | 1.4998 | 0.6025 | 0.1025 | 0.1125 | 0.2475 | 0.5375 | 0.565 |
| No log | 18.96 | 76 | 1.4608 | 0.6025 | 0.1075 | 0.11 | 0.275 | 0.5375 | 0.6025 |
| No log | 19.96 | 80 | 1.3988 | 0.62 | 0.1075 | 0.11 | 0.285 | 0.545 | 0.6025 |
| No log | 20.96 | 84 | 1.3833 | 0.6275 | 0.1075 | 0.11 | 0.2825 | 0.555 | 0.61 |
| No log | 21.96 | 88 | 1.3400 | 0.6475 | 0.11 | 0.11 | 0.2875 | 0.57 | 0.62 |
| No log | 22.96 | 92 | 1.3355 | 0.6425 | 0.1125 | 0.11 | 0.29 | 0.575 | 0.6375 |
| No log | 23.96 | 96 | 1.2812 | 0.6525 | 0.11 | 0.11 | 0.295 | 0.585 | 0.635 |
| No log | 24.96 | 100 | 1.2769 | 0.6425 | 0.11 | 0.11 | 0.31 | 0.585 | 0.6275 |
| No log | 25.96 | 104 | 1.2410 | 0.665 | 0.11 | 0.1075 | 0.315 | 0.59 | 0.6375 |
| No log | 26.96 | 108 | 1.2272 | 0.6725 | 0.1075 | 0.1075 | 0.32 | 0.595 | 0.64 |
| No log | 27.96 | 112 | 1.2168 | 0.67 | 0.11 | 0.1075 | 0.3225 | 0.595 | 0.645 |
| No log | 28.96 | 116 | 1.1919 | 0.675 | 0.11 | 0.1075 | 0.3325 | 0.595 | 0.64 |
| No log | 29.96 | 120 | 1.1948 | 0.6825 | 0.11 | 0.1075 | 0.3375 | 0.6 | 0.655 |
| No log | 30.96 | 124 | 1.1802 | 0.6875 | 0.1075 | 0.1075 | 0.3325 | 0.605 | 0.665 |
| No log | 31.96 | 128 | 1.1939 | 0.68 | 0.11 | 0.1075 | 0.345 | 0.615 | 0.65 |
| No log | 32.96 | 132 | 1.1690 | 0.6925 | 0.1075 | 0.1075 | 0.34 | 0.615 | 0.665 |
| No log | 33.96 | 136 | 1.1763 | 0.68 | 0.105 | 0.1075 | 0.3475 | 0.6175 | 0.6525 |
| No log | 34.96 | 140 | 1.1851 | 0.6875 | 0.105 | 0.1075 | 0.3525 | 0.615 | 0.6675 |
| No log | 35.96 | 144 | 1.1574 | 0.6925 | 0.11 | 0.1075 | 0.355 | 0.62 | 0.6675 |
| No log | 36.96 | 148 | 1.1618 | 0.68 | 0.1075 | 0.1075 | 0.36 | 0.62 | 0.665 |
| No log | 37.96 | 152 | 1.1731 | 0.6825 | 0.105 | 0.1075 | 0.35 | 0.615 | 0.6575 |
| No log | 38.96 | 156 | 1.1550 | 0.68 | 0.1075 | 0.1075 | 0.3425 | 0.6225 | 0.665 |
| No log | 39.96 | 160 | 1.1553 | 0.7 | 0.11 | 0.1075 | 0.3475 | 0.625 | 0.675 |
| No log | 40.96 | 164 | 1.1708 | 0.6875 | 0.1125 | 0.1075 | 0.355 | 0.6275 | 0.665 |
| No log | 41.96 | 168 | 1.1366 | 0.7 | 0.115 | 0.1075 | 0.3525 | 0.63 | 0.68 |
| No log | 42.96 | 172 | 1.1699 | 0.69 | 0.115 | 0.1075 | 0.3575 | 0.63 | 0.6825 |
| No log | 43.96 | 176 | 1.1548 | 0.7025 | 0.1125 | 0.1075 | 0.3525 | 0.6325 | 0.6725 |
| No log | 44.96 | 180 | 1.1628 | 0.6925 | 0.11 | 0.1075 | 0.3575 | 0.635 | 0.675 |
| No log | 45.96 | 184 | 1.1620 | 0.695 | 0.11 | 0.1075 | 0.355 | 0.6325 | 0.6875 |
| No log | 46.96 | 188 | 1.1668 | 0.695 | 0.1125 | 0.1075 | 0.3525 | 0.645 | 0.68 |
| No log | 47.96 | 192 | 1.1595 | 0.6975 | 0.11 | 0.1075 | 0.3475 | 0.635 | 0.6875 |
| No log | 48.96 | 196 | 1.1622 | 0.7025 | 0.11 | 0.1075 | 0.355 | 0.63 | 0.68 |
| No log | 49.96 | 200 | 1.1779 | 0.695 | 0.1075 | 0.1075 | 0.3575 | 0.635 | 0.685 |
| No log | 50.96 | 204 | 1.1656 | 0.695 | 0.11 | 0.1075 | 0.3525 | 0.635 | 0.685 |
| No log | 51.96 | 208 | 1.1536 | 0.705 | 0.1075 | 0.1075 | 0.355 | 0.635 | 0.69 |
| No log | 52.96 | 212 | 1.1675 | 0.7025 | 0.1075 | 0.11 | 0.355 | 0.635 | 0.6975 |
| No log | 53.96 | 216 | 1.1775 | 0.6925 | 0.1075 | 0.11 | 0.3575 | 0.6325 | 0.6925 |
| No log | 54.96 | 220 | 1.1690 | 0.7 | 0.1075 | 0.11 | 0.36 | 0.6375 | 0.685 |
| No log | 55.96 | 224 | 1.1700 | 0.7 | 0.11 | 0.11 | 0.3625 | 0.64 | 0.69 |
| No log | 56.96 | 228 | 1.1637 | 0.7025 | 0.11 | 0.11 | 0.3625 | 0.64 | 0.6875 |
| No log | 57.96 | 232 | 1.1640 | 0.695 | 0.11 | 0.11 | 0.3625 | 0.6375 | 0.6875 |
| No log | 58.96 | 236 | 1.1663 | 0.6975 | 0.11 | 0.11 | 0.3625 | 0.6375 | 0.6875 |
| No log | 59.96 | 240 | 1.1687 | 0.695 | 0.11 | 0.11 | 0.3625 | 0.6375 | 0.69 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
|
CyberHarem/tedeza_rize_istheorderarabbit
|
CyberHarem
| 2023-09-28T06:21:50Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/tedeza_rize_istheorderarabbit",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T06:02:53Z |
---
license: mit
datasets:
- CyberHarem/tedeza_rize_istheorderarabbit
pipeline_tag: text-to-image
tags:
- art
---
# Lora of tedeza_rize_istheorderarabbit
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 7800, you need to download `7800/tedeza_rize_istheorderarabbit.pt` as the embedding and `7800/tedeza_rize_istheorderarabbit.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 7800**, with the score of 0.970. The trigger words are:
1. `tedeza_rize_istheorderarabbit`
2. `purple_hair, long_hair, twintails, purple_eyes, bangs, hair_ornament, blush, hairclip, hair_between_eyes, closed_mouth, indoors`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9000 | 0.964 | [Download](9000/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9000/previews/pattern_11.png) |  |  | [<NSFW, click to see>](9000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9000/previews/nude.png) | [<NSFW, click to see>](9000/previews/nude2.png) |  |  |
| 8400 | 0.966 | [Download](8400/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8400/previews/pattern_11.png) |  |  | [<NSFW, click to see>](8400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8400/previews/nude.png) | [<NSFW, click to see>](8400/previews/nude2.png) |  |  |
| **7800** | **0.970** | [**Download**](7800/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7800/previews/pattern_11.png) |  |  | [<NSFW, click to see>](7800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7800/previews/nude.png) | [<NSFW, click to see>](7800/previews/nude2.png) |  |  |
| 7200 | 0.965 | [Download](7200/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7200/previews/pattern_11.png) |  |  | [<NSFW, click to see>](7200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7200/previews/nude.png) | [<NSFW, click to see>](7200/previews/nude2.png) |  |  |
| 6600 | 0.969 | [Download](6600/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/pattern_11.png) |  |  | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| 6000 | 0.921 | [Download](6000/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6000/previews/pattern_11.png) |  |  | [<NSFW, click to see>](6000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6000/previews/nude.png) | [<NSFW, click to see>](6000/previews/nude2.png) |  |  |
| 5400 | 0.960 | [Download](5400/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5400/previews/pattern_11.png) |  |  | [<NSFW, click to see>](5400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5400/previews/nude.png) | [<NSFW, click to see>](5400/previews/nude2.png) |  |  |
| 4800 | 0.963 | [Download](4800/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4800/previews/pattern_11.png) |  |  | [<NSFW, click to see>](4800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4800/previews/nude.png) | [<NSFW, click to see>](4800/previews/nude2.png) |  |  |
| 4200 | 0.959 | [Download](4200/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4200/previews/pattern_11.png) |  |  | [<NSFW, click to see>](4200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4200/previews/nude.png) | [<NSFW, click to see>](4200/previews/nude2.png) |  |  |
| 3600 | 0.903 | [Download](3600/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3600/previews/pattern_11.png) |  |  | [<NSFW, click to see>](3600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3600/previews/nude.png) | [<NSFW, click to see>](3600/previews/nude2.png) |  |  |
| 3000 | 0.932 | [Download](3000/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3000/previews/pattern_11.png) |  |  | [<NSFW, click to see>](3000/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3000/previews/nude.png) | [<NSFW, click to see>](3000/previews/nude2.png) |  |  |
| 2400 | 0.927 | [Download](2400/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2400/previews/pattern_11.png) |  |  | [<NSFW, click to see>](2400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2400/previews/nude.png) | [<NSFW, click to see>](2400/previews/nude2.png) |  |  |
| 1800 | 0.885 | [Download](1800/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1800/previews/pattern_11.png) |  |  | [<NSFW, click to see>](1800/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1800/previews/nude.png) | [<NSFW, click to see>](1800/previews/nude2.png) |  |  |
| 1200 | 0.822 | [Download](1200/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1200/previews/pattern_11.png) |  |  | [<NSFW, click to see>](1200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1200/previews/nude.png) | [<NSFW, click to see>](1200/previews/nude2.png) |  |  |
| 600 | 0.687 | [Download](600/tedeza_rize_istheorderarabbit.zip) |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](600/previews/pattern_11.png) |  |  | [<NSFW, click to see>](600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](600/previews/nude.png) | [<NSFW, click to see>](600/previews/nude2.png) |  |  |
|
shikari2917/mypic2
|
shikari2917
| 2023-09-28T06:09:25Z | 4 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-28T06:09:18Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of a sks rafeh
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
Gayathri142214002/Pegasus_paraphraser_2
|
Gayathri142214002
| 2023-09-28T06:03:08Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"pegasus",
"text2text-generation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-25T05:19:43Z |
---
tags:
- generated_from_trainer
model-index:
- name: Pegasus_paraphraser_2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Pegasus_paraphraser_2
This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser_1](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser_1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2781
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.2589 | 0.45 | 1000 | 0.2488 |
| 0.2693 | 0.9 | 2000 | 0.2436 |
| 0.2255 | 1.35 | 3000 | 0.2632 |
| 0.2291 | 1.8 | 4000 | 0.2603 |
| 0.2092 | 2.25 | 5000 | 0.2714 |
| 0.1955 | 2.69 | 6000 | 0.2668 |
| 0.1893 | 3.14 | 7000 | 0.2802 |
| 0.1706 | 3.59 | 8000 | 0.2781 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
anniew666/lora-roberta-large-no-anger-f4-0927
|
anniew666
| 2023-09-28T05:38:51Z | 2 | 0 |
peft
|
[
"peft",
"generated_from_trainer",
"base_model:FacebookAI/roberta-large",
"base_model:adapter:FacebookAI/roberta-large",
"license:mit",
"region:us"
] | null | 2023-09-27T19:03:52Z |
---
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
model-index:
- name: lora-roberta-large-no-anger-f4-0927
results: []
library_name: peft
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# lora-roberta-large-no-anger-f4-0927
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7106
- Accuracy: 0.7405
- Prec: 0.7387
- Recall: 0.7405
- F1: 0.7387
- B Acc: 0.5982
- Micro F1: 0.7405
- Prec Joy: 0.7558
- Recall Joy: 0.7617
- F1 Joy: 0.7587
- Prec Anger: 0.6294
- Recall Anger: 0.5631
- F1 Anger: 0.5944
- Prec Disgust: 0.4637
- Recall Disgust: 0.3854
- F1 Disgust: 0.4209
- Prec Fear: 0.4892
- Recall Fear: 0.5817
- F1 Fear: 0.5315
- Prec Neutral: 0.8292
- Recall Neutral: 0.8481
- F1 Neutral: 0.8385
- Prec Sadness: 0.6600
- Recall Sadness: 0.6140
- F1 Sadness: 0.6362
- Prec Surprise: 0.5320
- Recall Surprise: 0.4331
- F1 Surprise: 0.4775
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 25.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Prec | Recall | F1 | B Acc | Micro F1 | Prec Joy | Recall Joy | F1 Joy | Prec Anger | Recall Anger | F1 Anger | Prec Disgust | Recall Disgust | F1 Disgust | Prec Fear | Recall Fear | F1 Fear | Prec Neutral | Recall Neutral | F1 Neutral | Prec Sadness | Recall Sadness | F1 Sadness | Prec Surprise | Recall Surprise | F1 Surprise |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:--------:|:--------:|:----------:|:------:|:----------:|:------------:|:--------:|:------------:|:--------------:|:----------:|:---------:|:-----------:|:-------:|:------------:|:--------------:|:----------:|:------------:|:--------------:|:----------:|:-------------:|:---------------:|:-----------:|
| 0.8167 | 1.25 | 2049 | 0.7756 | 0.7130 | 0.7003 | 0.7130 | 0.7030 | 0.5272 | 0.7130 | 0.7252 | 0.7430 | 0.7340 | 0.6026 | 0.3749 | 0.4622 | 0.4187 | 0.3646 | 0.3898 | 0.5369 | 0.4170 | 0.4694 | 0.7763 | 0.8629 | 0.8173 | 0.6123 | 0.5784 | 0.5949 | 0.4797 | 0.3495 | 0.4044 |
| 0.7639 | 2.5 | 4098 | 0.7302 | 0.7293 | 0.7206 | 0.7293 | 0.7224 | 0.5662 | 0.7293 | 0.7361 | 0.7617 | 0.7487 | 0.6187 | 0.5198 | 0.5649 | 0.3881 | 0.4229 | 0.4048 | 0.5851 | 0.4247 | 0.4922 | 0.7961 | 0.8570 | 0.8254 | 0.6380 | 0.6185 | 0.6281 | 0.532 | 0.3585 | 0.4283 |
| 0.7395 | 3.75 | 6147 | 0.7348 | 0.7287 | 0.7328 | 0.7287 | 0.7271 | 0.5793 | 0.7287 | 0.6989 | 0.8136 | 0.7519 | 0.6786 | 0.4384 | 0.5327 | 0.4180 | 0.3875 | 0.4022 | 0.4632 | 0.5830 | 0.5162 | 0.8480 | 0.8134 | 0.8303 | 0.6648 | 0.5950 | 0.6280 | 0.5210 | 0.4241 | 0.4676 |
| 0.789 | 5.0 | 8196 | 0.7419 | 0.7275 | 0.7206 | 0.7275 | 0.7180 | 0.5511 | 0.7275 | 0.6888 | 0.8113 | 0.7450 | 0.6014 | 0.5183 | 0.5568 | 0.4038 | 0.4021 | 0.4029 | 0.5747 | 0.4305 | 0.4923 | 0.8063 | 0.8420 | 0.8238 | 0.6861 | 0.5838 | 0.6308 | 0.6224 | 0.2695 | 0.3762 |
| 0.7439 | 6.25 | 10245 | 0.7608 | 0.7207 | 0.7317 | 0.7207 | 0.7224 | 0.5858 | 0.7207 | 0.6882 | 0.8143 | 0.7459 | 0.6198 | 0.5004 | 0.5537 | 0.3944 | 0.3542 | 0.3732 | 0.4556 | 0.5843 | 0.5120 | 0.8599 | 0.7888 | 0.8228 | 0.7047 | 0.5590 | 0.6235 | 0.4535 | 0.4996 | 0.4754 |
| 0.712 | 7.5 | 12294 | 0.7240 | 0.7298 | 0.7270 | 0.7298 | 0.7263 | 0.5809 | 0.7298 | 0.7057 | 0.8043 | 0.7518 | 0.6313 | 0.4795 | 0.5450 | 0.4141 | 0.4271 | 0.4205 | 0.5707 | 0.4517 | 0.5043 | 0.8329 | 0.8214 | 0.8271 | 0.6126 | 0.6459 | 0.6288 | 0.5209 | 0.4367 | 0.4751 |
| 0.7032 | 8.75 | 14343 | 0.7095 | 0.7344 | 0.7328 | 0.7344 | 0.7317 | 0.5833 | 0.7344 | 0.7557 | 0.7479 | 0.7518 | 0.6391 | 0.5302 | 0.5796 | 0.4311 | 0.3521 | 0.3876 | 0.4724 | 0.6062 | 0.5310 | 0.8188 | 0.8498 | 0.8340 | 0.6472 | 0.6140 | 0.6301 | 0.5605 | 0.3827 | 0.4549 |
| 0.6972 | 10.0 | 16392 | 0.7108 | 0.7343 | 0.7325 | 0.7343 | 0.7317 | 0.5923 | 0.7343 | 0.7158 | 0.8038 | 0.7572 | 0.5785 | 0.5474 | 0.5625 | 0.3615 | 0.4729 | 0.4097 | 0.5714 | 0.4865 | 0.5255 | 0.8322 | 0.8288 | 0.8305 | 0.6797 | 0.5973 | 0.6358 | 0.5403 | 0.4097 | 0.4660 |
| 0.6859 | 11.25 | 18441 | 0.7211 | 0.7376 | 0.7321 | 0.7376 | 0.7322 | 0.5792 | 0.7376 | 0.7067 | 0.8093 | 0.7545 | 0.6216 | 0.5325 | 0.5736 | 0.4119 | 0.4188 | 0.4153 | 0.5720 | 0.4755 | 0.5193 | 0.8264 | 0.8407 | 0.8335 | 0.6677 | 0.6099 | 0.6375 | 0.5876 | 0.3675 | 0.4522 |
| 0.6542 | 12.5 | 20490 | 0.7143 | 0.7347 | 0.7294 | 0.7347 | 0.7307 | 0.5817 | 0.7347 | 0.7358 | 0.7824 | 0.7584 | 0.6263 | 0.5407 | 0.5804 | 0.3931 | 0.3792 | 0.3860 | 0.5700 | 0.4665 | 0.5131 | 0.8203 | 0.8364 | 0.8283 | 0.6158 | 0.6658 | 0.6398 | 0.5400 | 0.4007 | 0.4600 |
| 0.6463 | 13.75 | 22539 | 0.7022 | 0.7369 | 0.7366 | 0.7369 | 0.7354 | 0.5947 | 0.7369 | 0.7371 | 0.7864 | 0.7610 | 0.5452 | 0.6393 | 0.5885 | 0.5170 | 0.3167 | 0.3928 | 0.5519 | 0.4858 | 0.5168 | 0.8455 | 0.8218 | 0.8335 | 0.6062 | 0.6649 | 0.6342 | 0.5320 | 0.4483 | 0.4866 |
| 0.6333 | 15.0 | 24588 | 0.7106 | 0.7405 | 0.7387 | 0.7405 | 0.7387 | 0.5982 | 0.7405 | 0.7558 | 0.7617 | 0.7587 | 0.6294 | 0.5631 | 0.5944 | 0.4637 | 0.3854 | 0.4209 | 0.4892 | 0.5817 | 0.5315 | 0.8292 | 0.8481 | 0.8385 | 0.6600 | 0.6140 | 0.6362 | 0.5320 | 0.4331 | 0.4775 |
| 0.6184 | 16.25 | 26637 | 0.7199 | 0.7338 | 0.7389 | 0.7338 | 0.7348 | 0.6077 | 0.7338 | 0.7207 | 0.8008 | 0.7586 | 0.6140 | 0.5571 | 0.5842 | 0.3692 | 0.4292 | 0.3969 | 0.5024 | 0.5972 | 0.5457 | 0.8534 | 0.8079 | 0.8301 | 0.6714 | 0.6 | 0.6337 | 0.5109 | 0.4618 | 0.4851 |
| 0.5916 | 17.5 | 28686 | 0.7220 | 0.7368 | 0.7376 | 0.7368 | 0.7363 | 0.6003 | 0.7368 | 0.7426 | 0.7859 | 0.7636 | 0.5858 | 0.5713 | 0.5784 | 0.3743 | 0.4125 | 0.3925 | 0.5766 | 0.4653 | 0.5150 | 0.8479 | 0.8258 | 0.8367 | 0.5879 | 0.6676 | 0.6252 | 0.5146 | 0.4735 | 0.4932 |
| 0.5823 | 18.75 | 30735 | 0.7228 | 0.7376 | 0.7374 | 0.7376 | 0.7364 | 0.5960 | 0.7376 | 0.7210 | 0.8058 | 0.7610 | 0.6206 | 0.5534 | 0.5851 | 0.4056 | 0.3625 | 0.3828 | 0.5199 | 0.5631 | 0.5406 | 0.8460 | 0.8200 | 0.8328 | 0.6599 | 0.6126 | 0.6354 | 0.5254 | 0.4546 | 0.4875 |
| 0.5728 | 20.0 | 32784 | 0.7313 | 0.7344 | 0.7365 | 0.7344 | 0.7349 | 0.6090 | 0.7344 | 0.7295 | 0.7934 | 0.7601 | 0.5795 | 0.5907 | 0.5851 | 0.3927 | 0.4271 | 0.4092 | 0.5434 | 0.5161 | 0.5294 | 0.8462 | 0.8115 | 0.8285 | 0.6541 | 0.6311 | 0.6424 | 0.4928 | 0.4933 | 0.4930 |
| 0.5562 | 21.25 | 34833 | 0.7414 | 0.7376 | 0.7372 | 0.7376 | 0.7366 | 0.5995 | 0.7376 | 0.7372 | 0.7934 | 0.7643 | 0.6308 | 0.5258 | 0.5735 | 0.3946 | 0.425 | 0.4092 | 0.5324 | 0.5341 | 0.5332 | 0.8433 | 0.8267 | 0.8349 | 0.6139 | 0.6374 | 0.6254 | 0.5249 | 0.4537 | 0.4867 |
| 0.5348 | 22.5 | 36882 | 0.7398 | 0.7370 | 0.7374 | 0.7370 | 0.7365 | 0.6017 | 0.7370 | 0.7268 | 0.8039 | 0.7634 | 0.5844 | 0.5892 | 0.5868 | 0.4013 | 0.3937 | 0.3975 | 0.5331 | 0.5238 | 0.5284 | 0.8488 | 0.8163 | 0.8322 | 0.6473 | 0.6275 | 0.6372 | 0.5194 | 0.4573 | 0.4864 |
| 0.5202 | 23.75 | 38931 | 0.7423 | 0.7389 | 0.7379 | 0.7389 | 0.7381 | 0.6013 | 0.7389 | 0.7415 | 0.7893 | 0.7646 | 0.6020 | 0.5728 | 0.5871 | 0.4013 | 0.3896 | 0.3953 | 0.5341 | 0.5296 | 0.5318 | 0.8416 | 0.8279 | 0.8347 | 0.6410 | 0.6338 | 0.6374 | 0.5093 | 0.4663 | 0.4869 |
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
|
JeswinMS4/finetuned-llama-2
|
JeswinMS4
| 2023-09-28T05:24:52Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T05:24:50Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
CyberHarem/kuraue_hinata_encouragementofclimb
|
CyberHarem
| 2023-09-28T05:22:42Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/kuraue_hinata_encouragementofclimb",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T05:01:51Z |
---
license: mit
datasets:
- CyberHarem/kuraue_hinata_encouragementofclimb
pipeline_tag: text-to-image
tags:
- art
---
# Lora of kuraue_hinata_encouragementofclimb
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 8320, you need to download `8320/kuraue_hinata_encouragementofclimb.pt` as the embedding and `8320/kuraue_hinata_encouragementofclimb.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 8320**, with the score of 0.905. The trigger words are:
1. `kuraue_hinata_encouragementofclimb`
2. `black_hair, blush, purple_eyes, twintails, bangs, closed_mouth, outdoors, hair_between_eyes`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | pattern_18 | pattern_19 | pattern_20 | pattern_21 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:------------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9600 | 0.870 | [Download](9600/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9600/previews/bikini.png) | [<NSFW, click to see>](9600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9600/previews/nude.png) | [<NSFW, click to see>](9600/previews/nude2.png) |  |  |
| 8960 | 0.905 | [Download](8960/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8960/previews/bikini.png) | [<NSFW, click to see>](8960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8960/previews/nude.png) | [<NSFW, click to see>](8960/previews/nude2.png) |  |  |
| **8320** | **0.905** | [**Download**](8320/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8320/previews/bikini.png) | [<NSFW, click to see>](8320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8320/previews/nude.png) | [<NSFW, click to see>](8320/previews/nude2.png) |  |  |
| 7680 | 0.901 | [Download](7680/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7680/previews/bikini.png) | [<NSFW, click to see>](7680/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7680/previews/nude.png) | [<NSFW, click to see>](7680/previews/nude2.png) |  |  |
| 7040 | 0.866 | [Download](7040/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7040/previews/bikini.png) | [<NSFW, click to see>](7040/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7040/previews/nude.png) | [<NSFW, click to see>](7040/previews/nude2.png) |  |  |
| 6400 | 0.900 | [Download](6400/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6400/previews/bikini.png) | [<NSFW, click to see>](6400/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6400/previews/nude.png) | [<NSFW, click to see>](6400/previews/nude2.png) |  |  |
| 5760 | 0.897 | [Download](5760/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5760/previews/bikini.png) | [<NSFW, click to see>](5760/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5760/previews/nude.png) | [<NSFW, click to see>](5760/previews/nude2.png) |  |  |
| 5120 | 0.889 | [Download](5120/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5120/previews/bikini.png) | [<NSFW, click to see>](5120/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5120/previews/nude.png) | [<NSFW, click to see>](5120/previews/nude2.png) |  |  |
| 4480 | 0.862 | [Download](4480/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4480/previews/bikini.png) | [<NSFW, click to see>](4480/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4480/previews/nude.png) | [<NSFW, click to see>](4480/previews/nude2.png) |  |  |
| 3840 | 0.899 | [Download](3840/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3840/previews/bikini.png) | [<NSFW, click to see>](3840/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3840/previews/nude.png) | [<NSFW, click to see>](3840/previews/nude2.png) |  |  |
| 3200 | 0.896 | [Download](3200/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3200/previews/bikini.png) | [<NSFW, click to see>](3200/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3200/previews/nude.png) | [<NSFW, click to see>](3200/previews/nude2.png) |  |  |
| 2560 | 0.829 | [Download](2560/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2560/previews/bikini.png) | [<NSFW, click to see>](2560/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2560/previews/nude.png) | [<NSFW, click to see>](2560/previews/nude2.png) |  |  |
| 1920 | 0.814 | [Download](1920/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1920/previews/bikini.png) | [<NSFW, click to see>](1920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1920/previews/nude.png) | [<NSFW, click to see>](1920/previews/nude2.png) |  |  |
| 1280 | 0.734 | [Download](1280/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1280/previews/bikini.png) | [<NSFW, click to see>](1280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1280/previews/nude.png) | [<NSFW, click to see>](1280/previews/nude2.png) |  |  |
| 640 | 0.598 | [Download](640/kuraue_hinata_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](640/previews/bikini.png) | [<NSFW, click to see>](640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](640/previews/nude.png) | [<NSFW, click to see>](640/previews/nude2.png) |  |  |
|
roa7n/gpt2-human_nontata_promoters-randomized_5_layers_0.003_lr_8_e
|
roa7n
| 2023-09-28T05:19:26Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T05:19:23Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
Natet/mt5-small-finetuned-amazon-en-es
|
Natet
| 2023-09-28T05:11:18Z | 11 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"summarization",
"generated_from_trainer",
"en",
"es",
"dataset:amazon_reviews_multi",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2023-09-27T10:22:02Z |
---
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-amazon-en-es
results: []
datasets:
- amazon_reviews_multi
language:
- en
- es
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of google/mt5-small on the amazon_reviews_multi dataset (https://huggingface.co/datasets/amazon_reviews_multi),
with a filter applied to reviews about books.
The filter_books function is used to filter examples in the data and returns only those that belong to the "book" or "digital ebook purchase" category.
It achieves the following results on the evaluation set:
- Loss: 3.0270
- Rouge1: 16.8614
- Rouge2: 8.3352
- Rougel: 16.5595
- Rougelsum: 16.5755
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
| 7.376 | 1.0 | 1209 | 3.3114 | 13.6834 | 5.4759 | 13.2778 | 13.3315 |
| 3.9197 | 2.0 | 2418 | 3.1662 | 15.4107 | 7.396 | 15.0443 | 15.0493 |
| 3.5954 | 3.0 | 3627 | 3.0844 | 15.4126 | 7.2537 | 15.0816 | 15.1281 |
| 3.4243 | 4.0 | 4836 | 3.0384 | 15.9869 | 7.7568 | 15.7054 | 15.6149 |
| 3.3145 | 5.0 | 6045 | 3.0512 | 17.3119 | 8.412 | 16.8461 | 16.7631 |
| 3.2597 | 6.0 | 7254 | 3.0237 | 16.7165 | 7.9706 | 16.4276 | 16.3935 |
| 3.2094 | 7.0 | 8463 | 3.0308 | 17.4737 | 8.7048 | 17.0836 | 17.0624 |
| 3.1886 | 8.0 | 9672 | 3.0270 | 16.8614 | 8.3352 | 16.5595 | 16.5755 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
|
ramanirudh/distilbert-base-uncased-finetuned-squad
|
ramanirudh
| 2023-09-28T05:07:20Z | 10 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-09-28T01:54:08Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: distilbert-base-uncased-finetuned-squad
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1602
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.211 | 1.0 | 5533 | 1.1554 |
| 0.9476 | 2.0 | 11066 | 1.1268 |
| 0.7422 | 3.0 | 16599 | 1.1602 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
flytech/Ruckus-13b-27
|
flytech
| 2023-09-28T04:08:13Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-13b-hf",
"base_model:finetune:meta-llama/Llama-2-13b-hf",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-27T22:57:31Z |
---
base_model: meta-llama/Llama-2-13b-hf
tags:
- generated_from_trainer
model-index:
- name: Ruckus-13b-27
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Ruckus-13b-27
This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 12
### Training results
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
CyberHarem/yukimura_aoi_encouragementofclimb
|
CyberHarem
| 2023-09-28T04:02:30Z | 0 | 0 | null |
[
"art",
"text-to-image",
"dataset:CyberHarem/yukimura_aoi_encouragementofclimb",
"license:mit",
"region:us"
] |
text-to-image
| 2023-09-28T03:43:45Z |
---
license: mit
datasets:
- CyberHarem/yukimura_aoi_encouragementofclimb
pipeline_tag: text-to-image
tags:
- art
---
# Lora of yukimura_aoi_encouragementofclimb
This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs).
The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11).
After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.
For example, if you want to use the model from step 9240, you need to download `9240/yukimura_aoi_encouragementofclimb.pt` as the embedding and `9240/yukimura_aoi_encouragementofclimb.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters.
**The best step we recommend is 9240**, with the score of 0.913. The trigger words are:
1. `yukimura_aoi_encouragementofclimb`
2. `blush, short_hair, green_eyes, hair_ornament, hairclip, grey_hair, brown_hair`
For the following groups, it is not recommended to use this model and we express regret:
1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
5. Individuals who finds the generated image content offensive to their values.
These are available steps:
| Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata |
|:---------|:----------|:-----------------------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-----------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------|:--------------------------------------------------|:-------------------------------------|:-------------------------------------|:-------------------------------------|:-----------------------------------------------|:------------------------------------------------|:-------------------------------------|:-----------------------------------------|
| 9900 | 0.896 | [Download](9900/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9900/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9900/previews/nude.png) | [<NSFW, click to see>](9900/previews/nude2.png) |  |  |
| **9240** | **0.913** | [**Download**](9240/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](9240/previews/bondage.png) |  |  |  | [<NSFW, click to see>](9240/previews/nude.png) | [<NSFW, click to see>](9240/previews/nude2.png) |  |  |
| 8580 | 0.902 | [Download](8580/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8580/previews/bondage.png) |  |  |  | [<NSFW, click to see>](8580/previews/nude.png) | [<NSFW, click to see>](8580/previews/nude2.png) |  |  |
| 7920 | 0.855 | [Download](7920/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7920/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7920/previews/nude.png) | [<NSFW, click to see>](7920/previews/nude2.png) |  |  |
| 7260 | 0.893 | [Download](7260/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7260/previews/bondage.png) |  |  |  | [<NSFW, click to see>](7260/previews/nude.png) | [<NSFW, click to see>](7260/previews/nude2.png) |  |  |
| 6600 | 0.891 | [Download](6600/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](6600/previews/bondage.png) |  |  |  | [<NSFW, click to see>](6600/previews/nude.png) | [<NSFW, click to see>](6600/previews/nude2.png) |  |  |
| 5940 | 0.882 | [Download](5940/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5940/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5940/previews/nude.png) | [<NSFW, click to see>](5940/previews/nude2.png) |  |  |
| 5280 | 0.870 | [Download](5280/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5280/previews/bondage.png) |  |  |  | [<NSFW, click to see>](5280/previews/nude.png) | [<NSFW, click to see>](5280/previews/nude2.png) |  |  |
| 4620 | 0.867 | [Download](4620/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4620/previews/bondage.png) |  |  |  | [<NSFW, click to see>](4620/previews/nude.png) | [<NSFW, click to see>](4620/previews/nude2.png) |  |  |
| 3960 | 0.869 | [Download](3960/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3960/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3960/previews/nude.png) | [<NSFW, click to see>](3960/previews/nude2.png) |  |  |
| 3300 | 0.888 | [Download](3300/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](3300/previews/bondage.png) |  |  |  | [<NSFW, click to see>](3300/previews/nude.png) | [<NSFW, click to see>](3300/previews/nude2.png) |  |  |
| 2640 | 0.863 | [Download](2640/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2640/previews/bondage.png) |  |  |  | [<NSFW, click to see>](2640/previews/nude.png) | [<NSFW, click to see>](2640/previews/nude2.png) |  |  |
| 1980 | 0.796 | [Download](1980/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1980/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1980/previews/nude.png) | [<NSFW, click to see>](1980/previews/nude2.png) |  |  |
| 1320 | 0.791 | [Download](1320/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1320/previews/bondage.png) |  |  |  | [<NSFW, click to see>](1320/previews/nude.png) | [<NSFW, click to see>](1320/previews/nude2.png) |  |  |
| 660 | 0.722 | [Download](660/yukimura_aoi_encouragementofclimb.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | [<NSFW, click to see>](660/previews/bondage.png) |  |  |  | [<NSFW, click to see>](660/previews/nude.png) | [<NSFW, click to see>](660/previews/nude2.png) |  |  |
|
DThai/layoutlm-funsd-tf
|
DThai
| 2023-09-28T03:51:17Z | 60 | 0 |
transformers
|
[
"transformers",
"tf",
"layoutlm",
"token-classification",
"generated_from_keras_callback",
"base_model:microsoft/layoutlm-base-uncased",
"base_model:finetune:microsoft/layoutlm-base-uncased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-28T03:50:52Z |
---
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: layoutlm-funsd-tf
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# layoutlm-funsd-tf
This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.4674
- Validation Loss: 0.6405
- Train Overall Precision: 0.7082
- Train Overall Recall: 0.7637
- Train Overall F1: 0.7349
- Train Overall Accuracy: 0.7984
- Epoch: 4
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
### Training results
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
| 1.7185 | 1.4324 | 0.2236 | 0.2805 | 0.2488 | 0.5123 | 0 |
| 1.1768 | 0.9053 | 0.5468 | 0.6744 | 0.6039 | 0.7257 | 1 |
| 0.7782 | 0.6968 | 0.6512 | 0.7250 | 0.6861 | 0.7760 | 2 |
| 0.5777 | 0.6506 | 0.6826 | 0.7682 | 0.7229 | 0.7924 | 3 |
| 0.4674 | 0.6405 | 0.7082 | 0.7637 | 0.7349 | 0.7984 | 4 |
### Framework versions
- Transformers 4.33.3
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
|
pepoo20/openai-whisper-mini-v2-LORA-colab
|
pepoo20
| 2023-09-28T03:50:45Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T03:50:43Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
oshita-n/textual_inversion_8
|
oshita-n
| 2023-09-28T03:39:49Z | 34 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T03:34:25Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - oshita-n/textual_inversion_8
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
Gayathri142214002/t5_Question_Generation_2
|
Gayathri142214002
| 2023-09-28T03:32:57Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-20T07:04:36Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5_Question_Generation_2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# t5_Question_Generation_2
This model is a fine-tuned version of [Gayathri142214002/t5_Question_Generation](https://huggingface.co/Gayathri142214002/t5_Question_Generation) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5549
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0256 | 0.25 | 100 | 0.7578 |
| 0.7848 | 0.5 | 200 | 0.6872 |
| 0.6682 | 0.75 | 300 | 0.6440 |
| 0.6444 | 1.0 | 400 | 0.5939 |
| 0.4903 | 1.25 | 500 | 0.5944 |
| 0.4894 | 1.5 | 600 | 0.5675 |
| 0.5001 | 1.75 | 700 | 0.5546 |
| 0.4891 | 2.0 | 800 | 0.5469 |
| 0.3779 | 2.25 | 900 | 0.5523 |
| 0.3802 | 2.5 | 1000 | 0.5609 |
| 0.395 | 2.74 | 1100 | 0.5483 |
| 0.3916 | 2.99 | 1200 | 0.5482 |
| 0.3383 | 3.24 | 1300 | 0.5634 |
| 0.3391 | 3.49 | 1400 | 0.5629 |
| 0.3294 | 3.74 | 1500 | 0.5573 |
| 0.3363 | 3.99 | 1600 | 0.5413 |
| 0.2851 | 4.24 | 1700 | 0.5533 |
| 0.3032 | 4.49 | 1800 | 0.5575 |
| 0.2995 | 4.74 | 1900 | 0.5548 |
| 0.3091 | 4.99 | 2000 | 0.5396 |
| 0.2606 | 5.24 | 2100 | 0.5420 |
| 0.2622 | 5.49 | 2200 | 0.5468 |
| 0.2817 | 5.74 | 2300 | 0.5460 |
| 0.2743 | 5.99 | 2400 | 0.5473 |
| 0.2501 | 6.24 | 2500 | 0.5542 |
| 0.2484 | 6.49 | 2600 | 0.5558 |
| 0.2388 | 6.74 | 2700 | 0.5542 |
| 0.2414 | 6.99 | 2800 | 0.5549 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
roa7n/gpt2-human_nontata_promoters-randomized_5_layers_3e-05_lr_2_e
|
roa7n
| 2023-09-28T03:30:19Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T03:30:16Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
omidvaramin/Ht5-small
|
omidvaramin
| 2023-09-28T03:25:36Z | 112 | 1 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-26T23:37:27Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Ht5-small
<!-- Provide a quick summary of what the model is/does. -->
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on Newsroom dataset to generate news headlines. To ask model to generate headliens
"Headline: " should be appended to the beginning of the article.
## Intended uses & limitations
You can use this model for headline generation task on English news articles.
### Usage
```python
article = """Two of the OPEC oil cartels 11 members, Nigeria and Venezuela, said today \
that they would voluntarily cut production in response to declining crude oil prices, which \
have fallen 20 percent from their peak two months ago.
The move, which would take less than 200,000 barrels of oil a day off the market, follows days \
of mixed signals from some OPEC officials, who have voiced increasing concern about the rapid \
drop in prices. Nigerias oil minister, Edmund Daukoru, who is president of OPEC this year, \
recently said the price of oil was very low.
Nigeria and Venezuela, which have generally been price hawks within the group, said their decision \
to cut production grew out of an informal deal reached at OPECs last meeting, earlier this month, \
to pare output if prices fell steeply. Some OPEC representatives have grown anxious at the slide in \
the oil futures markets, where prices for benchmark contracts have fallen from a midsummer high of \
$77.03 a barrel.
But traders shrugged off the announcement of the production cuts today. On the New York Mercantile \
Exchange, the most widely watched contract price light, low-sulfur crude for delivery next month \
traded this afternoon at $62.30 a barrel, down 0.7 percent.
Mr. Daukoru has been in contact with other OPEC ministers to discuss prices, which on Monday briefly \
slipped below $60 a barrel for the first time in six months. But the Organization of the Petroleum \
Exporting Countries, as the cartel is formally known, denied any shift in policy.
We are not currently concerned, a delegate from one of OPECs Gulf members said. The prices are \
currently manageable and fair. We are not overly alarmed by the prices. It is not a cause for alarm. \
It's the market working.
It is not unusual for oil prices to fall after Labor Day and the conclusion of the summer travel season. \
Demand tends to slow in the third quarter, and refiners reduce their output for seasonal maintenance; \
consumption picks up again with the first winter cold in the Western Hemisphere, and prices sometimes do as well.
We are not going to push extra oil in the market or force it down our customers throats, we just respond to demand, \
the delegate from the Gulf said.
Still, contradictory statements from senior OPEC representatives have sown doubt about the oil cartel's strategy. \
Whether OPEC countries actually reduce their output or not, the mixed messages have at least succeeded in one way: \
oil traders have been persuaded that OPEC is willing to step in to defend prices, and have traded on that belief, \
slowing the recent price decline.
While apparently fanciful, reports of an imminent output cut reflect two hard facts: stocks are building faster than \
expected, and several producers have an incredibly low pain threshold when it comes to price drops, Antoine Halff, an \
energy analyst with Fimat, wrote in a note to clients today. However, more price declines will likely be needed before \
OPEC producers decide on any coordinated move.
Venezuela, which pumps about 2.5 million barrels a day, said it would cut its daily output by 50,000 barrels, or about 2 \
percent, starting Oct. 1. Nigeria said it would trim its exports by 5 percent on the same date, a reduction of about \
120,000 barrels a day from its current output of about 3.8 million barrels a day.
They are trying to influence the psychology of the market, said Larry Goldstein, a veteran oil analyst and the president \
of the Petroleum Industry Research Foundation in New York. Although they are reacting to the reduction in demand, they \
are trying to convince the market that they are actually anticipating it, by making cuts ahead of the market. But they \
are simply reacting to it, which is how markets should operate."""
import transformers
import os
import torch
#If you have more than one GPU, you can specify here which one to use
os.environ["CUDA_VISIBLE_DEVICES"]="5"
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
#appending the task identifier to the beginning of input
article = "Headline: " + article
model = AutoModelForSeq2SeqLM.from_pretrained("omidvaramin/Ht5-small").to(device)
tokenizer = AutoTokenizer.from_pretrained("omidvaramin/Ht5-small")
#encodign article using tokenizer
encoding = tokenizer(article
, max_length=1024
, truncation=True
,return_tensors="pt"
,padding='longest')
input_ids = encoding['input_ids']
attention_masks = encoding['attention_mask']
#transfering the data into GPU
input_ids = input_ids.to(device)
attention_masks = attention_masks.to(device)
#generate headlines using kbeam technique
beam_outputs = model.generate(
input_ids = input_ids,
attention_mask = attention_masks
,do_sample = False
,num_beams = 4
,max_length = 20
,min_length = 1
,num_return_sequences = 1
)
result = tokenizer.batch_decode(beam_outputs,
skip_special_tokens=True)
print(result[0])
>>> [{'OPEC Members Say They Will Cut Oil Production'}]
```
### BibTeX entry and citation info
```bibtex
@ARTICLE{10154027,
author={Omidvar, Amin and An, Aijun},
journal={IEEE Access},
title={Learning to Generate Popular Headlines},
year={2023},
volume={11},
number={},
pages={60904-60914},
doi={10.1109/ACCESS.2023.3286853}}
|
xinli95/q-Taxi-v3
|
xinli95
| 2023-09-28T03:24:25Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-28T03:24:23Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="xinli95/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
omidvaramin/Hprophetnet-large
|
omidvaramin
| 2023-09-28T03:23:27Z | 97 | 1 |
transformers
|
[
"transformers",
"pytorch",
"prophetnet",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-24T23:58:19Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Hprophetnet-large
<!-- Provide a quick summary of what the model is/does. -->
This model is a fine-tuned version of [prophetnet-large-uncased-cnndm](https://huggingface.co/microsoft/prophetnet-large-uncased-cnndm) on Newsroom dataset to generate news headlines. To ask model to generate headliens
"Headline: " should be appended to the beginning of the article.
## Intended uses & limitations
You can use this model for headline generation task on English news articles.
### Usage
```python
article = """Two of the OPEC oil cartels 11 members, Nigeria and Venezuela, said today \
that they would voluntarily cut production in response to declining crude oil prices, which \
have fallen 20 percent from their peak two months ago.
The move, which would take less than 200,000 barrels of oil a day off the market, follows days \
of mixed signals from some OPEC officials, who have voiced increasing concern about the rapid \
drop in prices. Nigerias oil minister, Edmund Daukoru, who is president of OPEC this year, \
recently said the price of oil was very low.
Nigeria and Venezuela, which have generally been price hawks within the group, said their decision \
to cut production grew out of an informal deal reached at OPECs last meeting, earlier this month, \
to pare output if prices fell steeply. Some OPEC representatives have grown anxious at the slide in \
the oil futures markets, where prices for benchmark contracts have fallen from a midsummer high of \
$77.03 a barrel.
But traders shrugged off the announcement of the production cuts today. On the New York Mercantile \
Exchange, the most widely watched contract price light, low-sulfur crude for delivery next month \
traded this afternoon at $62.30 a barrel, down 0.7 percent.
Mr. Daukoru has been in contact with other OPEC ministers to discuss prices, which on Monday briefly \
slipped below $60 a barrel for the first time in six months. But the Organization of the Petroleum \
Exporting Countries, as the cartel is formally known, denied any shift in policy.
We are not currently concerned, a delegate from one of OPECs Gulf members said. The prices are \
currently manageable and fair. We are not overly alarmed by the prices. It is not a cause for alarm. \
It's the market working.
It is not unusual for oil prices to fall after Labor Day and the conclusion of the summer travel season. \
Demand tends to slow in the third quarter, and refiners reduce their output for seasonal maintenance; \
consumption picks up again with the first winter cold in the Western Hemisphere, and prices sometimes do as well.
We are not going to push extra oil in the market or force it down our customers throats, we just respond to demand, \
the delegate from the Gulf said.
Still, contradictory statements from senior OPEC representatives have sown doubt about the oil cartel's strategy. \
Whether OPEC countries actually reduce their output or not, the mixed messages have at least succeeded in one way: \
oil traders have been persuaded that OPEC is willing to step in to defend prices, and have traded on that belief, \
slowing the recent price decline.
While apparently fanciful, reports of an imminent output cut reflect two hard facts: stocks are building faster than \
expected, and several producers have an incredibly low pain threshold when it comes to price drops, Antoine Halff, an \
energy analyst with Fimat, wrote in a note to clients today. However, more price declines will likely be needed before \
OPEC producers decide on any coordinated move.
Venezuela, which pumps about 2.5 million barrels a day, said it would cut its daily output by 50,000 barrels, or about 2 \
percent, starting Oct. 1. Nigeria said it would trim its exports by 5 percent on the same date, a reduction of about \
120,000 barrels a day from its current output of about 3.8 million barrels a day.
They are trying to influence the psychology of the market, said Larry Goldstein, a veteran oil analyst and the president \
of the Petroleum Industry Research Foundation in New York. Although they are reacting to the reduction in demand, they \
are trying to convince the market that they are actually anticipating it, by making cuts ahead of the market. But they \
are simply reacting to it, which is how markets should operate."""
import transformers
import os
import torch
#If you have more than one GPU, you can specify here which one to use
os.environ["CUDA_VISIBLE_DEVICES"]="5"
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
#appending the task identifier to the beginning of input
article = "Headline: " + article
model = AutoModelForSeq2SeqLM.from_pretrained("omidvaramin/Hprophetnet-large").to(device)
tokenizer = AutoTokenizer.from_pretrained("omidvaramin/Hprophetnet-large")
#encodign article using tokenizer
encoding = tokenizer(article
, max_length=1024
, truncation=True
,return_tensors="pt"
,padding='longest')
input_ids = encoding['input_ids']
attention_masks = encoding['attention_mask']
#transfering the data into GPU
input_ids = input_ids.to(device)
attention_masks = attention_masks.to(device)
#generate headlines using kbeam technique
beam_outputs = model.generate(
input_ids = input_ids,
attention_mask = attention_masks
,do_sample = False
,num_beams = 4
,max_length = 20
,min_length = 1
,num_return_sequences = 1
)
result = tokenizer.batch_decode(beam_outputs,
skip_special_tokens=True)
print(result[0])
>>> [{'opec members agree to cut oil output'}]
```
### BibTeX entry and citation info
```bibtex
@ARTICLE{10154027,
author={Omidvar, Amin and An, Aijun},
journal={IEEE Access},
title={Learning to Generate Popular Headlines},
year={2023},
volume={11},
number={},
pages={60904-60914},
doi={10.1109/ACCESS.2023.3286853}}
|
omidvaramin/HBART
|
omidvaramin
| 2023-09-28T03:22:36Z | 111 | 1 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-09-24T21:02:54Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Hprophetnet-large
<!-- Provide a quick summary of what the model is/does. -->
This model is a fine-tuned version of [bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on Newsroom dataset to generate news headlines. To ask model to generate headliens
"Headline: " should be appended to the beginning of the article.
## Intended uses & limitations
You can use this model for headline generation task on English news articles.
### Usage
```python
article = """Two of the OPEC oil cartels 11 members, Nigeria and Venezuela, said today \
that they would voluntarily cut production in response to declining crude oil prices, which \
have fallen 20 percent from their peak two months ago.
The move, which would take less than 200,000 barrels of oil a day off the market, follows days \
of mixed signals from some OPEC officials, who have voiced increasing concern about the rapid \
drop in prices. Nigerias oil minister, Edmund Daukoru, who is president of OPEC this year, \
recently said the price of oil was very low.
Nigeria and Venezuela, which have generally been price hawks within the group, said their decision \
to cut production grew out of an informal deal reached at OPECs last meeting, earlier this month, \
to pare output if prices fell steeply. Some OPEC representatives have grown anxious at the slide in \
the oil futures markets, where prices for benchmark contracts have fallen from a midsummer high of \
$77.03 a barrel.
But traders shrugged off the announcement of the production cuts today. On the New York Mercantile \
Exchange, the most widely watched contract price light, low-sulfur crude for delivery next month \
traded this afternoon at $62.30 a barrel, down 0.7 percent.
Mr. Daukoru has been in contact with other OPEC ministers to discuss prices, which on Monday briefly \
slipped below $60 a barrel for the first time in six months. But the Organization of the Petroleum \
Exporting Countries, as the cartel is formally known, denied any shift in policy.
We are not currently concerned, a delegate from one of OPECs Gulf members said. The prices are \
currently manageable and fair. We are not overly alarmed by the prices. It is not a cause for alarm. \
It's the market working.
It is not unusual for oil prices to fall after Labor Day and the conclusion of the summer travel season. \
Demand tends to slow in the third quarter, and refiners reduce their output for seasonal maintenance; \
consumption picks up again with the first winter cold in the Western Hemisphere, and prices sometimes do as well.
We are not going to push extra oil in the market or force it down our customers throats, we just respond to demand, \
the delegate from the Gulf said.
Still, contradictory statements from senior OPEC representatives have sown doubt about the oil cartel's strategy. \
Whether OPEC countries actually reduce their output or not, the mixed messages have at least succeeded in one way: \
oil traders have been persuaded that OPEC is willing to step in to defend prices, and have traded on that belief, \
slowing the recent price decline.
While apparently fanciful, reports of an imminent output cut reflect two hard facts: stocks are building faster than \
expected, and several producers have an incredibly low pain threshold when it comes to price drops, Antoine Halff, an \
energy analyst with Fimat, wrote in a note to clients today. However, more price declines will likely be needed before \
OPEC producers decide on any coordinated move.
Venezuela, which pumps about 2.5 million barrels a day, said it would cut its daily output by 50,000 barrels, or about 2 \
percent, starting Oct. 1. Nigeria said it would trim its exports by 5 percent on the same date, a reduction of about \
120,000 barrels a day from its current output of about 3.8 million barrels a day.
They are trying to influence the psychology of the market, said Larry Goldstein, a veteran oil analyst and the president \
of the Petroleum Industry Research Foundation in New York. Although they are reacting to the reduction in demand, they \
are trying to convince the market that they are actually anticipating it, by making cuts ahead of the market. But they \
are simply reacting to it, which is how markets should operate."""
import transformers
import os
import torch
#If you have more than one GPU, you can specify here which one to use
os.environ["CUDA_VISIBLE_DEVICES"]="5"
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
#appending the task identifier to the beginning of input
article = "Headline: " + article
model = AutoModelForSeq2SeqLM.from_pretrained("omidvaramin/HBART").to(device)
tokenizer = AutoTokenizer.from_pretrained("omidvaramin/HBART")
#encodign article using tokenizer
encoding = tokenizer(article
, max_length=1024
, truncation=True
,return_tensors="pt"
,padding='longest')
input_ids = encoding['input_ids']
attention_masks = encoding['attention_mask']
#transfering the data into GPU
input_ids = input_ids.to(device)
attention_masks = attention_masks.to(device)
#generate headlines using kbeam technique
beam_outputs = model.generate(
input_ids = input_ids,
attention_mask = attention_masks
,do_sample = False
,num_beams = 4
,max_length = 20
,min_length = 1
,num_return_sequences = 1
)
result = tokenizer.batch_decode(beam_outputs,
skip_special_tokens=True)
print(result[0])
>>> [{'2 OPEC Nations Agree to Cut Oil Output'}]
```
### BibTeX entry and citation info
```bibtex
@ARTICLE{10154027,
author={Omidvar, Amin and An, Aijun},
journal={IEEE Access},
title={Learning to Generate Popular Headlines},
year={2023},
volume={11},
number={},
pages={60904-60914},
doi={10.1109/ACCESS.2023.3286853}}
|
tylerkiser/ppo-Huggy
|
tylerkiser
| 2023-09-28T03:11:51Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-09-28T03:06:07Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: tylerkiser/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
pablorfb/chatbot
|
pablorfb
| 2023-09-28T02:59:30Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T02:59:27Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
pablorfb/outputs
|
pablorfb
| 2023-09-28T02:59:27Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:projecte-aina/aguila-7b",
"base_model:finetune:projecte-aina/aguila-7b",
"region:us"
] | null | 2023-09-28T02:59:24Z |
---
base_model: projecte-aina/aguila-7b
tags:
- generated_from_trainer
model-index:
- name: outputs
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# outputs
This model is a fine-tuned version of [projecte-aina/aguila-7b](https://huggingface.co/projecte-aina/aguila-7b) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 120
### Training results
### Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
|
VuongQuoc/checkpoints_27_9_microsoft_deberta_21_9
|
VuongQuoc
| 2023-09-28T02:39:59Z | 1 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deberta-v2",
"multiple-choice",
"generated_from_trainer",
"base_model:VuongQuoc/checkpoints_26_9_microsoft_deberta_21_9",
"base_model:finetune:VuongQuoc/checkpoints_26_9_microsoft_deberta_21_9",
"license:mit",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-09-26T16:11:41Z |
---
license: mit
base_model: VuongQuoc/checkpoints_26_9_microsoft_deberta_21_9
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: checkpoints_27_9_microsoft_deberta_21_9
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# checkpoints_27_9_microsoft_deberta_21_9
This model is a fine-tuned version of [VuongQuoc/checkpoints_26_9_microsoft_deberta_21_9](https://huggingface.co/VuongQuoc/checkpoints_26_9_microsoft_deberta_21_9) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6632
- Map@3: 0.8608
- Accuracy: 0.775
- MAX_INPUT = 256
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Map@3 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
| 0.6308 | 0.05 | 100 | 0.6775 | 0.8842 | 0.815 |
| 0.3472 | 0.11 | 200 | 0.7255 | 0.8767 | 0.805 |
| 0.2267 | 0.16 | 300 | 0.7786 | 0.8608 | 0.785 |
| 0.143 | 0.21 | 400 | 0.8580 | 0.8333 | 0.735 |
| 0.0723 | 0.27 | 500 | 0.9517 | 0.8358 | 0.735 |
| 0.3952 | 0.32 | 600 | 0.6632 | 0.8608 | 0.775 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.9.0
- Tokenizers 0.13.3
|
roa7n/gpt2-human_nontata_promoters-randomized_5_layers_0.003_lr_2_e
|
roa7n
| 2023-09-28T02:25:09Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-28T02:25:07Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
checkiejan/multi-qa-mpnet-base-dot-v1-covidqa-search-triplet-100
|
checkiejan
| 2023-09-28T02:24:39Z | 13 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-09-28T02:24:14Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, cls pooling.
sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 298 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.TripletLoss.TripletLoss` with parameters:
```
{'distance_metric': 'TripletDistanceMetric.EUCLIDEAN', 'triplet_margin': 5}
```
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 50,
"evaluator": "sentence_transformers.evaluation.TripletEvaluator.TripletEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 29,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
oshita-n/textual_inversion_3
|
oshita-n
| 2023-09-28T02:22:02Z | 35 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-28T02:16:32Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - oshita-n/textual_inversion_3
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
hw2942/chinese-macbert-base-SSE50
|
hw2942
| 2023-09-28T02:06:24Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:hfl/chinese-macbert-base",
"base_model:finetune:hfl/chinese-macbert-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-28T02:00:13Z |
---
license: apache-2.0
base_model: hfl/chinese-macbert-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: chinese-macbert-base-wallstreetcn-morning-news-market-overview-SSE50-3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chinese-macbert-base-wallstreetcn-morning-news-market-overview-SSE50-3
This model is a fine-tuned version of [hfl/chinese-macbert-base](https://huggingface.co/hfl/chinese-macbert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5654
- Accuracy: 0.7576
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 34 | 0.4055 | 0.8485 |
| No log | 2.0 | 68 | 0.8733 | 0.6667 |
| No log | 3.0 | 102 | 0.9532 | 0.7273 |
| No log | 4.0 | 136 | 1.3407 | 0.7576 |
| No log | 5.0 | 170 | 1.5447 | 0.6970 |
| No log | 6.0 | 204 | 1.4398 | 0.7273 |
| No log | 7.0 | 238 | 1.3168 | 0.7879 |
| No log | 8.0 | 272 | 1.4771 | 0.7576 |
| No log | 9.0 | 306 | 1.5679 | 0.7576 |
| No log | 10.0 | 340 | 1.5654 | 0.7576 |
### Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
hkbluesky/distilbert-base-uncased-finetuned-emotion
|
hkbluesky
| 2023-09-28T01:45:59Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-07-21T05:45:05Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.928
- name: F1
type: f1
value: 0.9276533528239984
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2170
- Accuracy: 0.928
- F1: 0.9277
## Model description
0-sadness
1-joy
2-love
3-anger
4-fear
5-surprise
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.7878 | 1.0 | 250 | 0.2981 | 0.915 | 0.9135 |
| 0.2452 | 2.0 | 500 | 0.2170 | 0.928 | 0.9277 |
### Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.