modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-05 00:41:53
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 539
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-05 00:41:31
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
akkasi/roberta-large-mnli_Peft_Lora_Tuning
|
akkasi
| 2023-10-14T16:51:27Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:FacebookAI/roberta-large-mnli",
"base_model:adapter:FacebookAI/roberta-large-mnli",
"region:us"
] | null | 2023-10-14T16:51:26Z |
---
library_name: peft
base_model: roberta-large-mnli
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
TheBloke/SauerkrautLM-13B-v1-GGUF
|
TheBloke
| 2023-10-14T16:47:34Z | 98 | 3 |
transformers
|
[
"transformers",
"gguf",
"llama",
"text-generation",
"de",
"en",
"base_model:VAGOsolutions/SauerkrautLM-13b-v1",
"base_model:quantized:VAGOsolutions/SauerkrautLM-13b-v1",
"license:llama2",
"region:us"
] |
text-generation
| 2023-10-14T16:32:22Z |
---
base_model: VAGOsolutions/SauerkrautLM-13b-v1
inference: false
language:
- de
- en
library_name: transformers
license: llama2
model_creator: VAGO solutions
model_name: SauerkrautLM 13B v1
model_type: llama
pipeline_tag: text-generation
prompt_template: "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent\
\ gibt hilfreiche, detaillierte und h\xF6fliche Antworten. \nUser: {prompt} \nAssistant:\n"
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 -->
# SauerkrautLM 13B v1 - GGUF
- Model creator: [VAGO solutions](https://huggingface.co/VAGOsolutions)
- Original model: [SauerkrautLM 13B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [VAGO solutions's SauerkrautLM 13B v1](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1).
<!-- 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/SauerkrautLM-13B-v1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF)
* [VAGO solutions's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Sauerkraut
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
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 |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [sauerkrautlm-13b-v1.Q2_K.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [sauerkrautlm-13b-v1.Q3_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [sauerkrautlm-13b-v1.Q3_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [sauerkrautlm-13b-v1.Q3_K_L.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [sauerkrautlm-13b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [sauerkrautlm-13b-v1.Q4_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [sauerkrautlm-13b-v1.Q4_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [sauerkrautlm-13b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [sauerkrautlm-13b-v1.Q5_K_S.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [sauerkrautlm-13b-v1.Q5_K_M.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [sauerkrautlm-13b-v1.Q6_K.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [sauerkrautlm-13b-v1.Q8_0.gguf](https://huggingface.co/TheBloke/SauerkrautLM-13B-v1-GGUF/blob/main/sauerkrautlm-13b-v1.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/SauerkrautLM-13B-v1-GGUF and below it, a specific filename to download, such as: sauerkrautlm-13b-v1.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/SauerkrautLM-13B-v1-GGUF sauerkrautlm-13b-v1.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/SauerkrautLM-13B-v1-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/SauerkrautLM-13B-v1-GGUF sauerkrautlm-13b-v1.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 sauerkrautlm-13b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten. \nUser: {prompt} \nAssistant:"
```
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/SauerkrautLM-13B-v1-GGUF", model_file="sauerkrautlm-13b-v1.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**: 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 start -->
# Original model card: VAGO solutions's SauerkrautLM 13B v1
## VAGO solutions SauerkrautLM
Introducing SauerkrautLM-v1 - Your German Language Powerhouse!
We are thrilled to unveil our **very first release**, **SauerkrautLM-v1**. This remarkable creation marks a significant milestone as it is specifically **tailored for the German-speaking community**. In a landscape where German language models are scarce, we are proud to offer a solution that fills this void.
What sets SauerkrautLM-v1 apart is its versatility. Whether you are an individual looking to harness its capabilities for personal use or a business seeking to integrate it into your projects, our model is designed to accommodate all. It operates under the LLAMA 2 License, providing you with the freedom to explore its potential in both private and commercial applications.
Performance is at the heart of SauerkrautLM-v1. We put it to the **test using a customized version of MT-Bench for the German language**, and the results speak volumes. It currently stands as the most robust German Language Model on Hugging Face (based on german mt-bench results), showcasing its exceptional capabilities. Rest assured, this model is here to shine and set new standards. And the best thing is it comes in three different sizes (3B, 7B, 13B) to address your individual needs.
Our model's journey began with meticulous training using an **augmented dataset within the QLoRA approach**. This is just the beginning of our model series, promising even more innovative and powerful solutions in the future.
Join us on this exciting adventure as we redefine the possibilities of language modeling for the German-speaking world.
SauerkrautLM-v1 is here to empower your language-related endeavors like never before.
## All Models
| Model | HF | GPTQ | GGUF |
|-------|-------|-------|-------|
| SauerkrautLM-3b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-3b-v1) | soon | soon |
| SauerkrautLM-7b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1) | soon | soon |
| SauerkrautLM-7b-v1-mistral | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral) | soon | soon |
| SauerkrautLM-13b-v1 | [Link](https://huggingface.co/VAGOsolutions/SauerkrautLM-13b-v1) | soon | soon |
## Model Details
**SauerkrautLM-13b-v1**
**Training Dataset:**
SauerkrautLM was trained with mix of German data augmentation and translated data.
We found, that only a simple translation of training data can lead to unnatural German phrasings.
Data augmentation techniques were used to grant grammatical, syntactical correctness and a more natural German wording in our training data.
**Training Procedure:**
SauerkrautLM-13b-v1 was fine-tuned using QLoRA on 1 A100 80GB with Axolotl.
- **Trained by:** SauerkrautLM-v1 trained by VAGO solutions
- **Model Type:** SauerkrautLM-v1 is an auto-regressive language model based on the transformer architecture
- **Language(s):** German, English
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Website](https://vago-solutions.de/#Kontakt) [David Golchinfar](mailto:golchinfar@vago-solutions.de)
**Prompt Template:**
```
Ein Chat zwischen einem Benutzer und einem KI-Assistenten. Der KI-Assistent gibt hilfreiche, detaillierte und höfliche Antworten.
User: {prompt}
Assistant:
```
## Evaluation
**[MT-Bench-TrueGerman](https://huggingface.co/datasets/VAGOsolutions/MT-Bench-TrueGerman)**
## Disclaimer
Our models have been meticulously trained on extensive datasets. While we have made diligent efforts to thoroughly screen and eliminate any instances of coarse or inappropriate language from our data, we must inform users that despite our best efforts in data cleansing, the possibility of some such content slipping through cannot be entirely ruled out.
Furthermore, it is important to note that we have implemented filters within our models; however, we cannot always guarantee consistently appropriate behavior. Therefore, if you encounter any issues or come across inappropriate content, we kindly request that you inform us through the contact information provided.
Additionally, it is essential to understand that the licensing of these models does not constitute legal advice. We are not held responsible for the actions of third parties who utilize our models. These models may be employed for commercial purposes, and the original Llama2 license remains applicable and is included with the model files.
## Contact
If you are interested in customized LLMs for business applications, please get in contact with us via our website or contact us at [Dr. Daryoush Vaziri](mailto:vaziri@vago-solutions.de). We are also grateful for your feedback and suggestions.
## Collaborations
We are also keenly seeking support and investment for our startup, VAGO solutions, where we continuously advance the development of robust language models designed to address a diverse range of purposes and requirements. If the prospect of collaboratively navigating future challenges excites you, we warmly invite you to reach out to us.
<!-- original-model-card end -->
|
lauraparra28/albert-base-v2-finetuned-squad
|
lauraparra28
| 2023-10-14T16:47:17Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"albert",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"base_model:albert/albert-base-v2",
"base_model:finetune:albert/albert-base-v2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-14T13:07:53Z |
---
license: apache-2.0
base_model: albert-base-v2
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: albert-base-v2-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. -->
# albert-base-v2-finetuned-squad
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4774
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.8783 | 1.0 | 8248 | 0.8800 |
| 0.691 | 2.0 | 16496 | 0.8360 |
| 0.5057 | 3.0 | 24744 | 0.9619 |
| 0.348 | 4.0 | 32992 | 1.1724 |
| 0.2192 | 5.0 | 41240 | 1.4774 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
RedBaron5/content
|
RedBaron5
| 2023-10-14T16:43:46Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"led",
"text2text-generation",
"generated_from_trainer",
"dataset:xlsum-fi",
"base_model:allenai/led-base-16384",
"base_model:finetune:allenai/led-base-16384",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-14T16:41:02Z |
---
license: apache-2.0
base_model: allenai/led-base-16384
tags:
- generated_from_trainer
datasets:
- xlsum-fi
model-index:
- name: allenai/led-base-16384
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. -->
# allenai/led-base-16384
This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the xlsum-fi dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3962
- Rouge2 Precision: 0.0109
- Rouge2 Recall: 0.0248
- Rouge2 Fmeasure: 0.0152
## 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
| 3.8391 | 0.32 | 10 | 3.5714 | 0.0062 | 0.016 | 0.0089 |
| 3.8 | 0.64 | 20 | 3.4777 | 0.0083 | 0.0202 | 0.0115 |
| 3.6502 | 0.96 | 30 | 3.3962 | 0.0109 | 0.0248 | 0.0152 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ
|
TheBloke
| 2023-10-14T16:28:07Z | 34 | 1 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"base_model:abdgrt/Tinyllama-2-1b-miniguanaco",
"base_model:quantized:abdgrt/Tinyllama-2-1b-miniguanaco",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-11T03:20:35Z |
---
base_model: abdgrt/Tinyllama-2-1b-miniguanaco
inference: false
license: other
model_creator: Odunusi Abraham Ayoola
model_name: Tinyllama 2 1B MiniGuanaco
model_type: llama
prompt_template: '### Human: {prompt}
### 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 -->
# Tinyllama 2 1B MiniGuanaco - GPTQ
- Model creator: [Odunusi Abraham Ayoola](https://huggingface.co/abdgrt)
- Original model: [Tinyllama 2 1B MiniGuanaco](https://huggingface.co/abdgrt/Tinyllama-2-1b-miniguanaco)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Odunusi Abraham Ayoola's Tinyllama 2 1B MiniGuanaco](https://huggingface.co/abdgrt/Tinyllama-2-1b-miniguanaco).
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/Tinyllama-2-1b-miniguanaco-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Tinyllama-2-1b-miniguanaco-GGUF)
* [Odunusi Abraham Ayoola's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/abdgrt/Tinyllama-2-1b-miniguanaco)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Guanaco
```
### Human: {prompt}
### 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.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<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/Tinyllama-2-1b-miniguanaco-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.77 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/Tinyllama-2-1b-miniguanaco-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.82 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/Tinyllama-2-1b-miniguanaco-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.23 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.26 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/Tinyllama-2-1b-miniguanaco-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.32 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.79 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/Tinyllama-2-1b-miniguanaco-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Tinyllama-2-1b-miniguanaco-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 `Tinyllama-2-1b-miniguanaco-GPTQ`:
```shell
mkdir Tinyllama-2-1b-miniguanaco-GPTQ
huggingface-cli download TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ --local-dir Tinyllama-2-1b-miniguanaco-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir Tinyllama-2-1b-miniguanaco-GPTQ
huggingface-cli download TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Tinyllama-2-1b-miniguanaco-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 Tinyllama-2-1b-miniguanaco-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ --local-dir Tinyllama-2-1b-miniguanaco-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/Tinyllama-2-1b-miniguanaco-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/Tinyllama-2-1b-miniguanaco-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Tinyllama-2-1b-miniguanaco-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: `Tinyllama-2-1b-miniguanaco-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-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/Tinyllama-2-1b-miniguanaco-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''### Human: {prompt}
### Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi 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/Tinyllama-2-1b-miniguanaco-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'''### Human: {prompt}
### 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 and Mistral 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: Odunusi Abraham Ayoola's Tinyllama 2 1B MiniGuanaco
No original model card was available.
|
mauricioplopes/facemask-model
|
mauricioplopes
| 2023-10-14T16:16:40Z | 0 | 0 |
fastai
|
[
"fastai",
"am",
"license:apache-2.0",
"region:us"
] | null | 2023-10-14T07:07:16Z |
---
license: apache-2.0
language:
- am
library_name: fastai
---
|
MohaK/ppo-SnowballTarget
|
MohaK
| 2023-10-14T16:07:29Z | 11 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-10-14T16:07:26Z |
---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
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: MohaK/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
jncraton/gte-tiny-ct2-int8
|
jncraton
| 2023-10-14T15:44:06Z | 7 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"feature-extraction",
"sentence-similarity",
"transformers",
"mteb",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-10-14T15:32:30Z |
---
model-index:
- name: gte_tiny
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 71.76119402985076
- type: ap
value: 34.63659287952359
- type: f1
value: 65.88939512571113
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 86.61324999999998
- type: ap
value: 81.7476302802319
- type: f1
value: 86.5863470912001
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 42.61000000000001
- type: f1
value: 42.2217180000715
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 28.377999999999997
- type: map_at_10
value: 44.565
- type: map_at_100
value: 45.48
- type: map_at_1000
value: 45.487
- type: map_at_3
value: 39.841
- type: map_at_5
value: 42.284
- type: mrr_at_1
value: 29.445
- type: mrr_at_10
value: 44.956
- type: mrr_at_100
value: 45.877
- type: mrr_at_1000
value: 45.884
- type: mrr_at_3
value: 40.209
- type: mrr_at_5
value: 42.719
- type: ndcg_at_1
value: 28.377999999999997
- type: ndcg_at_10
value: 53.638
- type: ndcg_at_100
value: 57.354000000000006
- type: ndcg_at_1000
value: 57.513000000000005
- type: ndcg_at_3
value: 43.701
- type: ndcg_at_5
value: 48.114000000000004
- type: precision_at_1
value: 28.377999999999997
- type: precision_at_10
value: 8.272
- type: precision_at_100
value: 0.984
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 18.303
- type: precision_at_5
value: 13.129
- type: recall_at_1
value: 28.377999999999997
- type: recall_at_10
value: 82.717
- type: recall_at_100
value: 98.43499999999999
- type: recall_at_1000
value: 99.644
- type: recall_at_3
value: 54.908
- type: recall_at_5
value: 65.647
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 46.637318326729876
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 36.01134479855804
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 59.82917555338909
- type: mrr
value: 74.7888361254012
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 87.1657730995964
- type: cos_sim_spearman
value: 86.62787748941281
- type: euclidean_pearson
value: 85.48127914481798
- type: euclidean_spearman
value: 86.48148861167424
- type: manhattan_pearson
value: 85.07496934780823
- type: manhattan_spearman
value: 86.39473964708843
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 81.73051948051948
- type: f1
value: 81.66368364988331
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 39.18623707448217
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 32.12697757150375
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 29.160000000000004
- type: map_at_10
value: 40.474
- type: map_at_100
value: 41.905
- type: map_at_1000
value: 42.041000000000004
- type: map_at_3
value: 37.147000000000006
- type: map_at_5
value: 38.873999999999995
- type: mrr_at_1
value: 36.91
- type: mrr_at_10
value: 46.495999999999995
- type: mrr_at_100
value: 47.288000000000004
- type: mrr_at_1000
value: 47.339999999999996
- type: mrr_at_3
value: 43.777
- type: mrr_at_5
value: 45.257999999999996
- type: ndcg_at_1
value: 36.91
- type: ndcg_at_10
value: 46.722
- type: ndcg_at_100
value: 51.969
- type: ndcg_at_1000
value: 54.232
- type: ndcg_at_3
value: 41.783
- type: ndcg_at_5
value: 43.797000000000004
- type: precision_at_1
value: 36.91
- type: precision_at_10
value: 9.013
- type: precision_at_100
value: 1.455
- type: precision_at_1000
value: 0.193
- type: precision_at_3
value: 20.124
- type: precision_at_5
value: 14.363000000000001
- type: recall_at_1
value: 29.160000000000004
- type: recall_at_10
value: 58.521
- type: recall_at_100
value: 80.323
- type: recall_at_1000
value: 95.13000000000001
- type: recall_at_3
value: 44.205
- type: recall_at_5
value: 49.97
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.750000000000004
- type: map_at_10
value: 36.39
- type: map_at_100
value: 37.5
- type: map_at_1000
value: 37.625
- type: map_at_3
value: 33.853
- type: map_at_5
value: 35.397
- type: mrr_at_1
value: 34.14
- type: mrr_at_10
value: 41.841
- type: mrr_at_100
value: 42.469
- type: mrr_at_1000
value: 42.521
- type: mrr_at_3
value: 39.724
- type: mrr_at_5
value: 40.955999999999996
- type: ndcg_at_1
value: 34.14
- type: ndcg_at_10
value: 41.409
- type: ndcg_at_100
value: 45.668
- type: ndcg_at_1000
value: 47.916
- type: ndcg_at_3
value: 37.836
- type: ndcg_at_5
value: 39.650999999999996
- type: precision_at_1
value: 34.14
- type: precision_at_10
value: 7.739
- type: precision_at_100
value: 1.2630000000000001
- type: precision_at_1000
value: 0.173
- type: precision_at_3
value: 18.217
- type: precision_at_5
value: 12.854
- type: recall_at_1
value: 27.750000000000004
- type: recall_at_10
value: 49.882
- type: recall_at_100
value: 68.556
- type: recall_at_1000
value: 83.186
- type: recall_at_3
value: 39.047
- type: recall_at_5
value: 44.458
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 36.879
- type: map_at_10
value: 48.878
- type: map_at_100
value: 49.918
- type: map_at_1000
value: 49.978
- type: map_at_3
value: 45.867999999999995
- type: map_at_5
value: 47.637
- type: mrr_at_1
value: 42.696
- type: mrr_at_10
value: 52.342
- type: mrr_at_100
value: 53.044000000000004
- type: mrr_at_1000
value: 53.077
- type: mrr_at_3
value: 50.01
- type: mrr_at_5
value: 51.437
- type: ndcg_at_1
value: 42.696
- type: ndcg_at_10
value: 54.469
- type: ndcg_at_100
value: 58.664
- type: ndcg_at_1000
value: 59.951
- type: ndcg_at_3
value: 49.419999999999995
- type: ndcg_at_5
value: 52.007000000000005
- type: precision_at_1
value: 42.696
- type: precision_at_10
value: 8.734
- type: precision_at_100
value: 1.1769999999999998
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 22.027
- type: precision_at_5
value: 15.135000000000002
- type: recall_at_1
value: 36.879
- type: recall_at_10
value: 67.669
- type: recall_at_100
value: 85.822
- type: recall_at_1000
value: 95.092
- type: recall_at_3
value: 54.157999999999994
- type: recall_at_5
value: 60.436
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.942
- type: map_at_10
value: 31.741999999999997
- type: map_at_100
value: 32.721000000000004
- type: map_at_1000
value: 32.809
- type: map_at_3
value: 29.17
- type: map_at_5
value: 30.714000000000002
- type: mrr_at_1
value: 24.746000000000002
- type: mrr_at_10
value: 33.517
- type: mrr_at_100
value: 34.451
- type: mrr_at_1000
value: 34.522000000000006
- type: mrr_at_3
value: 31.148999999999997
- type: mrr_at_5
value: 32.606
- type: ndcg_at_1
value: 24.746000000000002
- type: ndcg_at_10
value: 36.553000000000004
- type: ndcg_at_100
value: 41.53
- type: ndcg_at_1000
value: 43.811
- type: ndcg_at_3
value: 31.674000000000003
- type: ndcg_at_5
value: 34.241
- type: precision_at_1
value: 24.746000000000002
- type: precision_at_10
value: 5.684
- type: precision_at_100
value: 0.859
- type: precision_at_1000
value: 0.109
- type: precision_at_3
value: 13.597000000000001
- type: precision_at_5
value: 9.672
- type: recall_at_1
value: 22.942
- type: recall_at_10
value: 49.58
- type: recall_at_100
value: 72.614
- type: recall_at_1000
value: 89.89200000000001
- type: recall_at_3
value: 36.552
- type: recall_at_5
value: 42.702
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.345
- type: map_at_10
value: 22.428
- type: map_at_100
value: 23.756
- type: map_at_1000
value: 23.872
- type: map_at_3
value: 20.212
- type: map_at_5
value: 21.291
- type: mrr_at_1
value: 19.279
- type: mrr_at_10
value: 27.1
- type: mrr_at_100
value: 28.211000000000002
- type: mrr_at_1000
value: 28.279
- type: mrr_at_3
value: 24.813
- type: mrr_at_5
value: 25.889
- type: ndcg_at_1
value: 19.279
- type: ndcg_at_10
value: 27.36
- type: ndcg_at_100
value: 33.499
- type: ndcg_at_1000
value: 36.452
- type: ndcg_at_3
value: 23.233999999999998
- type: ndcg_at_5
value: 24.806
- type: precision_at_1
value: 19.279
- type: precision_at_10
value: 5.149
- type: precision_at_100
value: 0.938
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 11.360000000000001
- type: precision_at_5
value: 8.035
- type: recall_at_1
value: 15.345
- type: recall_at_10
value: 37.974999999999994
- type: recall_at_100
value: 64.472
- type: recall_at_1000
value: 85.97200000000001
- type: recall_at_3
value: 26.203
- type: recall_at_5
value: 30.485
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 26.362000000000002
- type: map_at_10
value: 36.406
- type: map_at_100
value: 37.726
- type: map_at_1000
value: 37.84
- type: map_at_3
value: 33.425
- type: map_at_5
value: 35.043
- type: mrr_at_1
value: 32.146
- type: mrr_at_10
value: 41.674
- type: mrr_at_100
value: 42.478
- type: mrr_at_1000
value: 42.524
- type: mrr_at_3
value: 38.948
- type: mrr_at_5
value: 40.415
- type: ndcg_at_1
value: 32.146
- type: ndcg_at_10
value: 42.374
- type: ndcg_at_100
value: 47.919
- type: ndcg_at_1000
value: 50.013
- type: ndcg_at_3
value: 37.29
- type: ndcg_at_5
value: 39.531
- type: precision_at_1
value: 32.146
- type: precision_at_10
value: 7.767
- type: precision_at_100
value: 1.236
- type: precision_at_1000
value: 0.16
- type: precision_at_3
value: 17.965999999999998
- type: precision_at_5
value: 12.742999999999999
- type: recall_at_1
value: 26.362000000000002
- type: recall_at_10
value: 54.98800000000001
- type: recall_at_100
value: 78.50200000000001
- type: recall_at_1000
value: 92.146
- type: recall_at_3
value: 40.486
- type: recall_at_5
value: 46.236
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.417
- type: map_at_10
value: 33.161
- type: map_at_100
value: 34.357
- type: map_at_1000
value: 34.473
- type: map_at_3
value: 30.245
- type: map_at_5
value: 31.541999999999998
- type: mrr_at_1
value: 29.909000000000002
- type: mrr_at_10
value: 38.211
- type: mrr_at_100
value: 39.056999999999995
- type: mrr_at_1000
value: 39.114
- type: mrr_at_3
value: 35.769
- type: mrr_at_5
value: 36.922
- type: ndcg_at_1
value: 29.909000000000002
- type: ndcg_at_10
value: 38.694
- type: ndcg_at_100
value: 44.057
- type: ndcg_at_1000
value: 46.6
- type: ndcg_at_3
value: 33.822
- type: ndcg_at_5
value: 35.454
- type: precision_at_1
value: 29.909000000000002
- type: precision_at_10
value: 7.180000000000001
- type: precision_at_100
value: 1.153
- type: precision_at_1000
value: 0.155
- type: precision_at_3
value: 16.134
- type: precision_at_5
value: 11.256
- type: recall_at_1
value: 24.417
- type: recall_at_10
value: 50.260000000000005
- type: recall_at_100
value: 73.55699999999999
- type: recall_at_1000
value: 91.216
- type: recall_at_3
value: 35.971
- type: recall_at_5
value: 40.793
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.266916666666663
- type: map_at_10
value: 32.75025
- type: map_at_100
value: 33.91341666666667
- type: map_at_1000
value: 34.031749999999995
- type: map_at_3
value: 30.166416666666674
- type: map_at_5
value: 31.577000000000005
- type: mrr_at_1
value: 28.828166666666664
- type: mrr_at_10
value: 36.80991666666667
- type: mrr_at_100
value: 37.67075
- type: mrr_at_1000
value: 37.733
- type: mrr_at_3
value: 34.513416666666664
- type: mrr_at_5
value: 35.788
- type: ndcg_at_1
value: 28.828166666666664
- type: ndcg_at_10
value: 37.796
- type: ndcg_at_100
value: 42.94783333333333
- type: ndcg_at_1000
value: 45.38908333333333
- type: ndcg_at_3
value: 33.374750000000006
- type: ndcg_at_5
value: 35.379666666666665
- type: precision_at_1
value: 28.828166666666664
- type: precision_at_10
value: 6.615749999999999
- type: precision_at_100
value: 1.0848333333333333
- type: precision_at_1000
value: 0.1484166666666667
- type: precision_at_3
value: 15.347833333333332
- type: precision_at_5
value: 10.848916666666666
- type: recall_at_1
value: 24.266916666666663
- type: recall_at_10
value: 48.73458333333333
- type: recall_at_100
value: 71.56341666666667
- type: recall_at_1000
value: 88.63091666666668
- type: recall_at_3
value: 36.31208333333333
- type: recall_at_5
value: 41.55633333333333
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.497
- type: map_at_10
value: 30.249
- type: map_at_100
value: 30.947000000000003
- type: map_at_1000
value: 31.049
- type: map_at_3
value: 28.188000000000002
- type: map_at_5
value: 29.332
- type: mrr_at_1
value: 26.687
- type: mrr_at_10
value: 33.182
- type: mrr_at_100
value: 33.794999999999995
- type: mrr_at_1000
value: 33.873
- type: mrr_at_3
value: 31.263
- type: mrr_at_5
value: 32.428000000000004
- type: ndcg_at_1
value: 26.687
- type: ndcg_at_10
value: 34.252
- type: ndcg_at_100
value: 38.083
- type: ndcg_at_1000
value: 40.682
- type: ndcg_at_3
value: 30.464999999999996
- type: ndcg_at_5
value: 32.282
- type: precision_at_1
value: 26.687
- type: precision_at_10
value: 5.2909999999999995
- type: precision_at_100
value: 0.788
- type: precision_at_1000
value: 0.109
- type: precision_at_3
value: 13.037
- type: precision_at_5
value: 9.049
- type: recall_at_1
value: 23.497
- type: recall_at_10
value: 43.813
- type: recall_at_100
value: 61.88399999999999
- type: recall_at_1000
value: 80.926
- type: recall_at_3
value: 33.332
- type: recall_at_5
value: 37.862
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.073
- type: map_at_10
value: 22.705000000000002
- type: map_at_100
value: 23.703
- type: map_at_1000
value: 23.833
- type: map_at_3
value: 20.593
- type: map_at_5
value: 21.7
- type: mrr_at_1
value: 19.683
- type: mrr_at_10
value: 26.39
- type: mrr_at_100
value: 27.264
- type: mrr_at_1000
value: 27.349
- type: mrr_at_3
value: 24.409
- type: mrr_at_5
value: 25.474000000000004
- type: ndcg_at_1
value: 19.683
- type: ndcg_at_10
value: 27.014
- type: ndcg_at_100
value: 31.948
- type: ndcg_at_1000
value: 35.125
- type: ndcg_at_3
value: 23.225
- type: ndcg_at_5
value: 24.866
- type: precision_at_1
value: 19.683
- type: precision_at_10
value: 4.948
- type: precision_at_100
value: 0.876
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 10.943
- type: precision_at_5
value: 7.86
- type: recall_at_1
value: 16.073
- type: recall_at_10
value: 36.283
- type: recall_at_100
value: 58.745999999999995
- type: recall_at_1000
value: 81.711
- type: recall_at_3
value: 25.637
- type: recall_at_5
value: 29.919
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.776
- type: map_at_10
value: 33.317
- type: map_at_100
value: 34.437
- type: map_at_1000
value: 34.54
- type: map_at_3
value: 30.706
- type: map_at_5
value: 32.202999999999996
- type: mrr_at_1
value: 30.224
- type: mrr_at_10
value: 37.34
- type: mrr_at_100
value: 38.268
- type: mrr_at_1000
value: 38.335
- type: mrr_at_3
value: 35.075
- type: mrr_at_5
value: 36.348
- type: ndcg_at_1
value: 30.224
- type: ndcg_at_10
value: 38.083
- type: ndcg_at_100
value: 43.413000000000004
- type: ndcg_at_1000
value: 45.856
- type: ndcg_at_3
value: 33.437
- type: ndcg_at_5
value: 35.661
- type: precision_at_1
value: 30.224
- type: precision_at_10
value: 6.1850000000000005
- type: precision_at_100
value: 1.0030000000000001
- type: precision_at_1000
value: 0.132
- type: precision_at_3
value: 14.646
- type: precision_at_5
value: 10.428999999999998
- type: recall_at_1
value: 25.776
- type: recall_at_10
value: 48.787000000000006
- type: recall_at_100
value: 72.04899999999999
- type: recall_at_1000
value: 89.339
- type: recall_at_3
value: 36.192
- type: recall_at_5
value: 41.665
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.156
- type: map_at_10
value: 30.886000000000003
- type: map_at_100
value: 32.551
- type: map_at_1000
value: 32.769
- type: map_at_3
value: 28.584
- type: map_at_5
value: 29.959999999999997
- type: mrr_at_1
value: 28.260999999999996
- type: mrr_at_10
value: 35.555
- type: mrr_at_100
value: 36.687
- type: mrr_at_1000
value: 36.742999999999995
- type: mrr_at_3
value: 33.531
- type: mrr_at_5
value: 34.717
- type: ndcg_at_1
value: 28.260999999999996
- type: ndcg_at_10
value: 36.036
- type: ndcg_at_100
value: 42.675000000000004
- type: ndcg_at_1000
value: 45.303
- type: ndcg_at_3
value: 32.449
- type: ndcg_at_5
value: 34.293
- type: precision_at_1
value: 28.260999999999996
- type: precision_at_10
value: 6.837999999999999
- type: precision_at_100
value: 1.4569999999999999
- type: precision_at_1000
value: 0.23500000000000001
- type: precision_at_3
value: 15.217
- type: precision_at_5
value: 11.028
- type: recall_at_1
value: 23.156
- type: recall_at_10
value: 45.251999999999995
- type: recall_at_100
value: 75.339
- type: recall_at_1000
value: 91.56
- type: recall_at_3
value: 34.701
- type: recall_at_5
value: 39.922999999999995
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 19.846
- type: map_at_10
value: 26.367
- type: map_at_100
value: 27.439999999999998
- type: map_at_1000
value: 27.552
- type: map_at_3
value: 24.006
- type: map_at_5
value: 25.230999999999998
- type: mrr_at_1
value: 21.257
- type: mrr_at_10
value: 28.071
- type: mrr_at_100
value: 29.037000000000003
- type: mrr_at_1000
value: 29.119
- type: mrr_at_3
value: 25.692999999999998
- type: mrr_at_5
value: 27.006000000000004
- type: ndcg_at_1
value: 21.257
- type: ndcg_at_10
value: 30.586000000000002
- type: ndcg_at_100
value: 35.949
- type: ndcg_at_1000
value: 38.728
- type: ndcg_at_3
value: 25.862000000000002
- type: ndcg_at_5
value: 27.967
- type: precision_at_1
value: 21.257
- type: precision_at_10
value: 4.861
- type: precision_at_100
value: 0.8130000000000001
- type: precision_at_1000
value: 0.116
- type: precision_at_3
value: 10.906
- type: precision_at_5
value: 7.763000000000001
- type: recall_at_1
value: 19.846
- type: recall_at_10
value: 41.805
- type: recall_at_100
value: 66.89699999999999
- type: recall_at_1000
value: 87.401
- type: recall_at_3
value: 29.261
- type: recall_at_5
value: 34.227000000000004
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.333
- type: map_at_10
value: 17.14
- type: map_at_100
value: 18.878
- type: map_at_1000
value: 19.067
- type: map_at_3
value: 14.123
- type: map_at_5
value: 15.699
- type: mrr_at_1
value: 23.192
- type: mrr_at_10
value: 33.553
- type: mrr_at_100
value: 34.553
- type: mrr_at_1000
value: 34.603
- type: mrr_at_3
value: 29.848000000000003
- type: mrr_at_5
value: 32.18
- type: ndcg_at_1
value: 23.192
- type: ndcg_at_10
value: 24.707
- type: ndcg_at_100
value: 31.701
- type: ndcg_at_1000
value: 35.260999999999996
- type: ndcg_at_3
value: 19.492
- type: ndcg_at_5
value: 21.543
- type: precision_at_1
value: 23.192
- type: precision_at_10
value: 7.824000000000001
- type: precision_at_100
value: 1.52
- type: precision_at_1000
value: 0.218
- type: precision_at_3
value: 14.180000000000001
- type: precision_at_5
value: 11.530999999999999
- type: recall_at_1
value: 10.333
- type: recall_at_10
value: 30.142999999999997
- type: recall_at_100
value: 54.298
- type: recall_at_1000
value: 74.337
- type: recall_at_3
value: 17.602999999999998
- type: recall_at_5
value: 22.938
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.03
- type: map_at_10
value: 17.345
- type: map_at_100
value: 23.462
- type: map_at_1000
value: 24.77
- type: map_at_3
value: 12.714
- type: map_at_5
value: 14.722
- type: mrr_at_1
value: 61.0
- type: mrr_at_10
value: 69.245
- type: mrr_at_100
value: 69.715
- type: mrr_at_1000
value: 69.719
- type: mrr_at_3
value: 67.583
- type: mrr_at_5
value: 68.521
- type: ndcg_at_1
value: 47.625
- type: ndcg_at_10
value: 35.973
- type: ndcg_at_100
value: 39.875
- type: ndcg_at_1000
value: 46.922000000000004
- type: ndcg_at_3
value: 40.574
- type: ndcg_at_5
value: 38.18
- type: precision_at_1
value: 61.0
- type: precision_at_10
value: 29.049999999999997
- type: precision_at_100
value: 8.828
- type: precision_at_1000
value: 1.8290000000000002
- type: precision_at_3
value: 45.333
- type: precision_at_5
value: 37.9
- type: recall_at_1
value: 8.03
- type: recall_at_10
value: 22.334
- type: recall_at_100
value: 45.919
- type: recall_at_1000
value: 68.822
- type: recall_at_3
value: 14.038999999999998
- type: recall_at_5
value: 17.118
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 44.714999999999996
- type: f1
value: 39.83929362259356
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 52.242999999999995
- type: map_at_10
value: 64.087
- type: map_at_100
value: 64.549
- type: map_at_1000
value: 64.567
- type: map_at_3
value: 61.667
- type: map_at_5
value: 63.266
- type: mrr_at_1
value: 56.271
- type: mrr_at_10
value: 68.146
- type: mrr_at_100
value: 68.524
- type: mrr_at_1000
value: 68.53200000000001
- type: mrr_at_3
value: 65.869
- type: mrr_at_5
value: 67.37100000000001
- type: ndcg_at_1
value: 56.271
- type: ndcg_at_10
value: 70.109
- type: ndcg_at_100
value: 72.09
- type: ndcg_at_1000
value: 72.479
- type: ndcg_at_3
value: 65.559
- type: ndcg_at_5
value: 68.242
- type: precision_at_1
value: 56.271
- type: precision_at_10
value: 9.286999999999999
- type: precision_at_100
value: 1.039
- type: precision_at_1000
value: 0.109
- type: precision_at_3
value: 26.308
- type: precision_at_5
value: 17.291
- type: recall_at_1
value: 52.242999999999995
- type: recall_at_10
value: 84.71
- type: recall_at_100
value: 93.309
- type: recall_at_1000
value: 96.013
- type: recall_at_3
value: 72.554
- type: recall_at_5
value: 79.069
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 14.346
- type: map_at_10
value: 24.552
- type: map_at_100
value: 26.161
- type: map_at_1000
value: 26.345000000000002
- type: map_at_3
value: 21.208
- type: map_at_5
value: 22.959
- type: mrr_at_1
value: 29.166999999999998
- type: mrr_at_10
value: 38.182
- type: mrr_at_100
value: 39.22
- type: mrr_at_1000
value: 39.263
- type: mrr_at_3
value: 35.983
- type: mrr_at_5
value: 37.14
- type: ndcg_at_1
value: 29.166999999999998
- type: ndcg_at_10
value: 31.421
- type: ndcg_at_100
value: 38.129999999999995
- type: ndcg_at_1000
value: 41.569
- type: ndcg_at_3
value: 28.172000000000004
- type: ndcg_at_5
value: 29.029
- type: precision_at_1
value: 29.166999999999998
- type: precision_at_10
value: 8.997
- type: precision_at_100
value: 1.5709999999999997
- type: precision_at_1000
value: 0.22
- type: precision_at_3
value: 19.187
- type: precision_at_5
value: 13.980999999999998
- type: recall_at_1
value: 14.346
- type: recall_at_10
value: 37.963
- type: recall_at_100
value: 63.43299999999999
- type: recall_at_1000
value: 84.057
- type: recall_at_3
value: 26.119999999999997
- type: recall_at_5
value: 30.988
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 33.059
- type: map_at_10
value: 46.421
- type: map_at_100
value: 47.323
- type: map_at_1000
value: 47.403
- type: map_at_3
value: 43.553999999999995
- type: map_at_5
value: 45.283
- type: mrr_at_1
value: 66.117
- type: mrr_at_10
value: 73.10900000000001
- type: mrr_at_100
value: 73.444
- type: mrr_at_1000
value: 73.46000000000001
- type: mrr_at_3
value: 71.70400000000001
- type: mrr_at_5
value: 72.58099999999999
- type: ndcg_at_1
value: 66.117
- type: ndcg_at_10
value: 55.696999999999996
- type: ndcg_at_100
value: 59.167
- type: ndcg_at_1000
value: 60.809000000000005
- type: ndcg_at_3
value: 51.243
- type: ndcg_at_5
value: 53.627
- type: precision_at_1
value: 66.117
- type: precision_at_10
value: 11.538
- type: precision_at_100
value: 1.429
- type: precision_at_1000
value: 0.165
- type: precision_at_3
value: 31.861
- type: precision_at_5
value: 20.997
- type: recall_at_1
value: 33.059
- type: recall_at_10
value: 57.691
- type: recall_at_100
value: 71.458
- type: recall_at_1000
value: 82.35
- type: recall_at_3
value: 47.792
- type: recall_at_5
value: 52.492000000000004
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 80.544
- type: ap
value: 74.69592367984956
- type: f1
value: 80.51138138449883
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 17.095
- type: map_at_10
value: 28.038999999999998
- type: map_at_100
value: 29.246
- type: map_at_1000
value: 29.311
- type: map_at_3
value: 24.253
- type: map_at_5
value: 26.442
- type: mrr_at_1
value: 17.535999999999998
- type: mrr_at_10
value: 28.53
- type: mrr_at_100
value: 29.697000000000003
- type: mrr_at_1000
value: 29.755
- type: mrr_at_3
value: 24.779999999999998
- type: mrr_at_5
value: 26.942
- type: ndcg_at_1
value: 17.549999999999997
- type: ndcg_at_10
value: 34.514
- type: ndcg_at_100
value: 40.497
- type: ndcg_at_1000
value: 42.17
- type: ndcg_at_3
value: 26.764
- type: ndcg_at_5
value: 30.678
- type: precision_at_1
value: 17.549999999999997
- type: precision_at_10
value: 5.692
- type: precision_at_100
value: 0.8699999999999999
- type: precision_at_1000
value: 0.101
- type: precision_at_3
value: 11.562
- type: precision_at_5
value: 8.917
- type: recall_at_1
value: 17.095
- type: recall_at_10
value: 54.642
- type: recall_at_100
value: 82.652
- type: recall_at_1000
value: 95.555
- type: recall_at_3
value: 33.504
- type: recall_at_5
value: 42.925000000000004
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 91.75558595531236
- type: f1
value: 91.25979279648296
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 69.90424076607387
- type: f1
value: 52.067408707562244
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 70.13449899125757
- type: f1
value: 67.62456762910598
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.862138533961
- type: f1
value: 74.66457222091381
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 34.10761942610792
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 31.673172170578408
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 32.058704977250315
- type: mrr
value: 33.24327760839221
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.163
- type: map_at_10
value: 11.652999999999999
- type: map_at_100
value: 14.849
- type: map_at_1000
value: 16.253999999999998
- type: map_at_3
value: 8.616999999999999
- type: map_at_5
value: 10.100000000000001
- type: mrr_at_1
value: 44.272
- type: mrr_at_10
value: 52.25
- type: mrr_at_100
value: 52.761
- type: mrr_at_1000
value: 52.811
- type: mrr_at_3
value: 50.31
- type: mrr_at_5
value: 51.347
- type: ndcg_at_1
value: 42.105
- type: ndcg_at_10
value: 32.044
- type: ndcg_at_100
value: 29.763
- type: ndcg_at_1000
value: 38.585
- type: ndcg_at_3
value: 36.868
- type: ndcg_at_5
value: 35.154999999999994
- type: precision_at_1
value: 43.653
- type: precision_at_10
value: 23.622
- type: precision_at_100
value: 7.7490000000000006
- type: precision_at_1000
value: 2.054
- type: precision_at_3
value: 34.262
- type: precision_at_5
value: 30.154999999999998
- type: recall_at_1
value: 5.163
- type: recall_at_10
value: 15.478
- type: recall_at_100
value: 30.424
- type: recall_at_1000
value: 62.67
- type: recall_at_3
value: 9.615
- type: recall_at_5
value: 12.369
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.618000000000002
- type: map_at_10
value: 35.465
- type: map_at_100
value: 36.712
- type: map_at_1000
value: 36.757
- type: map_at_3
value: 31.189
- type: map_at_5
value: 33.537
- type: mrr_at_1
value: 24.305
- type: mrr_at_10
value: 37.653
- type: mrr_at_100
value: 38.662
- type: mrr_at_1000
value: 38.694
- type: mrr_at_3
value: 33.889
- type: mrr_at_5
value: 35.979
- type: ndcg_at_1
value: 24.305
- type: ndcg_at_10
value: 43.028
- type: ndcg_at_100
value: 48.653999999999996
- type: ndcg_at_1000
value: 49.733
- type: ndcg_at_3
value: 34.768
- type: ndcg_at_5
value: 38.753
- type: precision_at_1
value: 24.305
- type: precision_at_10
value: 7.59
- type: precision_at_100
value: 1.076
- type: precision_at_1000
value: 0.11800000000000001
- type: precision_at_3
value: 16.271
- type: precision_at_5
value: 12.068
- type: recall_at_1
value: 21.618000000000002
- type: recall_at_10
value: 63.977
- type: recall_at_100
value: 89.03999999999999
- type: recall_at_1000
value: 97.10600000000001
- type: recall_at_3
value: 42.422
- type: recall_at_5
value: 51.629000000000005
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 69.405
- type: map_at_10
value: 83.05
- type: map_at_100
value: 83.684
- type: map_at_1000
value: 83.70400000000001
- type: map_at_3
value: 80.08800000000001
- type: map_at_5
value: 81.937
- type: mrr_at_1
value: 79.85
- type: mrr_at_10
value: 86.369
- type: mrr_at_100
value: 86.48599999999999
- type: mrr_at_1000
value: 86.48700000000001
- type: mrr_at_3
value: 85.315
- type: mrr_at_5
value: 86.044
- type: ndcg_at_1
value: 79.86999999999999
- type: ndcg_at_10
value: 87.04499999999999
- type: ndcg_at_100
value: 88.373
- type: ndcg_at_1000
value: 88.531
- type: ndcg_at_3
value: 84.04
- type: ndcg_at_5
value: 85.684
- type: precision_at_1
value: 79.86999999999999
- type: precision_at_10
value: 13.183
- type: precision_at_100
value: 1.51
- type: precision_at_1000
value: 0.156
- type: precision_at_3
value: 36.67
- type: precision_at_5
value: 24.12
- type: recall_at_1
value: 69.405
- type: recall_at_10
value: 94.634
- type: recall_at_100
value: 99.214
- type: recall_at_1000
value: 99.958
- type: recall_at_3
value: 85.992
- type: recall_at_5
value: 90.656
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 50.191676323145465
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 56.4874020363744
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.228
- type: map_at_10
value: 11.245
- type: map_at_100
value: 13.353000000000002
- type: map_at_1000
value: 13.665
- type: map_at_3
value: 7.779999999999999
- type: map_at_5
value: 9.405
- type: mrr_at_1
value: 20.9
- type: mrr_at_10
value: 31.657999999999998
- type: mrr_at_100
value: 32.769999999999996
- type: mrr_at_1000
value: 32.833
- type: mrr_at_3
value: 28.333000000000002
- type: mrr_at_5
value: 30.043
- type: ndcg_at_1
value: 20.9
- type: ndcg_at_10
value: 19.073
- type: ndcg_at_100
value: 27.055
- type: ndcg_at_1000
value: 32.641
- type: ndcg_at_3
value: 17.483999999999998
- type: ndcg_at_5
value: 15.42
- type: precision_at_1
value: 20.9
- type: precision_at_10
value: 10.17
- type: precision_at_100
value: 2.162
- type: precision_at_1000
value: 0.35100000000000003
- type: precision_at_3
value: 16.467000000000002
- type: precision_at_5
value: 13.68
- type: recall_at_1
value: 4.228
- type: recall_at_10
value: 20.573
- type: recall_at_100
value: 43.887
- type: recall_at_1000
value: 71.22
- type: recall_at_3
value: 10.023
- type: recall_at_5
value: 13.873
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 82.77965135067481
- type: cos_sim_spearman
value: 75.85121335808076
- type: euclidean_pearson
value: 80.09115175262697
- type: euclidean_spearman
value: 75.72249155647123
- type: manhattan_pearson
value: 79.89723577351782
- type: manhattan_spearman
value: 75.49855259442387
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 80.46084116030949
- type: cos_sim_spearman
value: 72.57579204392951
- type: euclidean_pearson
value: 76.39020830763684
- type: euclidean_spearman
value: 72.3718627025895
- type: manhattan_pearson
value: 76.6148833027359
- type: manhattan_spearman
value: 72.57570008442319
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 80.43678068337017
- type: cos_sim_spearman
value: 82.38941154076062
- type: euclidean_pearson
value: 81.59260573633661
- type: euclidean_spearman
value: 82.31144262574114
- type: manhattan_pearson
value: 81.43266909137056
- type: manhattan_spearman
value: 82.14704293004861
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 80.73713431763163
- type: cos_sim_spearman
value: 77.97860512809388
- type: euclidean_pearson
value: 80.35755041527027
- type: euclidean_spearman
value: 78.021703511412
- type: manhattan_pearson
value: 80.24440317109162
- type: manhattan_spearman
value: 77.93165415697575
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 85.15111852351204
- type: cos_sim_spearman
value: 86.54032447238258
- type: euclidean_pearson
value: 86.14157021537433
- type: euclidean_spearman
value: 86.67537291929713
- type: manhattan_pearson
value: 86.081041854808
- type: manhattan_spearman
value: 86.61561701560558
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 81.34532445104026
- type: cos_sim_spearman
value: 83.31325001474116
- type: euclidean_pearson
value: 82.81892375201032
- type: euclidean_spearman
value: 83.4521695148055
- type: manhattan_pearson
value: 82.72503790526163
- type: manhattan_spearman
value: 83.37833652941349
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.25463453839801
- type: cos_sim_spearman
value: 88.27655263515948
- type: euclidean_pearson
value: 88.0248334411439
- type: euclidean_spearman
value: 88.18141448876868
- type: manhattan_pearson
value: 87.8080451127279
- type: manhattan_spearman
value: 88.01028114423058
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 63.57551045355218
- type: cos_sim_spearman
value: 66.67614095126629
- type: euclidean_pearson
value: 66.0787243112528
- type: euclidean_spearman
value: 66.83660560636939
- type: manhattan_pearson
value: 66.74684019662031
- type: manhattan_spearman
value: 67.11761598074368
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 83.70881496766829
- type: cos_sim_spearman
value: 84.37803542941634
- type: euclidean_pearson
value: 84.84501245857096
- type: euclidean_spearman
value: 84.47088079741476
- type: manhattan_pearson
value: 84.77244090794765
- type: manhattan_spearman
value: 84.43307343706205
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 81.53946254759089
- type: mrr
value: 94.68259953554072
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 51.817
- type: map_at_10
value: 62.339999999999996
- type: map_at_100
value: 62.88
- type: map_at_1000
value: 62.909000000000006
- type: map_at_3
value: 59.004
- type: map_at_5
value: 60.906000000000006
- type: mrr_at_1
value: 54.333
- type: mrr_at_10
value: 63.649
- type: mrr_at_100
value: 64.01
- type: mrr_at_1000
value: 64.039
- type: mrr_at_3
value: 61.056
- type: mrr_at_5
value: 62.639
- type: ndcg_at_1
value: 54.333
- type: ndcg_at_10
value: 67.509
- type: ndcg_at_100
value: 69.69999999999999
- type: ndcg_at_1000
value: 70.613
- type: ndcg_at_3
value: 61.729
- type: ndcg_at_5
value: 64.696
- type: precision_at_1
value: 54.333
- type: precision_at_10
value: 9.2
- type: precision_at_100
value: 1.043
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 24.0
- type: precision_at_5
value: 16.2
- type: recall_at_1
value: 51.817
- type: recall_at_10
value: 82.056
- type: recall_at_100
value: 91.667
- type: recall_at_1000
value: 99.0
- type: recall_at_3
value: 66.717
- type: recall_at_5
value: 74.17200000000001
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.82475247524752
- type: cos_sim_ap
value: 95.4781199603258
- type: cos_sim_f1
value: 91.16186693147964
- type: cos_sim_precision
value: 90.53254437869822
- type: cos_sim_recall
value: 91.8
- type: dot_accuracy
value: 99.75049504950495
- type: dot_ap
value: 93.05183539809457
- type: dot_f1
value: 87.31117824773412
- type: dot_precision
value: 87.93103448275862
- type: dot_recall
value: 86.7
- type: euclidean_accuracy
value: 99.82475247524752
- type: euclidean_ap
value: 95.38547978154382
- type: euclidean_f1
value: 91.16325511732403
- type: euclidean_precision
value: 91.02691924227318
- type: euclidean_recall
value: 91.3
- type: manhattan_accuracy
value: 99.82574257425742
- type: manhattan_ap
value: 95.47237521890308
- type: manhattan_f1
value: 91.27849355797821
- type: manhattan_precision
value: 90.47151277013754
- type: manhattan_recall
value: 92.10000000000001
- type: max_accuracy
value: 99.82574257425742
- type: max_ap
value: 95.4781199603258
- type: max_f1
value: 91.27849355797821
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 57.542169376331245
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 35.74399302634387
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.65076347632749
- type: mrr
value: 50.418099057804945
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 29.73997756592847
- type: cos_sim_spearman
value: 29.465208011593308
- type: dot_pearson
value: 24.83735342474541
- type: dot_spearman
value: 26.005180528584855
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.208
- type: map_at_10
value: 1.434
- type: map_at_100
value: 7.829
- type: map_at_1000
value: 19.807
- type: map_at_3
value: 0.549
- type: map_at_5
value: 0.8330000000000001
- type: mrr_at_1
value: 78.0
- type: mrr_at_10
value: 85.35199999999999
- type: mrr_at_100
value: 85.673
- type: mrr_at_1000
value: 85.673
- type: mrr_at_3
value: 84.667
- type: mrr_at_5
value: 85.06700000000001
- type: ndcg_at_1
value: 72.0
- type: ndcg_at_10
value: 59.214999999999996
- type: ndcg_at_100
value: 44.681
- type: ndcg_at_1000
value: 43.035000000000004
- type: ndcg_at_3
value: 66.53099999999999
- type: ndcg_at_5
value: 63.23
- type: precision_at_1
value: 78.0
- type: precision_at_10
value: 62.4
- type: precision_at_100
value: 45.76
- type: precision_at_1000
value: 19.05
- type: precision_at_3
value: 71.333
- type: precision_at_5
value: 67.2
- type: recall_at_1
value: 0.208
- type: recall_at_10
value: 1.6580000000000001
- type: recall_at_100
value: 11.324
- type: recall_at_1000
value: 41.537
- type: recall_at_3
value: 0.579
- type: recall_at_5
value: 0.8959999999999999
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.442
- type: map_at_10
value: 8.863
- type: map_at_100
value: 14.606
- type: map_at_1000
value: 16.258
- type: map_at_3
value: 4.396
- type: map_at_5
value: 6.199000000000001
- type: mrr_at_1
value: 30.612000000000002
- type: mrr_at_10
value: 43.492
- type: mrr_at_100
value: 44.557
- type: mrr_at_1000
value: 44.557
- type: mrr_at_3
value: 40.816
- type: mrr_at_5
value: 42.143
- type: ndcg_at_1
value: 25.509999999999998
- type: ndcg_at_10
value: 22.076
- type: ndcg_at_100
value: 34.098
- type: ndcg_at_1000
value: 46.265
- type: ndcg_at_3
value: 24.19
- type: ndcg_at_5
value: 23.474
- type: precision_at_1
value: 30.612000000000002
- type: precision_at_10
value: 19.796
- type: precision_at_100
value: 7.286
- type: precision_at_1000
value: 1.5310000000000001
- type: precision_at_3
value: 25.85
- type: precision_at_5
value: 24.490000000000002
- type: recall_at_1
value: 2.442
- type: recall_at_10
value: 15.012
- type: recall_at_100
value: 45.865
- type: recall_at_1000
value: 82.958
- type: recall_at_3
value: 5.731
- type: recall_at_5
value: 9.301
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 70.974
- type: ap
value: 14.534996211286682
- type: f1
value: 54.785946183399005
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 58.56819468024901
- type: f1
value: 58.92391487111204
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 43.273202335218194
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 84.37742146986946
- type: cos_sim_ap
value: 68.1684129575579
- type: cos_sim_f1
value: 64.93475108748189
- type: cos_sim_precision
value: 59.89745876058849
- type: cos_sim_recall
value: 70.89709762532982
- type: dot_accuracy
value: 80.49710913750968
- type: dot_ap
value: 54.699790073944186
- type: dot_f1
value: 54.45130013221684
- type: dot_precision
value: 46.74612183125236
- type: dot_recall
value: 65.19788918205805
- type: euclidean_accuracy
value: 84.5085533766466
- type: euclidean_ap
value: 68.38835695236224
- type: euclidean_f1
value: 65.3391121002694
- type: euclidean_precision
value: 58.75289656625237
- type: euclidean_recall
value: 73.58839050131925
- type: manhattan_accuracy
value: 84.40126363473803
- type: manhattan_ap
value: 68.09539181555348
- type: manhattan_f1
value: 64.99028182701653
- type: manhattan_precision
value: 60.22062134173795
- type: manhattan_recall
value: 70.58047493403694
- type: max_accuracy
value: 84.5085533766466
- type: max_ap
value: 68.38835695236224
- type: max_f1
value: 65.3391121002694
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.34167733923235
- type: cos_sim_ap
value: 84.84136381147736
- type: cos_sim_f1
value: 77.01434980904001
- type: cos_sim_precision
value: 74.27937915742794
- type: cos_sim_recall
value: 79.95842315983985
- type: dot_accuracy
value: 85.06422944075756
- type: dot_ap
value: 76.49446747522325
- type: dot_f1
value: 71.11606520830432
- type: dot_precision
value: 64.93638676844785
- type: dot_recall
value: 78.59562673236834
- type: euclidean_accuracy
value: 88.45810532852097
- type: euclidean_ap
value: 84.91526721863501
- type: euclidean_f1
value: 77.04399001750662
- type: euclidean_precision
value: 74.62298867162133
- type: euclidean_recall
value: 79.62734832152756
- type: manhattan_accuracy
value: 88.46004579500912
- type: manhattan_ap
value: 84.81590026238194
- type: manhattan_f1
value: 76.97804626491822
- type: manhattan_precision
value: 73.79237288135593
- type: manhattan_recall
value: 80.45118570988605
- type: max_accuracy
value: 88.46004579500912
- type: max_ap
value: 84.91526721863501
- type: max_f1
value: 77.04399001750662
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
- mteb
---
# {gte-tiny}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
It is distilled from `thenlper/gte-small`, with comparable (slightly worse) performance at around half the size.
<!--- 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
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# 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, mean pooling.
sentence_embeddings = mean_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})
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
NeverSleep/Mistral-11B-AirOmniMix-GGUF
|
NeverSleep
| 2023-10-14T15:36:47Z | 26 | 0 | null |
[
"gguf",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2023-10-14T04:00:46Z |
---
license: cc-by-nc-4.0
---
Replaced Zephyr by Airoboros 2.2 in the mix.
## Description
This repo contains quantized files of Mistral-11B-AirOmniMix.
## Model used
- [Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
- [Mistral-7B-v0.1-Open-Platypus](https://huggingface.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus)
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b)
## Prompt template
The best one after further testing is this one, since Zephyr is out of the merge:
```
USER: <prompt>
ASSISTANT:
```
But this one work too:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Or use any prompting system from one of the 4 source model, should work.
## The secret sauce
Mistral-11B-OpenOrcaPlatypus :
```
slices:
- sources:
- model: Open-Orca/Mistral-7B-OpenOrca
layer_range: [0, 24]
- sources:
- model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
Mistral-11B-CC-Airo :
```
slices:
- sources:
- model: "/content/drive/MyDrive/CC-v1.1-7B-bf16"
layer_range: [0, 24]
- sources:
- model: "/content/drive/MyDrive/Mistral-7B-Airoboros-2.2-bf16"
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
Mistral-11B-AirOmniMix :
```
slices:
- sources:
- model: Mistral-11B-OpenOrcaPlatypus
layer_range: [0, 48]
- model: Mistral-11B-CC-Airo
layer_range: [0, 48]
merge_method: slerp
base_model: Mistral-11B-OpenOrcaPlatypus
parameters:
t:
- filter: lm_head
value: [0.75]
- filter: embed_tokens
value: [0.75]
- filter: self_attn
value: [0.75, 0.25]
- filter: mlp
value: [0.25, 0.75]
- filter: layernorm
value: [0.5, 0.5]
- filter: modelnorm
value: [0.75]
- value: 0.5 # fallback for rest of tensors
dtype: bfloat16
```
I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here.
## Some scoring I done myself
hf-causal-experimental (pretrained=/content/drive/MyDrive/Mistral-11B-AirOmniMix), limit: None, provide_description: False, num_fewshot: 0, batch_size: 4
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5452|± |0.0146|
| | |acc_norm|0.5836|± |0.0144|
|arc_easy | 0|acc |0.8321|± |0.0077|
| | |acc_norm|0.8119|± |0.0080|
|hellaswag | 0|acc |0.6381|± |0.0048|
| | |acc_norm|0.8250|± |0.0038|
|piqa | 0|acc |0.8096|± |0.0092|
| | |acc_norm|0.8243|± |0.0089|
|truthfulqa_mc| 1|mc1 |0.3941|± |0.0171|
| | |mc2 |0.5606|± |0.0155|
|winogrande | 0|acc |0.7395|± |0.0123|
## Others
Special thanks to Sushi, [Henky](https://github.com/KoboldAI/KoboldAI-Client) for the machine he give me for big task, and [Charles Goddard](https://github.com/cg123) for his amazing tool.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
NeverSleep/Mistral-11B-AirOmniMix
|
NeverSleep
| 2023-10-14T15:36:31Z | 1,486 | 2 |
transformers
|
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T01:57:46Z |
---
license: cc-by-nc-4.0
---
Replaced Zephyr by Airoboros 2.2 in the mix.
## Description
This repo contains fp16 files of Mistral-11B-AirOmniMix.
## Model used
- [Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
- [Mistral-7B-v0.1-Open-Platypus](https://huggingface.co/akjindal53244/Mistral-7B-v0.1-Open-Platypus)
- [CollectiveCognition-v1.1-Mistral-7B](https://huggingface.co/teknium/CollectiveCognition-v1.1-Mistral-7B)
- [airoboros-mistral2.2-7b](https://huggingface.co/teknium/airoboros-mistral2.2-7b)
## Prompt template
The best one after further testing is this one, since Zephyr is out of the merge:
```
USER: <prompt>
ASSISTANT:
```
But this one work too:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Or use any prompting system from one of the 4 source model, should work.
## The secret sauce
Mistral-11B-OpenOrcaPlatypus :
```
slices:
- sources:
- model: Open-Orca/Mistral-7B-OpenOrca
layer_range: [0, 24]
- sources:
- model: akjindal53244/Mistral-7B-v0.1-Open-Platypus
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
Mistral-11B-CC-Airo :
```
slices:
- sources:
- model: "/content/drive/MyDrive/CC-v1.1-7B-bf16"
layer_range: [0, 24]
- sources:
- model: "/content/drive/MyDrive/Mistral-7B-Airoboros-2.2-bf16"
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16
```
Mistral-11B-AirOmniMix :
```
slices:
- sources:
- model: Mistral-11B-OpenOrcaPlatypus
layer_range: [0, 48]
- model: Mistral-11B-CC-Airo
layer_range: [0, 48]
merge_method: slerp
base_model: Mistral-11B-OpenOrcaPlatypus
parameters:
t:
- filter: lm_head
value: [0.75]
- filter: embed_tokens
value: [0.75]
- filter: self_attn
value: [0.75, 0.25]
- filter: mlp
value: [0.25, 0.75]
- filter: layernorm
value: [0.5, 0.5]
- filter: modelnorm
value: [0.75]
- value: 0.5 # fallback for rest of tensors
dtype: bfloat16
```
I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here.
## Some scoring I done myself
hf-causal-experimental (pretrained=/content/drive/MyDrive/Mistral-11B-AirOmniMix), limit: None, provide_description: False, num_fewshot: 0, batch_size: 4
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5452|± |0.0146|
| | |acc_norm|0.5836|± |0.0144|
|arc_easy | 0|acc |0.8321|± |0.0077|
| | |acc_norm|0.8119|± |0.0080|
|hellaswag | 0|acc |0.6381|± |0.0048|
| | |acc_norm|0.8250|± |0.0038|
|piqa | 0|acc |0.8096|± |0.0092|
| | |acc_norm|0.8243|± |0.0089|
|truthfulqa_mc| 1|mc1 |0.3941|± |0.0171|
| | |mc2 |0.5606|± |0.0155|
|winogrande | 0|acc |0.7395|± |0.0123|
## Others
Special thanks to Sushi, [Henky](https://github.com/KoboldAI/KoboldAI-Client) for the machine he give me for big task, and [Charles Goddard](https://github.com/cg123) for his amazing tool.
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
sungkwangjoong/xlm-roberta-base-finetuned-panx-all
|
sungkwangjoong
| 2023-10-14T15:34:54Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-14T15:29:10Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-all
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. -->
# xlm-roberta-base-finetuned-panx-all
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1763
- F1: 0.8466
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3074 | 1.0 | 835 | 0.1948 | 0.8087 |
| 0.1625 | 2.0 | 1670 | 0.1672 | 0.8350 |
| 0.1064 | 3.0 | 2505 | 0.1763 | 0.8466 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
sungkwangjoong/xlm-roberta-base-finetuned-panx-en
|
sungkwangjoong
| 2023-10-14T15:28:34Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-14T15:26:33Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-en
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.en
split: validation
args: PAN-X.en
metrics:
- name: F1
type: f1
value: 0.7014590347923682
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-en
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3964
- F1: 0.7015
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.1219 | 1.0 | 50 | 0.6235 | 0.4926 |
| 0.508 | 2.0 | 100 | 0.4043 | 0.6909 |
| 0.3484 | 3.0 | 150 | 0.3964 | 0.7015 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/speechless-codellama-34b-v2.0-GPTQ
|
TheBloke
| 2023-10-14T15:26:44Z | 19 | 4 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-2",
"code",
"en",
"dataset:jondurbin/airoboros-2.2",
"dataset:Open-Orca/OpenOrca",
"dataset:garage-bAInd/Open-Platypus",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"arxiv:2308.12950",
"base_model:uukuguy/speechless-codellama-34b-v2.0",
"base_model:quantized:uukuguy/speechless-codellama-34b-v2.0",
"license:llama2",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
] |
text-generation
| 2023-10-13T07:21:57Z |
---
base_model: uukuguy/speechless-codellama-34b-v2.0
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
inference: false
language:
- en
library_name: transformers
license: llama2
model-index:
- name: SpeechlessCoder
results:
- dataset:
name: HumanEval
type: openai_humaneval
metrics:
- name: pass@1
type: pass@1
value: 75.61
verified: false
task:
type: text-generation
model_creator: Jiangwen Su
model_name: Speechless Codellama 34B v2.0
model_type: llama
pipeline_tag: text-generation
prompt_template: '{prompt}
'
quantized_by: TheBloke
tags:
- llama-2
- code
---
<!-- 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 -->
# Speechless Codellama 34B v2.0 - GPTQ
- Model creator: [Jiangwen Su](https://huggingface.co/uukuguy)
- Original model: [Speechless Codellama 34B v2.0](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Jiangwen Su's Speechless Codellama 34B v2.0](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0).
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/speechless-codellama-34b-v2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF)
* [Jiangwen Su's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- 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.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<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/speechless-codellama-34b-v2.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 17.69 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 18.33 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/speechless-codellama-34b-v2.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 20.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 14.14 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 34.30 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 16384 | 35.07 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher 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/speechless-codellama-34b-v2.0-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/speechless-codellama-34b-v2.0-GPTQ:gptq-4bit-128g-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 `speechless-codellama-34b-v2.0-GPTQ`:
```shell
mkdir speechless-codellama-34b-v2.0-GPTQ
huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --local-dir speechless-codellama-34b-v2.0-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir speechless-codellama-34b-v2.0-GPTQ
huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir speechless-codellama-34b-v2.0-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 speechless-codellama-34b-v2.0-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/speechless-codellama-34b-v2.0-GPTQ --local-dir speechless-codellama-34b-v2.0-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-128g-actorder_True https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-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/speechless-codellama-34b-v2.0-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/speechless-codellama-34b-v2.0-GPTQ:gptq-4bit-128g-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: `speechless-codellama-34b-v2.0-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-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/speechless-codellama-34b-v2.0-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi 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/speechless-codellama-34b-v2.0-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-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'''{prompt}
'''
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 and Mistral 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: Jiangwen Su's Speechless Codellama 34B v2.0
<p><h1> speechless-codellama-34b-v2.0 </h1></p>
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-GGUF)
Use the following datasets to fine-tune codellama/CodeLlama-34B in order to improve the model's inference and planning capabilities.
Total 153,013 samples.
- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
## HumanEval
| human-eval | pass@1 |
| --- | --- |
| humaneval-python | 75.61 |
[Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard)
| Models | pass@1 |
|------ | ------ |
| Phind-CodeLlama-34B-v2| 71.95|
| WizardCoder-Python-34B-V1.0| 70.73|
| Phind-CodeLlama-34B-Python-v1| 70.22|
| Phind-CodeLlama-34B-v1| 65.85|
| WizardCoder-Python-13B-V1.0| 62.19|
| WizardCoder-15B-V1.0| 58.12|
| CodeLlama-34B-Python| 53.29|
| CodeLlama-34B-Instruct| 50.79|
| CodeLlama-13B-Instruct| 50.6|
| CodeLlama-34B| 45.11|
| CodeLlama-13B-Python| 42.89|
| CodeLlama-13B| 35.07|
## NL2SQL
SQL-EVAL: 125/175 (71.43%)
Average rate of exact match: 67.43%
Average correct rate: 71.43%
- GPT4: 130/175 (74.29%)
- GPT3-Turbo-0613: 105/174 (60.00%)
## lm-evaluation-harness
[Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
| Metric | Value |
| --- | --- |
| ARC | 54.35 |
| HellaSwag | 75.65 |
| MMLU | 54.67 |
| TruthfulQA | 45.21 |
| Average | 57.47 |
H800-80G x 2
transformers=4.33.0
flash-attn=2.1.0
bitsandbytes=0.41.1
peft=0.5.0
## Training Arguments
| | |
|------ | ------ |
| lr | 2e-4 |
| lr_scheduler_type | cosine |
| weight_decay | 0.0 |
| optim | paged_adamw_8bit |
| flash_attention | True |
| rerope | False |
| max_new_tokens | 8192 |
| num_train_epochs | 3 |
| bits | 4 |
| lora_r | 64 |
| lora_alpha | 16 |
| lora_dropout | 0.05 |
| double_quant | True |
| quant_type | nf4 |
| dataset_format | airoboros |
| mini_batch_size | 4 |
| grandient_accumulation_steps | 16 |
| bf16 | True |
| | |
|------ | ------ |
| epoch | 3.0 |
| etrain_loss | 0.4261 |
| etrain_runtime | 1 day, 14:42:57.87 |
| etrain_samples_per_second | 3.227 |
| etrain_steps_per_second | 0.025 |
| eeval_loss | 0.4537 |
| eeval_runtime | 0:00:36.19 |
| eeval_samples_per_second | 5.525 |
| eeval_steps_per_second | 2.763 |
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 13B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
## Model Use
To use this model, please make sure to install transformers from `main` until the next version is released:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [x] Infilling.
- [ ] Instructions / chat.
- [ ] Python specialist.
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "codellama/CodeLlama-13b-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
'import socket\n\ndef ping_exponential_backoff(host: str):',
do_sample=True,
top_k=10,
temperature=0.1,
top_p=0.95,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in three model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
**This repository contains the base version of the 13B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct 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** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**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 Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are 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, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-user-guide](https://ai.meta.com/llama/responsible-user-guide).
|
sungkwangjoong/xlm-roberta-base-finetuned-panx-ko
|
sungkwangjoong
| 2023-10-14T15:26:29Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-14T15:24:14Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-ko
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.ko
split: validation
args: PAN-X.ko
metrics:
- name: F1
type: f1
value: 0.7460711331679073
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-ko
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2877
- F1: 0.7461
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.8031 | 1.0 | 70 | 0.3877 | 0.5850 |
| 0.3254 | 2.0 | 140 | 0.3009 | 0.7181 |
| 0.2295 | 3.0 | 210 | 0.2877 | 0.7461 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Workhack/intent_classifier_mistral_7b_adapter
|
Workhack
| 2023-10-14T15:21:07Z | 13 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-14T15:21:05Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
poteminr/llama2-conll2003
|
poteminr
| 2023-10-14T15:17:50Z | 3 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
] | null | 2023-09-28T06:35:23Z |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## 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
|
LoftQ/bart-large-bit2-rank8
|
LoftQ
| 2023-10-14T15:14:16Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"bart",
"arxiv:1910.09700",
"base_model:facebook/bart-large",
"base_model:adapter:facebook/bart-large",
"region:us"
] | null | 2023-10-14T15:12:35Z |
---
library_name: peft
base_model: facebook/bart-large
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
tt1717/ppo-LunarLander-v2-scratch
|
tt1717
| 2023-10-14T15:00:47Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T15:00:41Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -153.09 +/- 78.81
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'T-T1717/ppo-LunarLander-v2-scratch'
'batch_size': 512
'minibatch_size': 128}
```
|
LoftQ/bart-large-bit4-rank8
|
LoftQ
| 2023-10-14T14:58:39Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"bart",
"arxiv:1910.09700",
"base_model:facebook/bart-large",
"base_model:adapter:facebook/bart-large",
"region:us"
] | null | 2023-10-14T14:56:28Z |
---
library_name: peft
base_model: facebook/bart-large
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
jordanhilado/sd-1-1-sketch-lora
|
jordanhilado
| 2023-10-14T14:55:56Z | 3 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:CompVis/stable-diffusion-v1-1",
"base_model:adapter:CompVis/stable-diffusion-v1-1",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-14T09:05:31Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-1
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - jordanhilado/sd-1-1-sketch-scene
These are LoRA adaption weights for CompVis/stable-diffusion-v1-1. The weights were fine-tuned on the zoheb/sketch-scene dataset. You can find some example images in the following.
|
sungkwangjoong/xlm-roberta-base-finetuned-panx-de
|
sungkwangjoong
| 2023-10-14T14:51:59Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"dataset:xtreme",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-14T05:33:11Z |
---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- xtreme
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-panx-de
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xtreme
type: xtreme
config: PAN-X.de
split: validation
args: PAN-X.de
metrics:
- name: F1
type: f1
value: 0.8657241810026685
---
<!-- 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. -->
# xlm-roberta-base-finetuned-panx-de
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the xtreme dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1338
- F1: 0.8657
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.257 | 1.0 | 525 | 0.1557 | 0.8218 |
| 0.126 | 2.0 | 1050 | 0.1460 | 0.8521 |
| 0.0827 | 3.0 | 1575 | 0.1338 | 0.8657 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
LoftQ/bart-large-bit4-rank32
|
LoftQ
| 2023-10-14T14:51:35Z | 1 | 0 |
peft
|
[
"peft",
"pytorch",
"bart",
"arxiv:1910.09700",
"base_model:facebook/bart-large",
"base_model:adapter:facebook/bart-large",
"region:us"
] | null | 2023-10-14T14:49:41Z |
---
library_name: peft
base_model: facebook/bart-large
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
SakshiRathi77/wav2vec2_xlsr_300m
|
SakshiRathi77
| 2023-10-14T14:44:27Z | 12 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"hi",
"dataset:mozilla-foundation/common_voice_15_0",
"base_model:facebook/wav2vec2-xls-r-300m",
"base_model:finetune:facebook/wav2vec2-xls-r-300m",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-14T08:30:35Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
- cer
model-index:
- name: wav2vec2-large-xls-r-300m-hi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 15
type: mozilla-foundation/common_voice_15_0
args: hi
metrics:
- name: Test WER
type: wer
value: 29.34
- name: Test CER
type: cer
value: 7.86
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 8
type: mozilla-foundation/common_voice_8_0
args: hi
metrics:
- name: Test WER
type: wer
value: 52.09
- name: Test CER
type: cer
value: 17.90
datasets:
- mozilla-foundation/common_voice_15_0
language:
- hi
library_name: transformers
pipeline_tag: automatic-speech-recognition
---
<!-- 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. -->
# wav2vec2-large-xls-r-300m-hi
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3611
- Wer: 29.92%
- Cer: 7.86%
View the results on Kaggle Notebook: https://www.kaggle.com/code/kingabzpro/wav2vec-2-eval
## Evaluation
```python
import torch
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import librosa
import unicodedata
import re
test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "hi", split="test")
wer = load_metric("wer")
cer = load_metric("cer")
processor = Wav2Vec2Processor.from_pretrained("SakshiRathi77/wav2vec2_xlsr_300m")
model = Wav2Vec2ForCTC.from_pretrained("SakshiRathi77/wav2vec2_xlsr_300m")
model.to("cuda")
# Preprocessing the datasets.
def speech_file_to_array_fn(batch):
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\’\'\|\&\–]'
remove_en = '[A-Za-z]'
batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"].lower())
batch["sentence"] = re.sub(remove_en, "", batch["sentence"]).lower()
batch["sentence"] = unicodedata.normalize("NFKC", batch["sentence"])
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids, skip_special_tokens=True)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
print("WER: {}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
print("CER: {}".format(100 * cer.compute(predictions=result["pred_strings"], references=result["sentence"])))
```
```bash
WER: 52.09850206372026
CER: 17.902923538230883
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- 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_steps: 300
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 7.0431 | 19.05 | 300 | 3.4423 | 1.0 | 1.0 |
| 2.3233 | 38.1 | 600 | 0.5965 | 0.4757 | 0.1329 |
| 0.5676 | 57.14 | 900 | 0.3962 | 0.3584 | 0.0954 |
| 0.3611 | 76.19 | 1200 | 0.3651 | 0.3190 | 0.0820 |
| 0.2996 | 95.24 | 1500 | 0.3611 | 0.2992 | 0.0786 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
prometheus-eval/prometheus-7b-v1.0
|
prometheus-eval
| 2023-10-14T14:43:41Z | 159 | 30 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"text2text-generation",
"en",
"dataset:kaist-ai/Feedback-Collection",
"arxiv:2310.08491",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-12T07:12:28Z |
---
tags:
- text2text-generation
datasets:
- kaist-ai/Feedback-Collection
license: apache-2.0
language:
- en
pipeline_tag: text2text-generation
library_name: transformers
metrics:
- pearsonr
- spearmanr
- accuracy
---
## Links for Reference
- **Homepage:https://github.com/kaistAI/Prometheus**
- **Repository:https://github.com/kaistAI/Prometheus**
- **Paper:https://arxiv.org/abs/2310.08491**
- **Point of Contact:seungone@kaist.ac.kr**
# TL;DR
Prometheus is an alternative of GPT-4 evaluation when doing fine-grained evaluation of an underlying LLM & a Reward model for Reinforcement Learning from Human Feedback (RLHF).
Prometheus is a language model using [Llama-2-Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) as a base model and fine-tuned on 100K feedback within the [Feedback Collection](https://huggingface.co/datasets/kaist-ai/Feedback-Collection).
Since it was fine-tuned on a large amount of feedback, it is specialized at evaluating long-form responses, outperforming GPT-3.5-Turbo, Llama-2-Chat 70B, and on par with GPT-4 on various benchmarks.
Most importantly, this was possible since we appended 2 reference materials (reference answer, and customized score rubric).
Prometheus is a cheap and powerful alternative to GPT-4 evaluation, which one could use to evaluate LLMs with customized criteria (e.g., Child readability, Cultural Sensitivity, Creativity).
Also, it could be used as a reward model for Reinforcement Learning from Human Feedback (RLHF).
# Model Details
## Model Description
- **Model type:** Language model
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Related Models:** [All Prometheus Checkpoints](https://huggingface.co/models?search=kaist-ai/Prometheus)
- **Resources for more information:**
- [Research paper](https://arxiv.org/abs/2310.08491)
- [GitHub Repo](https://github.com/kaistAI/Prometheus)
Prometheus is trained with two different sizes (7B and 13B).
You could check the 13B sized LM on [this page](https://huggingface.co/kaist-ai/prometheus-13b-v1.0).
Also, check out our dataset as well on [this page](https://huggingface.co/datasets/kaist-ai/Feedback-Collection).
## Prompt Format
Prometheus requires 4 components in the input: An instruction, a response to evaluate, a score rubric, and a reference answer. You could refer to the prompt format below.
You should fill in the instruction, response, reference answer, criteria description, and score description for score in range of 1 to 5.
```
###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: \"Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)\"
4. Please do not generate any other opening, closing, and explanations.
###The instruction to evaluate:
{instruction}
###Response to evaluate:
{response}
###Reference Answer (Score 5):
{reference_answer}
###Score Rubrics:
[{criteria_description}]
Score 1: {score1_description}
Score 2: {score2_description}
Score 3: {score3_description}
Score 4: {score4_description}
Score 5: {score5_description}
###Feedback:
```
After this, you should apply the conversation template of Llama-2-Chat (not applying it might lead to unexpected behaviors).
You can find the conversation class at this [link](https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py).
```
conv = get_conv_template("llama-2")
conv.set_system_message("You are a fair evaluator language model.")
conv.append_message(conv.roles[0], dialogs['instruction'])
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
x = tokenizer(prompt,truncation=False)
```
As a result, a feedback and score decision will be generated, divided by a separating phrase ```[RESULT]```
## License
Feedback Collection and Prometheus is subject to OpenAI's Terms of Use for the generated data. If you suspect any violations, please reach out to us.
# Usage
Find below some example scripts on how to use the model in `transformers`:
## Using the Pytorch model
### Running the model on a CPU
<details>
<summary> Click to expand </summary>
```python
from transformers import AutoTokenizer, LlamaForCausalLM
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = LlamaForCausalLM.from_pretrained("kaist-ai/Prometheus-7b-v1.0", device_map="auto")
input_text = "###Task Description: An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given. 1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general. 2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric. 3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)" 4. Please do not generate any other opening, closing, and explanations. ###The instruction to evaluate: You are a well-known psychiatrist who has a reputation for being empathetic and understanding. A client comes to you saying they've had a really hard day at work. They describe their boss as being overly critical and not listening to their ideas, which has left them feeling frustrated and undervalued. They also mention feeling overwhelmed with the workload and a growing sense of loneliness as they are new to the city. How do you respond to them to make them feel heard and understood, as well as offering helpful advice? ###Response to evaluate: It's indeed challenging to deal with a difficult boss and to carry a large workload, especially when you are new to a city and haven't established a supportive network. I would suggest taking a step back to think about your situation and perhaps speak to your boss regarding the issues you're facing. On the other hand, dealing with a large workload can be managed by prioritizing tasks, and maybe you can discuss it with your superiors too. In regards to feeling lonely, you might want to explore activities or groups that align with your interests to meet new people. And also, remember to take time for yourself to relax and destress. I'm here to assist you as we navigate through these issues. ###Reference Answer (Score 5): I hear that you're dealing with quite a few challenging situations at once. It must be tough to have your ideas dismissed by your boss and to feel undervalued in your work environment. It's understandable that such experiences can lead to frustration and a feeling of being overwhelmed. It's important to acknowledge these feelings and not to dismiss them. Feeling heard and validated in our experiences can often be the first step towards resolving the challenges we face. So, I want you to know that your feelings are completely valid and it's okay to be frustrated and overwhelmed. In terms of dealing with your boss, have you considered seeking a private conversation with them to express your feelings? It's often beneficial to communicate what you're experiencing, using "I" statements to express how you feel when your ideas are not taken into consideration. This can lead to mutual understanding and possibly a change in behavior. About the workload, it might help to prioritize tasks and potentially delegate, if possible. Also, consider discussing your workload with your superiors. There might be a misunderstanding about what's manageable or they might have suggestions about how to handle the situation. On the personal front, feeling lonely, especially when you're new to a city, can be really hard. Seek out opportunities to meet new people, perhaps through hobbies, community activities, or online groups. It might take a bit of time, but gradually, you can build a network of friends and acquaintances. Remember, it's perfectly okay to have bad days and it's important to take care of your mental health. Consider incorporating activities into your daily routine that make you happy and help you unwind. This could be anything from reading, yoga, going for a walk, or even listening to your favorite music. Please know that you're not alone in this. I'm here to support you through this challenging time and together, we can work towards resolving these issues. ###Score Rubrics: [Is the model able to identify and react correctly to the emotional context of the user's input?] Score 1: The model utterly fails to grasp the user's emotional context and responds in an unfitting manner. Score 2: The model sporadically identifies the emotional context but frequently replies in a manner that doesn't match the user's emotional status. Score 3: The model typically identifies the emotional context and reacts suitably, but occasionally misreads or misjudges the user's feelings. Score 4: The model often identifies the emotional context and reacts suitably, with minor cases of misreading or misjudging. Score 5: The model flawlessly identifies the emotional context of the user's input and consistently responds in a considerate and empathetic manner. ###Feedback:"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
### Running the model on a GPU
<details>
<summary> Click to expand </summary>
```python
# pip install accelerate
import torch
from transformers import AutoTokenizer, LlamaForCausalLM
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = LlamaForCausalLM.from_pretrained("kaist-ai/Prometheus-7b-v1.0", device_map="auto")
input_text = "###Task Description: An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given. 1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general. 2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric. 3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)" 4. Please do not generate any other opening, closing, and explanations. ###The instruction to evaluate: You are a well-known psychiatrist who has a reputation for being empathetic and understanding. A client comes to you saying they've had a really hard day at work. They describe their boss as being overly critical and not listening to their ideas, which has left them feeling frustrated and undervalued. They also mention feeling overwhelmed with the workload and a growing sense of loneliness as they are new to the city. How do you respond to them to make them feel heard and understood, as well as offering helpful advice? ###Response to evaluate: It's indeed challenging to deal with a difficult boss and to carry a large workload, especially when you are new to a city and haven't established a supportive network. I would suggest taking a step back to think about your situation and perhaps speak to your boss regarding the issues you're facing. On the other hand, dealing with a large workload can be managed by prioritizing tasks, and maybe you can discuss it with your superiors too. In regards to feeling lonely, you might want to explore activities or groups that align with your interests to meet new people. And also, remember to take time for yourself to relax and destress. I'm here to assist you as we navigate through these issues. ###Reference Answer (Score 5): I hear that you're dealing with quite a few challenging situations at once. It must be tough to have your ideas dismissed by your boss and to feel undervalued in your work environment. It's understandable that such experiences can lead to frustration and a feeling of being overwhelmed. It's important to acknowledge these feelings and not to dismiss them. Feeling heard and validated in our experiences can often be the first step towards resolving the challenges we face. So, I want you to know that your feelings are completely valid and it's okay to be frustrated and overwhelmed. In terms of dealing with your boss, have you considered seeking a private conversation with them to express your feelings? It's often beneficial to communicate what you're experiencing, using "I" statements to express how you feel when your ideas are not taken into consideration. This can lead to mutual understanding and possibly a change in behavior. About the workload, it might help to prioritize tasks and potentially delegate, if possible. Also, consider discussing your workload with your superiors. There might be a misunderstanding about what's manageable or they might have suggestions about how to handle the situation. On the personal front, feeling lonely, especially when you're new to a city, can be really hard. Seek out opportunities to meet new people, perhaps through hobbies, community activities, or online groups. It might take a bit of time, but gradually, you can build a network of friends and acquaintances. Remember, it's perfectly okay to have bad days and it's important to take care of your mental health. Consider incorporating activities into your daily routine that make you happy and help you unwind. This could be anything from reading, yoga, going for a walk, or even listening to your favorite music. Please know that you're not alone in this. I'm here to support you through this challenging time and together, we can work towards resolving these issues. ###Score Rubrics: [Is the model able to identify and react correctly to the emotional context of the user's input?] Score 1: The model utterly fails to grasp the user's emotional context and responds in an unfitting manner. Score 2: The model sporadically identifies the emotional context but frequently replies in a manner that doesn't match the user's emotional status. Score 3: The model typically identifies the emotional context and reacts suitably, but occasionally misreads or misjudges the user's feelings. Score 4: The model often identifies the emotional context and reacts suitably, with minor cases of misreading or misjudging. Score 5: The model flawlessly identifies the emotional context of the user's input and consistently responds in a considerate and empathetic manner. ###Feedback:"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids, sample=True, temperature=1.0, top_p=0.9, max_new_tokens=256, repetition_penalty=1.03)
print(tokenizer.decode(outputs[0]))
```
</details>
### Running the model on a GPU using different precisions
#### FP16
<details>
<summary> Click to expand </summary>
```python
# pip install accelerate
import torch
from transformers import AutoTokenizer, LlamaForCausalLM
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = LlamaForCausalLM.from_pretrained("kaist-ai/Prometheus-7b-v1.0", device_map="auto", torch_dtype=torch.float16)
input_text = "###Task Description: An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given. 1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general. 2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric. 3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)" 4. Please do not generate any other opening, closing, and explanations. ###The instruction to evaluate: You are a well-known psychiatrist who has a reputation for being empathetic and understanding. A client comes to you saying they've had a really hard day at work. They describe their boss as being overly critical and not listening to their ideas, which has left them feeling frustrated and undervalued. They also mention feeling overwhelmed with the workload and a growing sense of loneliness as they are new to the city. How do you respond to them to make them feel heard and understood, as well as offering helpful advice? ###Response to evaluate: It's indeed challenging to deal with a difficult boss and to carry a large workload, especially when you are new to a city and haven't established a supportive network. I would suggest taking a step back to think about your situation and perhaps speak to your boss regarding the issues you're facing. On the other hand, dealing with a large workload can be managed by prioritizing tasks, and maybe you can discuss it with your superiors too. In regards to feeling lonely, you might want to explore activities or groups that align with your interests to meet new people. And also, remember to take time for yourself to relax and destress. I'm here to assist you as we navigate through these issues. ###Reference Answer (Score 5): I hear that you're dealing with quite a few challenging situations at once. It must be tough to have your ideas dismissed by your boss and to feel undervalued in your work environment. It's understandable that such experiences can lead to frustration and a feeling of being overwhelmed. It's important to acknowledge these feelings and not to dismiss them. Feeling heard and validated in our experiences can often be the first step towards resolving the challenges we face. So, I want you to know that your feelings are completely valid and it's okay to be frustrated and overwhelmed. In terms of dealing with your boss, have you considered seeking a private conversation with them to express your feelings? It's often beneficial to communicate what you're experiencing, using "I" statements to express how you feel when your ideas are not taken into consideration. This can lead to mutual understanding and possibly a change in behavior. About the workload, it might help to prioritize tasks and potentially delegate, if possible. Also, consider discussing your workload with your superiors. There might be a misunderstanding about what's manageable or they might have suggestions about how to handle the situation. On the personal front, feeling lonely, especially when you're new to a city, can be really hard. Seek out opportunities to meet new people, perhaps through hobbies, community activities, or online groups. It might take a bit of time, but gradually, you can build a network of friends and acquaintances. Remember, it's perfectly okay to have bad days and it's important to take care of your mental health. Consider incorporating activities into your daily routine that make you happy and help you unwind. This could be anything from reading, yoga, going for a walk, or even listening to your favorite music. Please know that you're not alone in this. I'm here to support you through this challenging time and together, we can work towards resolving these issues. ###Score Rubrics: [Is the model able to identify and react correctly to the emotional context of the user's input?] Score 1: The model utterly fails to grasp the user's emotional context and responds in an unfitting manner. Score 2: The model sporadically identifies the emotional context but frequently replies in a manner that doesn't match the user's emotional status. Score 3: The model typically identifies the emotional context and reacts suitably, but occasionally misreads or misjudges the user's feelings. Score 4: The model often identifies the emotional context and reacts suitably, with minor cases of misreading or misjudging. Score 5: The model flawlessly identifies the emotional context of the user's input and consistently responds in a considerate and empathetic manner. ###Feedback:"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
#### INT8
<details>
<summary> Click to expand </summary>
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, LlamaForCausalLM
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = LlamaForCausalLM.from_pretrained("kaist-ai/Prometheus-7b-v1.0", device_map="auto", load_in_8bit=True)
input_text = "###Task Description: An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given. 1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general. 2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric. 3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)" 4. Please do not generate any other opening, closing, and explanations. ###The instruction to evaluate: You are a well-known psychiatrist who has a reputation for being empathetic and understanding. A client comes to you saying they've had a really hard day at work. They describe their boss as being overly critical and not listening to their ideas, which has left them feeling frustrated and undervalued. They also mention feeling overwhelmed with the workload and a growing sense of loneliness as they are new to the city. How do you respond to them to make them feel heard and understood, as well as offering helpful advice? ###Response to evaluate: It's indeed challenging to deal with a difficult boss and to carry a large workload, especially when you are new to a city and haven't established a supportive network. I would suggest taking a step back to think about your situation and perhaps speak to your boss regarding the issues you're facing. On the other hand, dealing with a large workload can be managed by prioritizing tasks, and maybe you can discuss it with your superiors too. In regards to feeling lonely, you might want to explore activities or groups that align with your interests to meet new people. And also, remember to take time for yourself to relax and destress. I'm here to assist you as we navigate through these issues. ###Reference Answer (Score 5): I hear that you're dealing with quite a few challenging situations at once. It must be tough to have your ideas dismissed by your boss and to feel undervalued in your work environment. It's understandable that such experiences can lead to frustration and a feeling of being overwhelmed. It's important to acknowledge these feelings and not to dismiss them. Feeling heard and validated in our experiences can often be the first step towards resolving the challenges we face. So, I want you to know that your feelings are completely valid and it's okay to be frustrated and overwhelmed. In terms of dealing with your boss, have you considered seeking a private conversation with them to express your feelings? It's often beneficial to communicate what you're experiencing, using "I" statements to express how you feel when your ideas are not taken into consideration. This can lead to mutual understanding and possibly a change in behavior. About the workload, it might help to prioritize tasks and potentially delegate, if possible. Also, consider discussing your workload with your superiors. There might be a misunderstanding about what's manageable or they might have suggestions about how to handle the situation. On the personal front, feeling lonely, especially when you're new to a city, can be really hard. Seek out opportunities to meet new people, perhaps through hobbies, community activities, or online groups. It might take a bit of time, but gradually, you can build a network of friends and acquaintances. Remember, it's perfectly okay to have bad days and it's important to take care of your mental health. Consider incorporating activities into your daily routine that make you happy and help you unwind. This could be anything from reading, yoga, going for a walk, or even listening to your favorite music. Please know that you're not alone in this. I'm here to support you through this challenging time and together, we can work towards resolving these issues. ###Score Rubrics: [Is the model able to identify and react correctly to the emotional context of the user's input?] Score 1: The model utterly fails to grasp the user's emotional context and responds in an unfitting manner. Score 2: The model sporadically identifies the emotional context but frequently replies in a manner that doesn't match the user's emotional status. Score 3: The model typically identifies the emotional context and reacts suitably, but occasionally misreads or misjudges the user's feelings. Score 4: The model often identifies the emotional context and reacts suitably, with minor cases of misreading or misjudging. Score 5: The model flawlessly identifies the emotional context of the user's input and consistently responds in a considerate and empathetic manner. ###Feedback:"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))
```
</details>
# Citation
If you find the following model helpful, please consider citing our paper!
**BibTeX:**
```bibtex
@misc{kim2023prometheus,
title={Prometheus: Inducing Fine-grained Evaluation Capability in Language Models},
author={Seungone Kim and Jamin Shin and Yejin Cho and Joel Jang and Shayne Longpre and Hwaran Lee and Sangdoo Yun and Seongjin Shin and Sungdong Kim and James Thorne and Minjoon Seo},
year={2023},
eprint={2310.08491},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
RL-Course-2023-Archive/ppo-LunarLander-JT
|
RL-Course-2023-Archive
| 2023-10-14T14:27:49Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T14:27:09Z |
---
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: -140.48 +/- 55.59
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
...
```
|
RL-Course-2023-Archive/ppo-LunarLander-ToMo2
|
RL-Course-2023-Archive
| 2023-10-14T14:22:20Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T14:21:52Z |
---
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: -167.81 +/- 47.41
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
...
```
|
RL-Course-2023-Archive/ppo-LunarLander-v2-Zuber
|
RL-Course-2023-Archive
| 2023-10-14T14:21:30Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T14:18:54Z |
---
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: -127.69 +/- 49.68
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
...
```
|
RL-Course-2023-Archive/ppo-LunarLander-v2-jmt
|
RL-Course-2023-Archive
| 2023-10-14T14:13:49Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T14:13:24Z |
---
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: -138.03 +/- 45.82
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
...
```
|
monsterapi/Mistral-7B-v0.1-Dolly-15k
|
monsterapi
| 2023-10-14T14:04:20Z | 0 | 0 |
peft
|
[
"peft",
"mistral",
"databricks",
"dolly",
"mistral 7b",
"llama",
"finetune",
"finetuning",
"dataset:databricks/databricks-dolly-15k",
"region:us"
] | null | 2023-10-14T13:28:13Z |
---
library_name: peft
datasets:
- databricks/databricks-dolly-15k
tags:
- mistral
- databricks
- dolly
- mistral 7b
- llama
- finetune
- finetuning
---
## Training procedure
We finetuned [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) Dataset for 1 epoch using [MonsterAPI](https://monsterapi.ai/) no-code [LLM finetuner](https://monsterapi.ai/finetuning).
## Finetuning with MonsterAPI no-code LLM Finetuner in 5 easy steps:
1. **Select an LLM:** Mistral 7B v0.1
2. **Select a task and Dataset:** Instruction Finetuning and databricks-dolly-15k Dataset
3. **Specify Hyperparameters:** We used default values suggested by finetuner
4. **Review and submit the job:** That's it!
### Hyperparameters & Run details:
- Model: mistralai/Mistral-7B-v0.1
- Dataset: databricks/databricks-dolly-15k
- Learning rate: 0.0002
- Number of epochs: 1
- Cutoff length: 512
- Data split: Training: 95% / Validation: 5%
- Gradient accumulation steps: 1
### About Model:
The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on majority of the benchmarks as tested by Mistral team.
### About Dataset:
databricks-dolly-15k is a corpus of more than 15,000 records generated by thousands of Databricks employees to enable large language models to exhibit the magical interactivity of ChatGPT.
### Framework versions
- PEFT 0.5.0
|
agoel3705/taxi-v3
|
agoel3705
| 2023-10-14T13:53:22Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T13:36:30Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: 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="agoel3705/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"])
```
|
pfunk/PongNoFrameskip-v4-DDQN-seed3
|
pfunk
| 2023-10-14T13:51:39Z | 0 | 0 |
cleanrl
|
[
"cleanrl",
"tensorboard",
"PongNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T13:51:32Z |
---
tags:
- PongNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PongNoFrameskip-v4
type: PongNoFrameskip-v4
metrics:
- type: mean_reward
value: 18.53 +/- 0.00
name: mean_reward
verified: false
---
# (CleanRL) **DQN** Agent Playing **PongNoFrameskip-v4**
This is a trained model of a DQN agent playing PongNoFrameskip-v4.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/DDQN.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[DDQN]"
python -m cleanrl_utils.enjoy --exp-name DDQN --env-id PongNoFrameskip-v4
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DDQN-seed3/raw/main/dqn_atari.py
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DDQN-seed3/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DDQN-seed3/raw/main/poetry.lock
poetry install --all-extras
python dqn_atari.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name DDQN --target-network-frequency 1000 --seed 3 --double-learning
```
# Hyperparameters
```python
{'alg_type': 'dqn_atari.py',
'batch_size': 32,
'buffer_size': 1000000,
'capture_video': True,
'cuda': True,
'double_learning': True,
'end_e': 0.05,
'env_id': 'PongNoFrameskip-v4',
'exp_name': 'DDQN',
'exploration_fraction': 0.2,
'gamma': 0.99,
'hf_entity': 'pfunk',
'learning_rate': 0.0001,
'learning_starts': 10000,
'max_gradient_norm': inf,
'save_model': True,
'seed': 3,
'start_e': 1.0,
'target_network_frequency': 1000,
'target_tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 10000000,
'track': True,
'train_frequency': 1,
'upload_model': True,
'wandb_entity': 'pfunk',
'wandb_project_name': 'dqpn'}
```
|
AndreasPiper/donut-base-sroie
|
AndreasPiper
| 2023-10-14T13:47:44Z | 2 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:imagefolder",
"license:mit",
"endpoints_compatible",
"region:us"
] |
image-text-to-text
| 2023-10-14T12:43:26Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- imagefolder
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 imagefolder 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: 2
- 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 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
Kwan0/layoutlmv3-base-finetune-DocLayNet-100k
|
Kwan0
| 2023-10-14T13:46:16Z | 296 | 4 |
transformers
|
[
"transformers",
"pytorch",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"dataset:pierreguillou/DocLayNet-large",
"base_model:microsoft/layoutlmv3-base",
"base_model:finetune:microsoft/layoutlmv3-base",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-10-05T03:24:24Z |
---
tags:
- generated_from_trainer
datasets:
- pierreguillou/DocLayNet-large
metrics:
- precision
- recall
- f1
- accuracy
base_model: microsoft/layoutlmv3-base
model-index:
- name: layoutlmv3-finetuned-doclaynet
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: pierreguillou/DocLayNet-large
type: pierreguillou/DocLayNet-large
args: doclaynet
metrics:
- type: precision
value: 0.847
name: Precision
- type: recall
value: 0.893
name: Recall
- type: f1
value: 0.870
name: F1
- type: accuracy
value: 0.957
name: Accuracy
---
# layoutlmv3-finetuned-funsd
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the pierreguillou/DocLayNet-large using bounding boxes and
categories for lines (not for for paragraphs).
It achieves the following results on the evaluation set:
- Loss: 0.33888205885887146,
- Precision: 0.8478835766832817,
- Recall: 0.8934488524091807,
- F1: 0.8700700634847538,
- Accuracy: 0.9574140990541197
The script for training can be found here: https://github.com/huggingface/transformers/tree/main/examples/research_projects/layoutlmv3
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: 2
- training_steps: 100000
### Framework versions
- Transformers 4.33.3
- Pytorch 1.11.0+cu115
- Datasets 2.14.5
- Tokenizers 0.13.3
|
nigelhitch/charli_xcx
|
nigelhitch
| 2023-10-14T13:39:32Z | 0 | 0 |
adapter-transformers
|
[
"adapter-transformers",
"music",
"audio-to-audio",
"dataset:meta-math/MetaMathQA",
"license:artistic-2.0",
"region:us"
] |
audio-to-audio
| 2023-10-14T13:22:44Z |
---
license: artistic-2.0
pipeline_tag: audio-to-audio
tags:
- music
datasets:
- meta-math/MetaMathQA
metrics:
- character
library_name: adapter-transformers
---
|
yesj1234/mbart-mmt_mid1_zh-ko
|
yesj1234
| 2023-10-14T13:33:38Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mbart",
"text2text-generation",
"generated_from_trainer",
"zh",
"ko",
"base_model:facebook/mbart-large-cc25",
"base_model:finetune:facebook/mbart-large-cc25",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-14T13:25:43Z |
---
language:
- zh
- ko
base_model: facebook/mbart-large-cc25
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: zh-kr_mid
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. -->
# zh-kr_mid
This model is a fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5557
- Bleu: 16.6036
- Gen Len: 15.4901
## 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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
| 2.7248 | 0.75 | 1000 | 1.9410 | 3.2381 | 48.6095 |
| 1.5683 | 1.5 | 2000 | 1.6889 | 10.2345 | 20.4433 |
| 1.1916 | 2.25 | 3000 | 1.6843 | 13.4571 | 18.8854 |
| 1.068 | 2.99 | 4000 | 1.6390 | 15.6862 | 15.5054 |
| 0.7313 | 3.74 | 5000 | 1.7003 | 15.2014 | 16.5938 |
| 0.4832 | 4.49 | 6000 | 1.8982 | 15.0381 | 16.9068 |
| 0.3862 | 5.24 | 7000 | 2.1426 | 15.5397 | 15.6451 |
| 0.3675 | 5.99 | 8000 | 2.1168 | 15.8847 | 15.6926 |
| 0.2627 | 6.74 | 9000 | 2.2603 | 16.3603 | 15.9671 |
| 0.1955 | 7.49 | 10000 | 2.4114 | 15.7447 | 15.979 |
| 0.171 | 8.23 | 11000 | 2.5141 | 15.7852 | 15.9244 |
| 0.1702 | 8.98 | 12000 | 2.5557 | 16.6036 | 15.4901 |
| 0.1298 | 9.73 | 13000 | 2.6536 | 16.1319 | 15.5492 |
| 0.1052 | 10.48 | 14000 | 2.7586 | 16.1807 | 15.8884 |
| 0.2268 | 11.23 | 15000 | 2.7258 | 15.1752 | 15.5346 |
| 0.1327 | 11.98 | 16000 | 2.7193 | 15.8563 | 15.7971 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Jake0078/Mommy
|
Jake0078
| 2023-10-14T13:19:46Z | 0 | 0 | null |
[
"license:unknown",
"region:us"
] | null | 2023-10-14T13:16:03Z |
---
license: unknown
metrics:
- character
---
|
RazinAleks/mT5-fine-tune
|
RazinAleks
| 2023-10-14T13:09:22Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-13T11:15:36Z |
---
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mT5-fine-tune
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-fine-tune
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: 2.5256
- Rouge1: 0.0822
- Rouge2: 0.0244
- Rougel: 0.0813
- Rougelsum: 0.0814
- Gen Len: 18.9803
- Chrf Score: 20.301
- Chrf Char Order: 6
- Chrf Word Order: 0
- Chrf Beta: 2
## 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: 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: 7
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Chrf Score | Chrf Char Order | Chrf Word Order | Chrf Beta |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:----------:|:---------------:|:---------------:|:---------:|
| 3.5479 | 1.0 | 1951 | 2.7435 | 0.0672 | 0.021 | 0.0666 | 0.0667 | 18.9323 | 19.2495 | 6 | 0 | 2 |
| 3.1717 | 2.0 | 3902 | 2.6452 | 0.0746 | 0.0207 | 0.0738 | 0.0737 | 18.9814 | 20.1079 | 6 | 0 | 2 |
| 3.0151 | 3.0 | 5853 | 2.6014 | 0.0834 | 0.0243 | 0.0826 | 0.0823 | 18.9891 | 20.2875 | 6 | 0 | 2 |
| 2.95 | 4.0 | 7804 | 2.5647 | 0.0765 | 0.0218 | 0.0757 | 0.0757 | 18.981 | 20.2327 | 6 | 0 | 2 |
| 2.8592 | 5.0 | 9755 | 2.5480 | 0.0822 | 0.0242 | 0.0814 | 0.0813 | 18.9819 | 20.3982 | 6 | 0 | 2 |
| 2.8214 | 6.0 | 11706 | 2.5317 | 0.0841 | 0.0255 | 0.0831 | 0.083 | 18.9764 | 20.3935 | 6 | 0 | 2 |
| 2.789 | 7.0 | 13657 | 2.5256 | 0.0822 | 0.0244 | 0.0813 | 0.0814 | 18.9803 | 20.301 | 6 | 0 | 2 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
lauraparra28/albert-large-v2-finetuned-squad
|
lauraparra28
| 2023-10-14T12:26:21Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"albert",
"question-answering",
"generated_from_trainer",
"dataset:squad_v2",
"base_model:albert/albert-large-v2",
"base_model:finetune:albert/albert-large-v2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-12T20:35:34Z |
---
license: apache-2.0
base_model: albert-large-v2
tags:
- generated_from_trainer
datasets:
- squad_v2
model-index:
- name: albert-large-v2-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. -->
# albert-large-v2-finetuned-squad
This model is a fine-tuned version of [albert-large-v2](https://huggingface.co/albert-large-v2) on the squad_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1819
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.8412 | 1.0 | 8248 | 0.8427 |
| 0.6729 | 2.0 | 16496 | 0.7978 |
| 0.5069 | 3.0 | 24744 | 0.8760 |
| 0.357 | 4.0 | 32992 | 1.0229 |
| 0.2374 | 5.0 | 41240 | 1.1819 |
### Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
MattStammers/appo-atari_qbert-superhuman
|
MattStammers
| 2023-10-14T12:22:36Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-26T22:43:26Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: atari_qbert
type: atari_qbert
metrics:
- type: mean_reward
value: 30000.00 +/- 2753.45
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **atari_qbert** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_qbert
```
## About the Model
This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it.
The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels.
The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
```
hyperparameters = {
"device": "gpu",
"seed": 1234,
"num_policies": 2,
"async_rl": true,
"serial_mode": false,
"batched_sampling": true,
"num_batches_to_accumulate": 2,
"worker_num_splits": 1,
"policy_workers_per_policy": 1,
"max_policy_lag": 1000,
"num_workers": 16,
"num_envs_per_worker": 2,
"batch_size": 1024,
"num_batches_per_epoch": 8,
"num_epochs": 4,
"rollout": 128,
"recurrence": 1,
"shuffle_minibatches": false,
"gamma": 0.99,
"reward_scale": 1.0,
"reward_clip": 1000.0,
"value_bootstrap": false,
"normalize_returns": true,
"exploration_loss_coeff": 0.0004677351413,
"value_loss_coeff": 0.5,
"kl_loss_coeff": 0.0,
"exploration_loss": "entropy",
"gae_lambda": 0.95,
"ppo_clip_ratio": 0.1,
"ppo_clip_value": 1.0,
"with_vtrace": false,
"vtrace_rho": 1.0,
"vtrace_c": 1.0,
"optimizer": "adam",
"adam_eps": 1e-05,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"max_grad_norm": 0.0,
"learning_rate": 0.0003033891184,
"lr_schedule": "linear_decay",
"lr_schedule_kl_threshold": 0.008,
"lr_adaptive_min": 1e-06,
"lr_adaptive_max": 0.01,
"obs_subtract_mean": 0.0,
"obs_scale": 255.0,
"normalize_input": true,
"normalize_input_keys": [
"obs"
],
"decorrelate_experience_max_seconds": 0,
"decorrelate_envs_on_one_worker": true,
"actor_worker_gpus": [],
"set_workers_cpu_affinity": true,
"force_envs_single_thread": false,
"default_niceness": 0,
"log_to_file": true,
"experiment_summaries_interval": 3,
"flush_summaries_interval": 30,
"stats_avg": 100,
"summaries_use_frameskip": true,
"heartbeat_interval": 10,
"heartbeat_reporting_interval": 60,
"train_for_env_steps": 100000000,
"train_for_seconds": 10000000000,
"save_every_sec": 120,
"keep_checkpoints": 2,
"load_checkpoint_kind": "latest",
"save_milestones_sec": 1200,
"save_best_every_sec": 5,
"save_best_metric": "reward",
"save_best_after": 100000,
"benchmark": false,
"encoder_mlp_layers": [
512,
512
],
"encoder_conv_architecture": "convnet_atari",
"encoder_conv_mlp_layers": [
512
],
"use_rnn": false,
"rnn_size": 512,
"rnn_type": "gru",
"rnn_num_layers": 1,
"decoder_mlp_layers": [],
"nonlinearity": "relu",
"policy_initialization": "orthogonal",
"policy_init_gain": 1.0,
"actor_critic_share_weights": true,
"adaptive_stddev": false,
"continuous_tanh_scale": 0.0,
"initial_stddev": 1.0,
"use_env_info_cache": false,
"env_gpu_actions": false,
"env_gpu_observations": true,
"env_frameskip": 4,
"env_framestack": 4,
}
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m sf_examples.atari.train_atari --algo=APPO --env=atari_qbert --train_dir=./train_dir --experiment=APPO-atari_qbert --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
jayulll/distilbert-base-uncased-finetuned-clinc
|
jayulll
| 2023-10-14T12:07:39Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:clinc_oos",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T11:02:08Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- clinc_oos
model-index:
- name: distilbert-base-uncased-distilled-clinc
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-distilled-clinc
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
It achieves the following results on the evaluation set:
- eval_loss: 3.2455
- eval_accuracy: 0.7248
- eval_runtime: 0.9586
- eval_samples_per_second: 3233.755
- eval_steps_per_second: 67.805
- epoch: 1.0
- step: 318
## 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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
|
nyxophyl/q-FrozenLake-v1-4x4-noSlippery
|
nyxophyl
| 2023-10-14T11:51:11Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T11:51:08Z |
---
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="nyxophyl/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"])
```
|
Lukansu/ppo-LunarLander-v2
|
Lukansu
| 2023-10-14T11:49:43Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T11:49:25Z |
---
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: 293.37 +/- 23.61
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
...
```
|
Devharsh434/horse
|
Devharsh434
| 2023-10-14T11:16:21Z | 0 | 0 | null |
[
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-14T11:11:11Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### Horse Dreambooth model trained by Devharsh434 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: VCETV24
Sample pictures of this concept:
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
|
airenGpt/codeAlpacaFalcon7B
|
airenGpt
| 2023-10-14T11:01:53Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-10-14T09:44:58Z |
---
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
### Framework versions
- PEFT 0.5.0
|
Falah/sdworldlandmarks
|
Falah
| 2023-10-14T10:40:09Z | 1 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-14T07:31:38Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### SDWorldLandmarks Dreambooth model trained by Falah 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:
|
pabloyesteb/rl_course_vizdoom_health_gathering_supreme
|
pabloyesteb
| 2023-10-14T10:34:37Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T09:17:04Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.04 +/- 5.13
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r pabloyesteb/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
PankajShukla/llamma-db-ai
|
PankajShukla
| 2023-10-14T10:22:54Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:TheBloke/CodeLlama-13B-Instruct-GPTQ",
"base_model:finetune:TheBloke/CodeLlama-13B-Instruct-GPTQ",
"license:llama2",
"region:us"
] | null | 2023-10-14T10:22:45Z |
---
license: llama2
base_model: TheBloke/CodeLlama-13B-Instruct-GPTQ
tags:
- generated_from_trainer
model-index:
- name: llamma-db-ai
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. -->
# llamma-db-ai
This model is a fine-tuned version of [TheBloke/CodeLlama-13B-Instruct-GPTQ](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GPTQ) 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: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 500
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
ahmed000000000/phi-1_5-finetuned-gsm8k
|
ahmed000000000
| 2023-10-14T10:11:28Z | 13 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mixformer-sequential",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:microsoft/phi-1_5",
"base_model:finetune:microsoft/phi-1_5",
"license:other",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-09-22T12:39:18Z |
---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-gsm8k
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. -->
# phi-1_5-finetuned-gsm8k
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1000
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
nyxophyl/ppo-Huggy
|
nyxophyl
| 2023-10-14T10:08:29Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-10-14T10:08:23Z |
---
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: nyxophyl/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
jason1i/stable-diffusion-v1-5-pokemon-lora
|
jason1i
| 2023-10-14T10:03:47Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-10-14T09:38:55Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - jason1i/stable-diffusion-v1-5-pokemon-lora
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/pokemon-blip-captions dataset. You can find some example images in the following.
|
hilmansw/resnet18-catdog-classifier
|
hilmansw
| 2023-10-14T09:52:51Z | 121 | 0 |
transformers
|
[
"transformers",
"pytorch",
"resnet",
"image-classification",
"generated_from_trainer",
"en",
"base_model:microsoft/resnet-18",
"base_model:finetune:microsoft/resnet-18",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-22T15:09:05Z |
---
license: apache-2.0
base_model: microsoft/resnet-18
tags:
- generated_from_trainer
model-index:
- name: resnet18-catdog-classifier
results: []
pipeline_tag: image-classification
language:
- en
metrics:
- accuracy
---
<!-- 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. -->
# Model description
This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on an [custom](https://www.kaggle.com/datasets/samuelcortinhas/cats-and-dogs-image-classification) dataset. This model was built using the "Cats & Dogs Classification" dataset obtained from Kaggle. During the model building process, this was done using the Pytorch framework with pre-trained Resnet-18. The method used during the process of building this classification model is fine-tuning with the dataset.
## Training results
| Epoch | Accuracy |
|:-----:|:--------:|
| 1.0 | 0.9357 |
| 2.0 | 0.9786 |
| 3.0 | 0.9000 |
| 4.0 | 0.9214 |
| 5.0 | 0.9143 |
| 6.0 | 0.9429 |
| 7.0 | 0.9714 |
| 8.0 | 0.9929 |
| 9.0 | 0.9714 |
| 10.0 | 0.9714 |
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- loss_function = CrossEntropyLoss
- optimizer = AdamW
- learning_rate: 0.0001
- batch_size: 16
- num_epochs: 10
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
|
SophiaPu/PixelCopter
|
SophiaPu
| 2023-10-14T09:52:29Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T07:58:35Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: PixelCopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 17.10 +/- 15.63
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
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
|
openbmb/UltraCM-13b
|
openbmb
| 2023-10-14T09:50:25Z | 14 | 18 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:openbmb/UltraFeedback",
"arxiv:2310.01377",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-22T09:35:17Z |
---
license: mit
datasets:
- openbmb/UltraFeedback
---
A critic model trained on [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback). Please refer to [paper](https://arxiv.org/abs/2310.01377) and [Github](https://github.com/thunlp/UltraFeedback) for more details.
# Use Case
```python
ultracm_instruction_template = """Given my answer to an instruction, your role is to provide specific and constructive feedback for me. You should find the best way for me to learn from your feedback and improve my performance.
You should consider multiple aspects of my answer, including helpfulness, truthfulness, honesty, and to what extent the answer follows instructions.
---
### Instruction
{instruction}
### Answer
{completion}
---
Please act as a teacher and provide specific and constructive feedback. Besides describing the weaknesses of the answer, you should also provide specific suggestions to guide me toward understanding how to improve. Please note, however, that your suggestions should help me better complete the instructions, but you should not introduce new requirements that are not mentioned in the instructions. Your feedback should focus on enhancing my ability to think critically and respond accurately. However, never explicitly provide the reference answer, nor do polite phrases be required. Only respond with concise feedback in chat style. Finally, score the overall quality of the answer from 1 to 10, where 1 is the worst and 10 is the best.
*Format*
### Feedback
Overall Score: [1-10]
[Your feedback]
---
### Feedback
Overall Score:
"""
import pandas as pd
dataset = [
{"instruction":"What if the Beatles had never formed as a band?",
"completion":"The Beatles are widely credited with starting the British Invasion, a wave of rock and roll bands from the United Kingdom that became popular in America in the 1960s. If the Beatles had never formed, this musical movement may have never happened, and the world may have been exposed to a different kind of music. So, without the Beatles\u2019 fame and success, other bands wouldn\u2019t have been able to break into the American music scene and create a wider range of sounds. We could have ended up with a less interesting mix of songs playing on the radio."},
{"source":"fair_eval","instruction":"Given that f(x) = 5x^3 - 2x + 3, find the value of f(2).","completion":"The problem is asking us to find the value of the function f(x) = 5x^3 - 2x + 3 at the point x = 2. \n\nStep 1: Substitute x with 2 in the function\nWe replace every x in the function with 2. This gives us:\nf(2) = 5(2)^3 - 2(2) + 3\n\nStep 2: Simplify the expression\nNext, we simplify the expression by performing the operations in order from left to right.\n\nFirst, calculate the cube of 2, which is 8. Substitute this back into the expression:\nf(2) = 5(8) - 4 + 3\n\nThen, multiply 5 by 8 which gives us 40:\nf(2) = 40 - 4 + 3\n\nFinally, subtract 4 from 40 which gives us 36, and then add 3 to that:\nf(2) = 36 + 3\n\nStep 3: Final calculation\nNow, add 36 and 3 together:\nf(2) = 39\n\nSo, the value of the function f(x) = 5x^3 - 2x + 3 at the point x = 2 is 39."}
]
import torch
def generate_feedback(example):
system_prompt = "User: A one-turn chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, very detailed, and polite answers to the user's questions.</s>"
conv = [system_prompt]
conv.append("User: " + ultracm_instruction_template.format(
instruction=example["instruction"],
completion=example["completion"],
) + "</s>")
conv.append("Assistant: ")
prompt = "\n".join(conv)
with torch.no_grad():
response = generator(prompt, num_return_sequences=1, return_full_text=False, handle_long_generation="hole", temperature=1.0, top_p=1.0, max_new_tokens=1024, repetition_penalty=1.2, do_sample=True)
response = response[0]["generated_text"].strip("\n").strip()
print(response)
from transformers import pipeline, LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("openbmb/UltraCM-13b")
model = LlamaForCausalLM.from_pretrained("openbmb/UltraCM-13b", device_map="auto")
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
for example in dataset:
generate_feedback(example)
```
# Citation
```
@misc{cui2023ultrafeedback,
title={UltraFeedback: Boosting Language Models with High-quality Feedback},
author={Ganqu Cui and Lifan Yuan and Ning Ding and Guanming Yao and Wei Zhu and Yuan Ni and Guotong Xie and Zhiyuan Liu and Maosong Sun},
year={2023},
eprint={2310.01377},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
SudeepShetty/dogs
|
SudeepShetty
| 2023-10-14T09:43:33Z | 14 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-10-14T09:38:35Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### DOGS Dreambooth model trained by SudeepShetty following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: VCETV107
Sample pictures of this concept:
|
monsterapi/llama2_70B_dolly15k_mergedweights
|
monsterapi
| 2023-10-14T09:41:09Z | 0 | 0 |
peft
|
[
"peft",
"pytorch",
"llama",
"meta-llama",
"code",
"instruct",
"databricks-dolly-15k",
"Llama-2-70b-hf",
"dataset:databricks/databricks-dolly-15k",
"base_model:meta-llama/Llama-2-70b-hf",
"base_model:adapter:meta-llama/Llama-2-70b-hf",
"license:apache-2.0",
"region:us"
] | null | 2023-10-14T08:46:06Z |
---
library_name: peft
tags:
- meta-llama
- code
- instruct
- databricks-dolly-15k
- Llama-2-70b-hf
datasets:
- databricks/databricks-dolly-15k
base_model: meta-llama/Llama-2-70b-hf
license: apache-2.0
---
Note: This repo contains the base weights already merged with lora, pls check qblocks/llama2_70B_dolly15k repo for LORA adapters only
### Finetuning Overview:
**Model Used:** meta-llama/Llama-2-70b-hf
**Dataset:** Databricks-dolly-15k
#### Dataset Insights:
The Databricks-dolly-15k dataset is an impressive compilation of over 15,000 records, made possible by the hard work and dedication of a multitude of Databricks professionals. It has been tailored to:
- Elevate the interactive capabilities of ChatGPT-like systems.
- Provide prompt/response pairs spanning eight distinct instruction categories, inclusive of the seven categories from the InstructGPT paper and an exploratory open-ended category.
- Ensure genuine and original content, largely offline-sourced with exceptions for Wikipedia in particular categories, and free from generative AI influences.
The contributors had the opportunity to rephrase and answer queries from their peers, highlighting a focus on accuracy and clarity. Additionally, some data subsets feature Wikipedia-sourced reference texts, marked by bracketed citation numbers like [42].
#### Finetuning Details:
Using [MonsterAPI](https://monsterapi.ai)'s user-friendly [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm), the finetuning:
- Stands out for its cost-effectiveness.
- Was executed in a total of 17.5 hours for 3 epochs with an A100 80GB GPU.
- Broke down to just 5.8 hours and `$19.25` per epoch, culminating in a combined cost of `$57.75` for all epochs.
#### Hyperparameters & Additional Details:
- **Epochs:** 3
- **Cost Per Epoch:** $19.25
- **Total Finetuning Cost:** $57.75
- **Model Path:** meta-llama/Llama-2-70b-hf
- **Learning Rate:** 0.0002
- **Data Split:** Training 90% / Validation 10%
- **Gradient Accumulation Steps:** 4
---
### Prompt Structure:
```
### INSTRUCTION:
[instruction]
[context]
### RESPONSE:
[response]
```
Loss metrics
Training loss (Blue) Validation Loss (orange):
---
license: apache-2.0
|
pablopz/SourceFilterNeuralFormants
|
pablopz
| 2023-10-14T09:36:05Z | 0 | 0 | null |
[
"license:mit",
"region:us"
] | null | 2023-09-28T09:02:21Z |
---
license: mit
---
[repo_link]: https://github.com/ljuvela/SourceFilterNeuralFormants
## Neural Formant synthesis with source-filter model structure.
This repository contains pretrained models for the project presented in [this repository][repo_link].
Instructions on how to use them can be found there.
|
caroagse/recommender-excercise
|
caroagse
| 2023-10-14T09:32:22Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-09T21:11:38Z |
---
tags:
- generated_from_trainer
model-index:
- name: recommender-excercise
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. -->
# recommender-excercise
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
## 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: 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
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0.67 | 1 | nan |
| No log | 1.33 | 2 | nan |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
Dijaaa/videomae-base-finetuned-ucf_crime2
|
Dijaaa
| 2023-10-14T09:16:14Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"videomae",
"video-classification",
"generated_from_trainer",
"base_model:MCG-NJU/videomae-base",
"base_model:finetune:MCG-NJU/videomae-base",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
video-classification
| 2023-09-28T11:23:04Z |
---
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf_crime2
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. -->
# videomae-base-finetuned-ucf_crime2
This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1449
- Accuracy: 0.2689
## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 504
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.3843 | 0.17 | 85 | 2.5040 | 0.1662 |
| 2.2227 | 1.17 | 170 | 2.3376 | 0.1935 |
| 2.1317 | 2.17 | 255 | 2.2547 | 0.2329 |
| 2.0338 | 3.17 | 340 | 2.1470 | 0.2485 |
| 1.9639 | 4.17 | 425 | 2.0700 | 0.2558 |
| 1.8565 | 5.16 | 504 | 2.0882 | 0.2625 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
|
waboucay/xlm-roberta-longformer-base-4096-rua_wl_3_classes
|
waboucay
| 2023-10-14T09:13:05Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"nli",
"fr",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T09:11:04Z |
---
language:
- fr
tags:
- nli
metrics:
- f1
---
## Eval results
We obtain the following results on ```validation``` and ```test``` sets:
| Set | F1<sub>micro</sub> | F1<sub>macro</sub> |
|------------|--------------------|--------------------|
| validation | 70.7 | 70.3 |
| test | 71.1 | 70.7 |
|
facebook/metaclip-l14-fullcc2.5b
|
facebook
| 2023-10-14T09:05:13Z | 516 | 3 |
transformers
|
[
"transformers",
"pytorch",
"clip",
"zero-shot-image-classification",
"vision",
"metaclip",
"arxiv:2309.16671",
"arxiv:2103.00020",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
zero-shot-image-classification
| 2023-10-09T21:16:27Z |
---
license: cc-by-nc-4.0
tags:
- vision
- metaclip
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
candidate_labels: playing music, playing sports
example_title: Cat & Dog
---
# MetaCLIP model, large-sized version, patch resolution 14
MetaCLIP model applied to 2.5 billion data points of CommonCrawl (CC). It was introduced in the paper [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) by Xu et al. and first released in [this repository](https://github.com/facebookresearch/MetaCLIP).
Disclaimer: The team releasing MetaCLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) paper aims to reveal CLIP’s method around training data curation. OpenAI never open-sourced code regarding their data preparation pipeline.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/clip_overview.jpg"
alt="drawing" width="600"/>
<small> CLIP high-level overview. Taken from the <a href="https://arxiv.org/abs/2103.00020">CLIP paper</a>. </small>
## Intended uses & limitations
You can use the raw model for linking images with text in a shared embedding space. This enables things like zero-shot image classification, text-based image retrieval, image-based text retrieval, etc.
### How to use
We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/clip#usage). Just replace the names of the models on the hub.
### BibTeX entry and citation info
```bibtex
@misc{xu2023demystifying,
title={Demystifying CLIP Data},
author={Hu Xu and Saining Xie and Xiaoqing Ellen Tan and Po-Yao Huang and Russell Howes and Vasu Sharma and Shang-Wen Li and Gargi Ghosh and Luke Zettlemoyer and Christoph Feichtenhofer},
year={2023},
eprint={2309.16671},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
facebook/metaclip-b16-400m
|
facebook
| 2023-10-14T09:03:32Z | 44 | 1 |
transformers
|
[
"transformers",
"pytorch",
"clip",
"zero-shot-image-classification",
"vision",
"metaclip",
"arxiv:2309.16671",
"arxiv:2103.00020",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
zero-shot-image-classification
| 2023-10-09T20:48:52Z |
---
license: cc-by-nc-4.0
tags:
- vision
- metaclip
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
candidate_labels: playing music, playing sports
example_title: Cat & Dog
---
# MetaCLIP model, base-sized version, patch resolution 16
MetaCLIP model applied to 400 million data points of CommonCrawl (CC). It was introduced in the paper [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) by Xu et al. and first released in [this repository](https://github.com/facebookresearch/MetaCLIP).
Disclaimer: The team releasing MetaCLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The [Demystifying CLIP Data](https://arxiv.org/abs/2309.16671) paper aims to reveal CLIP’s method around training data curation. OpenAI never open-sourced code regarding their data preparation pipeline.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/clip_overview.jpg"
alt="drawing" width="600"/>
<small> CLIP high-level overview. Taken from the <a href="https://arxiv.org/abs/2103.00020">CLIP paper</a>. </small>
## Intended uses & limitations
You can use the raw model for linking images with text in a shared embedding space. This enables things like zero-shot image classification, text-based image retrieval, image-based text retrieval, etc.
### How to use
We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/clip#usage). Just replace the names of the models on the hub.
### BibTeX entry and citation info
```bibtex
@misc{xu2023demystifying,
title={Demystifying CLIP Data},
author={Hu Xu and Saining Xie and Xiaoqing Ellen Tan and Po-Yao Huang and Russell Howes and Vasu Sharma and Shang-Wen Li and Gargi Ghosh and Luke Zettlemoyer and Christoph Feichtenhofer},
year={2023},
eprint={2309.16671},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
|
zeeshanparvez/bert-finetuned-squad
|
zeeshanparvez
| 2023-10-14T08:53:07Z | 3 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"question-answering",
"generated_from_keras_callback",
"base_model:google-bert/bert-base-cased",
"base_model:finetune:google-bert/bert-base-cased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-10-13T21:51:56Z |
---
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_keras_callback
model-index:
- name: zeeshanparvez/bert-finetuned-squad
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. -->
# zeeshanparvez/bert-finetuned-squad
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.1590
- Epoch: 2
## 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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 39897, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
### Training results
| Train Loss | Epoch |
|:----------:|:-----:|
| 2.6892 | 0 |
| 2.2982 | 1 |
| 2.1590 | 2 |
### Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
|
nguynking/videberta-xsmall-lora-nli-checkpoint-2
|
nguynking
| 2023-10-14T08:34:33Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:nguynking/videberta-xsmall-nli-1",
"base_model:adapter:nguynking/videberta-xsmall-nli-1",
"region:us"
] | null | 2023-10-14T08:34:32Z |
---
library_name: peft
base_model: nguynking/videberta-xsmall-nli-1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
pfunk/PongNoFrameskip-v4-DQPN_DQN-seed2
|
pfunk
| 2023-10-14T08:14:52Z | 0 | 0 |
cleanrl
|
[
"cleanrl",
"tensorboard",
"PongNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T08:14:46Z |
---
tags:
- PongNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQPN_freq
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PongNoFrameskip-v4
type: PongNoFrameskip-v4
metrics:
- type: mean_reward
value: 19.21 +/- 0.00
name: mean_reward
verified: false
---
# (CleanRL) **DQPN_freq** Agent Playing **PongNoFrameskip-v4**
This is a trained model of a DQPN_freq agent playing PongNoFrameskip-v4.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/DQPN_DQN.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[DQPN_DQN]"
python -m cleanrl_utils.enjoy --exp-name DQPN_DQN --env-id PongNoFrameskip-v4
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_DQN-seed2/raw/main/dqpn_freq_atari.py
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_DQN-seed2/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_DQN-seed2/raw/main/poetry.lock
poetry install --all-extras
python dqpn_freq_atari.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name DQPN_DQN --target-network-frequency 1000 --policy-network-frequency 1 --seed 2
```
# Hyperparameters
```python
{'alg_type': 'dqpn_freq_atari.py',
'batch_size': 32,
'buffer_size': 1000000,
'capture_video': True,
'cuda': True,
'double_learning': False,
'end_e': 0.05,
'env_id': 'PongNoFrameskip-v4',
'exp_name': 'DQPN_DQN',
'exploration_fraction': 0.2,
'gamma': 0.99,
'hf_entity': 'pfunk',
'learning_rate': 0.0001,
'learning_starts': 10000,
'max_gradient_norm': inf,
'policy_network_frequency': 1,
'policy_tau': 1.0,
'save_model': True,
'seed': 2,
'start_e': 1.0,
'target_network_frequency': 1000,
'target_tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 10000000,
'track': True,
'train_frequency': 1,
'upload_model': True,
'wandb_entity': 'pfunk',
'wandb_project_name': 'dqpn'}
```
|
MattStammers/appo-atari_privateye
|
MattStammers
| 2023-10-14T08:13:59Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-26T21:49:25Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: atari_privateye
type: atari_privateye
metrics:
- type: mean_reward
value: 100.00 +/- 0.00
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **atari_privateye** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-atari_privateye
```
## About the Model
This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it.
The aim is to reach state-of-the-art (SOTA) performance on each atari environment. I will flag the models with SOTA when they reach at or near these levels.
The hyperparameters used in the model are the ones I have pushed to my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his.
I saved time and energy by using many of his tuned hyperparameters to maximise performance. However, he used 2 billion training steps. I have started as explained above at 10 million then moved to 100m to see how performance goes:
```
hyperparameters = {
"device": "gpu",
"seed": 1234,
"num_policies": 2,
"async_rl": true,
"serial_mode": false,
"batched_sampling": true,
"num_batches_to_accumulate": 2,
"worker_num_splits": 1,
"policy_workers_per_policy": 1,
"max_policy_lag": 1000,
"num_workers": 16,
"num_envs_per_worker": 2,
"batch_size": 1024,
"num_batches_per_epoch": 8,
"num_epochs": 4,
"rollout": 128,
"recurrence": 1,
"shuffle_minibatches": false,
"gamma": 0.99,
"reward_scale": 1.0,
"reward_clip": 1000.0,
"value_bootstrap": false,
"normalize_returns": true,
"exploration_loss_coeff": 0.0004677351413,
"value_loss_coeff": 0.5,
"kl_loss_coeff": 0.0,
"exploration_loss": "entropy",
"gae_lambda": 0.95,
"ppo_clip_ratio": 0.1,
"ppo_clip_value": 1.0,
"with_vtrace": false,
"vtrace_rho": 1.0,
"vtrace_c": 1.0,
"optimizer": "adam",
"adam_eps": 1e-05,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"max_grad_norm": 0.0,
"learning_rate": 0.0003033891184,
"lr_schedule": "linear_decay",
"lr_schedule_kl_threshold": 0.008,
"lr_adaptive_min": 1e-06,
"lr_adaptive_max": 0.01,
"obs_subtract_mean": 0.0,
"obs_scale": 255.0,
"normalize_input": true,
"normalize_input_keys": [
"obs"
],
"decorrelate_experience_max_seconds": 0,
"decorrelate_envs_on_one_worker": true,
"actor_worker_gpus": [],
"set_workers_cpu_affinity": true,
"force_envs_single_thread": false,
"default_niceness": 0,
"log_to_file": true,
"experiment_summaries_interval": 3,
"flush_summaries_interval": 30,
"stats_avg": 100,
"summaries_use_frameskip": true,
"heartbeat_interval": 10,
"heartbeat_reporting_interval": 60,
"train_for_env_steps": 100000000,
"train_for_seconds": 10000000000,
"save_every_sec": 120,
"keep_checkpoints": 2,
"load_checkpoint_kind": "latest",
"save_milestones_sec": 1200,
"save_best_every_sec": 5,
"save_best_metric": "reward",
"save_best_after": 100000,
"benchmark": false,
"encoder_mlp_layers": [
512,
512
],
"encoder_conv_architecture": "convnet_atari",
"encoder_conv_mlp_layers": [
512
],
"use_rnn": false,
"rnn_size": 512,
"rnn_type": "gru",
"rnn_num_layers": 1,
"decoder_mlp_layers": [],
"nonlinearity": "relu",
"policy_initialization": "orthogonal",
"policy_init_gain": 1.0,
"actor_critic_share_weights": true,
"adaptive_stddev": false,
"continuous_tanh_scale": 0.0,
"initial_stddev": 1.0,
"use_env_info_cache": false,
"env_gpu_actions": false,
"env_gpu_observations": true,
"env_frameskip": 4,
"env_framestack": 4,
}
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m sf_examples.atari.enjoy_atari --algo=APPO --env=atari_privateye --train_dir=./train_dir --experiment=APPO-atari_privateye
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m sf_examples.atari.train_atari --algo=APPO --env=atari_privateye --train_dir=./train_dir --experiment=APPO-atari_privateye --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
lst-nectec/HoogBERTa
|
lst-nectec
| 2023-10-14T08:08:33Z | 576 | 3 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"roberta",
"fill-mask",
"th",
"dataset:best2009",
"dataset:scb_mt_enth_2020",
"dataset:oscar",
"dataset:wikipedia",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-03-31T14:48:36Z |
---
license: mit
datasets:
- best2009
- scb_mt_enth_2020
- oscar
- wikipedia
language:
- th
widget:
- text: วัน ที่ _ 12 _ มีนาคม นี้ _ ฉัน จะ ไป <mask> วัดพระแก้ว _ ที่ กรุงเทพ
library_name: transformers
---
# HoogBERTa
This repository includes the Thai pretrained language representation (HoogBERTa_base) and can be used for **Feature Extraction and Masked Language Modeling Tasks**.
# Documentation
## Prerequisite
Since we use subword-nmt BPE encoding, input needs to be pre-tokenize using [BEST](https://huggingface.co/datasets/best2009) standard before inputting into HoogBERTa
```
pip install attacut
```
## Getting Start
To initialize the model from hub, use the following commands
```python
from transformers import AutoTokenizer, AutoModel
from attacut import tokenize
import torch
tokenizer = AutoTokenizer.from_pretrained("lst-nectec/HoogBERTa")
model = AutoModel.from_pretrained("lst-nectec/HoogBERTa")
```
To extract token features, based on the RoBERTa architecture, use the following commands
```python
model.eval()
sentence = "วันที่ 12 มีนาคมนี้ ฉันจะไปเที่ยววัดพระแก้ว ที่กรุงเทพ"
all_sent = []
sentences = sentence.split(" ")
for sent in sentences:
all_sent.append(" ".join(tokenize(sent)).replace("_","[!und:]"))
sentence = " _ ".join(all_sent)
tokenized_text = tokenizer(sentence, return_tensors = 'pt')
token_ids = tokenized_text['input_ids']
with torch.no_grad():
features = model(**tokenized_text, output_hidden_states = True).hidden_states[-1]
```
For batch processing,
```python
model.eval()
sentenceL = ["วันที่ 12 มีนาคมนี้","ฉันจะไปเที่ยววัดพระแก้ว ที่กรุงเทพ"]
inputList = []
for sentX in sentenceL:
sentences = sentX.split(" ")
all_sent = []
for sent in sentences:
all_sent.append(" ".join(tokenize(sent)).replace("_","[!und:]"))
sentence = " _ ".join(all_sent)
inputList.append(sentence)
tokenized_text = tokenizer(inputList, padding = True, return_tensors = 'pt')
token_ids = tokenized_text['input_ids']
with torch.no_grad():
features = model(**tokenized_text, output_hidden_states = True).hidden_states[-1]
```
To use HoogBERTa as an embedding layer, use
```python
with torch.no_grad():
features = model(token_ids, output_hidden_states = True).hidden_states[-1] # where token_ids is a tensor with type "long".
```
# Huggingface Models
1. `HoogBERTaEncoder`
- [HoogBERTa](https://huggingface.co/lst-nectec/HoogBERTa): `Feature Extraction` and `Mask Language Modeling`
2. `HoogBERTaMuliTaskTagger`:
- [HoogBERTa-NER-lst20](https://huggingface.co/lst-nectec/HoogBERTa-NER-lst20): `Named-entity recognition (NER)` based on LST20
- [HoogBERTa-POS-lst20](https://huggingface.co/lst-nectec/HoogBERTa-POS-lst20): `Part-of-speech tagging (POS)` based on LST20
- [HoogBERTa-SENTENCE-lst20](https://huggingface.co/lst-nectec/HoogBERTa-SENTENCE-lst20): `Clause Boundary Classification` based on LST20
# Citation
Please cite as:
``` bibtex
@inproceedings{porkaew2021hoogberta,
title = {HoogBERTa: Multi-task Sequence Labeling using Thai Pretrained Language Representation},
author = {Peerachet Porkaew, Prachya Boonkwan and Thepchai Supnithi},
booktitle = {The Joint International Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP 2021)},
year = {2021},
address={Online}
}
```
Download full-text [PDF](https://drive.google.com/file/d/1hwdyIssR5U_knhPE2HJigrc0rlkqWeLF/view?usp=sharing)
Check out the code on [Github](https://github.com/lstnlp/HoogBERTa)
|
Leeyuyu/swin-tiny-patch4-window7-224-finetunedo
|
Leeyuyu
| 2023-10-14T07:47:14Z | 33 | 0 |
transformers
|
[
"transformers",
"pytorch",
"swin",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:microsoft/swin-tiny-patch4-window7-224",
"base_model:finetune:microsoft/swin-tiny-patch4-window7-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-10-13T23:25:22Z |
---
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: swin-tiny-patch4-window7-224-finetunedo
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. -->
# swin-tiny-patch4-window7-224-finetunedo
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3710
- Roc Auc: 0.8606
## 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: 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: 0.1
- num_epochs: 8
### Training results
| Training Loss | Epoch | Step | Validation Loss | Roc Auc |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log | 1.0 | 3 | 0.5066 | 0.7647 |
| No log | 2.0 | 6 | 0.4204 | 0.7941 |
| No log | 3.0 | 9 | 0.4298 | 0.7353 |
| 0.4868 | 4.0 | 12 | 0.4040 | 0.8018 |
| 0.4868 | 5.0 | 15 | 0.3925 | 0.7724 |
| 0.4868 | 6.0 | 18 | 0.3674 | 0.8235 |
| 0.4096 | 7.0 | 21 | 0.3673 | 0.8606 |
| 0.4096 | 8.0 | 24 | 0.3710 | 0.8606 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
LeighMiller/sentiment-analysis-simple-demo-model
|
LeighMiller
| 2023-10-14T06:45:27Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:imdb",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-10-14T04:28:44Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- imdb
metrics:
- accuracy
- f1
model-index:
- name: sentiment-analysis-simple-demo-model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: imdb
type: imdb
config: plain_text
split: test
args: plain_text
metrics:
- name: Accuracy
type: accuracy
value: 0.904
- name: F1
type: f1
value: 0.9024390243902438
---
<!-- 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. -->
# sentiment-analysis-simple-demo-model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2508
- Accuracy: 0.904
- F1: 0.9024
## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
|
cys/a2c-PandaReachDense-v3
|
cys
| 2023-10-14T06:39:26Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T06:34:01Z |
---
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: -0.23 +/- 0.06
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
...
```
|
parasora/phi-1_5-JCommon-ft
|
parasora
| 2023-10-14T06:07:29Z | 1 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:microsoft/phi-1_5",
"base_model:adapter:microsoft/phi-1_5",
"region:us"
] | null | 2023-10-14T06:07:08Z |
---
library_name: peft
base_model: microsoft/phi-1_5
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
mmnga/debug
|
mmnga
| 2023-10-14T05:34:30Z | 0 | 0 | null |
[
"license:unknown",
"region:us"
] | null | 2023-10-03T14:11:13Z |
---
license: unknown
---
# このリポジトリはmmngaのDebug用のリポジトリです (This Repo is mmnga's DebugRepo.)
**検証用のモデル置き場です。正しく動作しないものがあります。**
|
pawanNLP123/llama2-qlora-finetunined-french
|
pawanNLP123
| 2023-10-14T05:31:22Z | 0 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:TinyPixel/Llama-2-7B-bf16-sharded",
"base_model:adapter:TinyPixel/Llama-2-7B-bf16-sharded",
"region:us"
] | null | 2023-10-14T05:31:04Z |
---
library_name: peft
base_model: TinyPixel/Llama-2-7B-bf16-sharded
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## 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
### Framework versions
- PEFT 0.6.0.dev0
|
if001/llama2_ja_small
|
if001
| 2023-10-14T04:50:54Z | 5 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"llama-2",
"ja",
"en",
"license:cc-by-4.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-10-11T09:11:41Z |
---
license: cc-by-4.0
language:
- ja
- en
pipeline_tag: text-generation
inference: false
tags:
- llama-2
---
日本語でtrainingしたllama2
model size: 417.12M
trainingは以下のscript参照
https://github.com/Lightning-AI/lit-gpt/tree/main
## use
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("if001/sentencepiece_ja", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("if001/llama2_ja_small")
import torch
from transformers import GenerationConfig
prompt="あのイーハトーヴォのすきとおった風、"
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"]
generation_config = GenerationConfig(
temperature=0.8,
top_p=0.95,
top_k=50,
num_beams=1,
do_sample=True,
repetition_penalty=1.2,
pad_token_id= tokenizer.pad_token_id,
# pad_token_id=tokenizer.unk_token_id,
eos_token_id=tokenizer.eos_token_id
)
with torch.no_grad():
generation_output = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=64,
)
s = generation_output.sequences[0]
output = tokenizer.decode(s)
print(output)
> あの イ ー ハ トー ヴォ の すき と おった 風 、 人の 声 とも 似 あ わぬ 歌 である 。 この 音楽 が われわれ を 最も 愛 し むる 時に その 音楽 は 「 われ 」 に 勝 るもの となった のである 。
```
## dataset
英語と日本語のデータセットを使用
```
total tokens: 8.64B
wikipedia_ja: 844.65M
wikipedia_en: 3.80B
open-text-books: 60.17M
oscar: 3.85B
aozorabunko: 92.97M
```
https://huggingface.co/datasets/izumi-lab/wikipedia-ja-20230720
https://huggingface.co/datasets/izumi-lab/wikipedia-en-20230720
https://huggingface.co/datasets/izumi-lab/open-text-books
https://huggingface.co/datasets/if001/aozorabunko-clean-sin
https://huggingface.co/datasets/if001/oscar_2023_filtered
|
surajp/Mistral-7B-Instruct-v01-qlora-numerai-1epoch
|
surajp
| 2023-10-14T04:28:07Z | 1 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:mistralai/Mistral-7B-Instruct-v0.1",
"base_model:adapter:mistralai/Mistral-7B-Instruct-v0.1",
"region:us"
] | null | 2023-10-14T04:28:00Z |
---
library_name: peft
base_model: mistralai/Mistral-7B-Instruct-v0.1
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## 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]
## 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
## 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
|
yesj1234/xlsr_mid_en-k_1
|
yesj1234
| 2023-10-14T03:46:33Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"./sample_speech.py",
"generated_from_trainer",
"base_model:facebook/wav2vec2-large-xlsr-53",
"base_model:finetune:facebook/wav2vec2-large-xlsr-53",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-14T03:42:18Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- automatic-speech-recognition
- ./sample_speech.py
- generated_from_trainer
metrics:
- wer
model-index:
- name: en-xlsr
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. -->
# en-xlsr
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ./SAMPLE_SPEECH.PY - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4835
- Cer: 0.1119
- Wer: 0.2446
## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 2.9534 | 0.22 | 100 | 2.9533 | 1.0 | 1.0 |
| 2.933 | 0.44 | 200 | 2.9231 | 1.0 | 1.0 |
| 2.904 | 0.65 | 300 | 2.8851 | 1.0 | 1.0 |
| 2.3607 | 0.87 | 400 | 2.1546 | 0.6799 | 0.9976 |
| 1.1725 | 1.09 | 500 | 0.9899 | 0.2665 | 0.6191 |
| 0.9865 | 1.31 | 600 | 0.8060 | 0.2126 | 0.5064 |
| 0.8959 | 1.53 | 700 | 0.7131 | 0.1980 | 0.4607 |
| 0.7743 | 1.74 | 800 | 0.6663 | 0.1799 | 0.4370 |
| 0.7805 | 1.96 | 900 | 0.6159 | 0.1683 | 0.3997 |
| 0.6562 | 2.18 | 1000 | 0.6186 | 0.1537 | 0.3705 |
| 0.6223 | 2.4 | 1100 | 0.5698 | 0.1496 | 0.3552 |
| 0.5627 | 2.62 | 1200 | 0.5555 | 0.1446 | 0.3372 |
| 0.5476 | 2.84 | 1300 | 0.5435 | 0.1416 | 0.3307 |
| 0.5002 | 3.05 | 1400 | 0.5304 | 0.1436 | 0.3393 |
| 0.5174 | 3.27 | 1500 | 0.5377 | 0.1485 | 0.3357 |
| 0.4745 | 3.49 | 1600 | 0.5289 | 0.1340 | 0.3132 |
| 0.5239 | 3.71 | 1700 | 0.5112 | 0.1395 | 0.3239 |
| 0.5115 | 3.93 | 1800 | 0.5079 | 0.1342 | 0.3094 |
| 0.4471 | 4.14 | 1900 | 0.5131 | 0.1301 | 0.2965 |
| 0.4455 | 4.36 | 2000 | 0.5015 | 0.1278 | 0.2931 |
| 0.4199 | 4.58 | 2100 | 0.4954 | 0.1299 | 0.2962 |
| 0.4699 | 4.8 | 2200 | 0.4827 | 0.1268 | 0.2890 |
| 0.3521 | 5.02 | 2300 | 0.4857 | 0.1217 | 0.2782 |
| 0.3976 | 5.23 | 2400 | 0.4936 | 0.1231 | 0.2802 |
| 0.365 | 5.45 | 2500 | 0.4906 | 0.1221 | 0.2774 |
| 0.3857 | 5.67 | 2600 | 0.4843 | 0.1202 | 0.2757 |
| 0.3578 | 5.89 | 2700 | 0.4857 | 0.1196 | 0.2708 |
| 0.3298 | 6.11 | 2800 | 0.4867 | 0.1197 | 0.2689 |
| 0.3099 | 6.32 | 2900 | 0.4924 | 0.1237 | 0.2770 |
| 0.3606 | 6.54 | 3000 | 0.4851 | 0.1189 | 0.2684 |
| 0.3807 | 6.76 | 3100 | 0.4700 | 0.1196 | 0.2656 |
| 0.3286 | 6.98 | 3200 | 0.4770 | 0.1205 | 0.2730 |
| 0.3318 | 7.2 | 3300 | 0.4845 | 0.1166 | 0.2579 |
| 0.2936 | 7.42 | 3400 | 0.4909 | 0.1159 | 0.2570 |
| 0.3119 | 7.63 | 3500 | 0.4899 | 0.1150 | 0.2539 |
| 0.3142 | 7.85 | 3600 | 0.4782 | 0.1143 | 0.2550 |
| 0.2935 | 8.07 | 3700 | 0.4885 | 0.1153 | 0.2527 |
| 0.2805 | 8.29 | 3800 | 0.4906 | 0.1143 | 0.2529 |
| 0.254 | 8.51 | 3900 | 0.4822 | 0.1144 | 0.2538 |
| 0.2855 | 8.72 | 4000 | 0.4852 | 0.1123 | 0.2476 |
| 0.2661 | 8.94 | 4100 | 0.4847 | 0.1132 | 0.2496 |
| 0.2524 | 9.16 | 4200 | 0.4900 | 0.1116 | 0.2442 |
| 0.253 | 9.38 | 4300 | 0.4888 | 0.1120 | 0.2458 |
| 0.2591 | 9.6 | 4400 | 0.4813 | 0.1125 | 0.2458 |
| 0.2583 | 9.81 | 4500 | 0.4844 | 0.1114 | 0.2435 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
luffycodes/llama-shishya-7b-ep3-v2
|
luffycodes
| 2023-10-14T03:15:37Z | 1,480 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"arxiv:2305.13272",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T03:05:35Z |
---
license: llama2
---
Student model using the CLASS framework.
If you use this work, please cite:
CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles
https://arxiv.org/abs/2305.13272
```
@misc{sonkar2023class,
title={CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles},
author={Shashank Sonkar and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk},
year={2023},
eprint={2305.13272},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
redrusa/lora-flan-t5-large-chat
|
redrusa
| 2023-10-14T03:11:40Z | 21 | 0 |
peft
|
[
"peft",
"pytorch",
"t5",
"region:us"
] | null | 2023-10-12T06:40:02Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
rubenadad/ppo-LunarLander-v2
|
rubenadad
| 2023-10-14T02:36:52Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T02:36:32Z |
---
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: 269.37 +/- 19.27
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
...
```
|
pfunk/PongNoFrameskip-v4-DQPN_x5-seed2
|
pfunk
| 2023-10-14T02:30:52Z | 0 | 0 |
cleanrl
|
[
"cleanrl",
"tensorboard",
"PongNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T02:30:46Z |
---
tags:
- PongNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: DQPN_freq
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PongNoFrameskip-v4
type: PongNoFrameskip-v4
metrics:
- type: mean_reward
value: 19.01 +/- 0.00
name: mean_reward
verified: false
---
# (CleanRL) **DQPN_freq** Agent Playing **PongNoFrameskip-v4**
This is a trained model of a DQPN_freq agent playing PongNoFrameskip-v4.
The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be
found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/DQPN_x5.py).
## Get Started
To use this model, please install the `cleanrl` package with the following command:
```
pip install "cleanrl[DQPN_x5]"
python -m cleanrl_utils.enjoy --exp-name DQPN_x5 --env-id PongNoFrameskip-v4
```
Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail.
## Command to reproduce the training
```bash
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_x5-seed2/raw/main/dqpn_freq_atari.py
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_x5-seed2/raw/main/pyproject.toml
curl -OL https://huggingface.co/pfunk/PongNoFrameskip-v4-DQPN_x5-seed2/raw/main/poetry.lock
poetry install --all-extras
python dqpn_freq_atari.py --track --wandb-entity pfunk --wandb-project-name dqpn --capture-video true --save-model true --upload-model true --hf-entity pfunk --exp-name DQPN_x5 --target-network-frequency 1000 --policy-network-frequency 5000 --seed 2
```
# Hyperparameters
```python
{'alg_type': 'dqpn_freq_atari.py',
'batch_size': 32,
'buffer_size': 1000000,
'capture_video': True,
'cuda': True,
'double_learning': False,
'end_e': 0.05,
'env_id': 'PongNoFrameskip-v4',
'exp_name': 'DQPN_x5',
'exploration_fraction': 0.2,
'gamma': 0.99,
'hf_entity': 'pfunk',
'learning_rate': 0.0001,
'learning_starts': 10000,
'max_gradient_norm': inf,
'policy_network_frequency': 5000,
'policy_tau': 1.0,
'save_model': True,
'seed': 2,
'start_e': 1.0,
'target_network_frequency': 1000,
'target_tau': 1.0,
'torch_deterministic': True,
'total_timesteps': 10000000,
'track': True,
'train_frequency': 1,
'upload_model': True,
'wandb_entity': 'pfunk',
'wandb_project_name': 'dqpn'}
```
|
kkt4828/distilbert-base-uncased-issues-128
|
kkt4828
| 2023-10-14T01:46:18Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"fill-mask",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-10-14T00:34:27Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-issues-128
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-issues-128
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2728
## 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: 16
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2526 | 1.0 | 292 | 1.8647 |
| 1.7421 | 2.0 | 584 | 1.6379 |
| 1.5862 | 3.0 | 876 | 1.5838 |
| 1.5041 | 4.0 | 1168 | 1.5427 |
| 1.4371 | 5.0 | 1460 | 1.4806 |
| 1.3826 | 6.0 | 1752 | 1.3648 |
| 1.3487 | 7.0 | 2044 | 1.4458 |
| 1.3292 | 8.0 | 2336 | 1.3345 |
| 1.2779 | 9.0 | 2628 | 1.3367 |
| 1.2599 | 10.0 | 2920 | 1.3373 |
| 1.2454 | 11.0 | 3212 | 1.3694 |
| 1.2239 | 12.0 | 3504 | 1.2550 |
| 1.2057 | 13.0 | 3796 | 1.3154 |
| 1.1792 | 14.0 | 4088 | 1.2952 |
| 1.1838 | 15.0 | 4380 | 1.3406 |
| 1.1739 | 16.0 | 4672 | 1.2728 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
|
rfanucchi/taxi_v10
|
rfanucchi
| 2023-10-14T01:36:38Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T01:06:26Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi_v10
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: -158.43 +/- 277.67
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="rfanucchi/taxi_v10", 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"])
```
|
zeerakwyne/dreambooth_lora_model_test
|
zeerakwyne
| 2023-10-14T01:04:16Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-10-14T01:02:58Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - zeerakwyne/dreambooth_lora_model_test
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
DeGra/RACLETTE-v.0
|
DeGra
| 2023-10-14T00:58:15Z | 0 | 0 | null |
[
"text-generation",
"license:afl-3.0",
"region:us"
] |
text-generation
| 2023-10-11T13:07:42Z |
---
license: afl-3.0
pipeline_tag: text-generation
---
**RACLETTE** - "**R**esponsive **A**nalysis of **C**hatbot **L**LMs for **E**motional and **T**herapeutic **T**racking and **E**valuation"
-Finetuned from [someone13574/Mistral-7B-v0.1-sharded](https://huggingface.co/someone13574/Mistral-7B-v0.1-sharded), a sharded version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
-Using [empathetic_dialogues dataset](https://huggingface.co/datasets/empathetic_dialogues)
|
agoel3705/q-FrozenLake-v1-4x4-noSlippery
|
agoel3705
| 2023-10-14T00:39:28Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-14T00:39:26Z |
---
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="agoel3705/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"])
```
|
malanevans/poca-SoccerTwos
|
malanevans
| 2023-10-14T00:36:14Z | 42 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-10-14T00:34:08Z |
---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
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: malanevans/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
luffycodes/llama-shishya-7b-ep3-v1
|
luffycodes
| 2023-10-14T00:33:41Z | 1,477 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"arxiv:2305.13272",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-10-14T00:23:56Z |
---
license: llama2
---
Student model using the CLASS framework.
If you use this work, please cite:
CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles
https://arxiv.org/abs/2305.13272
```
@misc{sonkar2023class,
title={CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles},
author={Shashank Sonkar and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk},
year={2023},
eprint={2305.13272},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
beatrice-yap/wav2vec2-base-nsc-demo-2
|
beatrice-yap
| 2023-10-13T23:35:40Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:facebook/wav2vec2-base-960h",
"base_model:finetune:facebook/wav2vec2-base-960h",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-10-13T23:35:16Z |
---
license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-nsc-demo-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. -->
# wav2vec2-base-nsc-demo-2
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7769
- Wer: 0.2568
## 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: 32
- 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: 1000
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.95 | 6.67 | 20 | 1.0674 | 0.3160 |
| 0.6587 | 13.33 | 40 | 0.9156 | 0.2864 |
| 0.5063 | 20.0 | 60 | 0.8279 | 0.2741 |
| 0.3928 | 26.67 | 80 | 0.7769 | 0.2568 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
WIS/Cartpole-v1
|
WIS
| 2023-10-13T23:30:43Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T23:30:34Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Cartpole-v1
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
|
damienbenveniste/gpt2_clm-model
|
damienbenveniste
| 2023-10-13T22:47:09Z | 5 | 1 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"generated_from_trainer",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | null | 2023-10-13T00:21:36Z |
---
tags:
- generated_from_trainer
model-index:
- name: gpt2_clm-model
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. -->
# gpt2_clm-model
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 10.9617
## 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 3 | 10.9628 |
| No log | 2.0 | 6 | 10.9620 |
| No log | 3.0 | 9 | 10.9617 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
adidutt/ppo-LunarLander-v2
|
adidutt
| 2023-10-13T22:38:05Z | 1 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T22:00:30Z |
---
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: 249.38 +/- 22.65
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
...
```
|
rfanucchi/Taxi_reinforcementelearning_course_8
|
rfanucchi
| 2023-10-13T22:27:04Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T21:52:10Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi_reinforcementelearning_course_8
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="rfanucchi/Taxi_reinforcementelearning_course_8", 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"])
```
|
jamiealexandre/mpnet
|
jamiealexandre
| 2023-10-13T22:21:00Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"xlm-roberta",
"feature-extraction",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2023-10-13T22:07:05Z |
---
pipeline_tag: feature-extraction
---
|
MoeenTB/a2c-PandaReachDense-v3
|
MoeenTB
| 2023-10-13T22:19:19Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T22:13:49Z |
---
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: -0.24 +/- 0.10
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
...
```
|
RazinAleks/working
|
RazinAleks
| 2023-10-13T22:14:55Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:RazinAleks/working",
"base_model:finetune:RazinAleks/working",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-10-12T16:54:27Z |
---
license: apache-2.0
base_model: RazinAleks/working
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: working
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. -->
# working
This model is a fine-tuned version of [RazinAleks/working](https://huggingface.co/RazinAleks/working) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2209
- Rouge1: 0.0485
- Rouge2: 0.0137
- Rougel: 0.0481
- Rougelsum: 0.0484
- Gen Len: 17.5748
## 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| 4.267 | 1.0 | 938 | 3.3590 | 0.0423 | 0.0117 | 0.042 | 0.0421 | 17.3022 |
| 3.9878 | 2.0 | 1876 | 3.2691 | 0.0437 | 0.0116 | 0.0435 | 0.0437 | 17.3476 |
| 3.9117 | 3.0 | 2814 | 3.2318 | 0.0483 | 0.014 | 0.0479 | 0.0481 | 17.61 |
| 3.8808 | 4.0 | 3752 | 3.2209 | 0.0485 | 0.0137 | 0.0481 | 0.0484 | 17.5748 |
### Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
typeof/idefics-9b
|
typeof
| 2023-10-13T22:14:34Z | 10 | 0 |
transformers
|
[
"transformers",
"safetensors",
"multimodal",
"text",
"image",
"image-to-text",
"text-generation",
"en",
"dataset:HuggingFaceM4/OBELICS",
"dataset:wikipedia",
"dataset:facebook/pmd",
"dataset:laion/laion2B-en",
"license:other",
"region:us"
] |
text-generation
| 2023-10-13T22:09:51Z |
---
language: en
tags:
- multimodal
- text
- image
- image-to-text
license: other
datasets:
- HuggingFaceM4/OBELICS
- wikipedia
- facebook/pmd
- laion/laion2B-en
pipeline_tag: text-generation
inference: false
---
|
jcfneto/lora-cabrita-br-ptbr
|
jcfneto
| 2023-10-13T22:04:39Z | 2 | 0 |
peft
|
[
"peft",
"arxiv:1910.09700",
"base_model:22h/open-cabrita3b",
"base_model:adapter:22h/open-cabrita3b",
"region:us"
] | null | 2023-10-13T22:04:33Z |
---
library_name: peft
base_model: 22h/open-cabrita3b
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
plusminusone/lora-trained-xl
|
plusminusone
| 2023-10-13T21:53:32Z | 1 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"dataset:plusminusone/rl001",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-10-13T21:17:36Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: rl001
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: false
datasets:
- plusminusone/rl001
---
# LoRA DreamBooth - plusminusone/lora-trained-xl
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0 trained on @fffiloni's SD-XL trainer.
The weights were trained on the concept prompt:
```
rl001
```
Use this keyword to trigger your custom model in your prompts.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Usage
Make sure to upgrade diffusers to >= 0.19.0:
```
pip install diffusers --upgrade
```
In addition make sure to install transformers, safetensors, accelerate as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
To just use the base model, you can run:
```python
import torch
from diffusers import DiffusionPipeline, AutoencoderKL
device = "cuda" if torch.cuda.is_available() else "cpu"
vae = AutoencoderKL.from_pretrained('madebyollin/sdxl-vae-fp16-fix', torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
vae=vae, torch_dtype=torch.float16, variant="fp16",
use_safetensors=True
)
pipe.to(device)
# This is where you load your trained weights
specific_safetensors = "pytorch_lora_weights.safetensors"
lora_scale = 0.9
pipe.load_lora_weights(
'plusminusone/lora-trained-xl',
weight_name = specific_safetensors,
# use_auth_token = True
)
prompt = "A majestic rl001 jumping from a big stone at night"
image = pipe(
prompt=prompt,
num_inference_steps=50,
cross_attention_kwargs={"scale": lora_scale}
).images[0]
```
|
rfanucchi/Taxi_reinforcementelearning_course_7
|
rfanucchi
| 2023-10-13T21:47:13Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T21:45:56Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi_reinforcementelearning_course_7
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="rfanucchi/Taxi_reinforcementelearning_course_7", 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"])
```
|
rfanucchi/Taxi_reinforcementelearning_course_6
|
rfanucchi
| 2023-10-13T21:44:43Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-10-13T21:42:58Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi_reinforcementelearning_course_6
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="rfanucchi/Taxi_reinforcementelearning_course_6", 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"])
```
|
JunxiongWang/BiGS_128_MNLI
|
JunxiongWang
| 2023-10-13T21:41:48Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"BiGS",
"text-classification",
"en",
"dataset:wikipedia",
"dataset:bookcorpus",
"dataset:glue",
"arxiv:2212.10544",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-03-02T02:50:47Z |
---
license: apache-2.0
datasets:
- wikipedia
- bookcorpus
- glue
language:
- en
metrics:
- accuracy
---
## Pretraining Without Attention(BiGS) <br>
## Official JAX Models with Maximal Sequence Length 128 <br>
### This is the finetune checkpoint in MNLI, val accruacy 86.34
### [Paper](https://arxiv.org/abs/2212.10544) | [](https://huggingface.co/JunxiongWang) | [](https://colab.research.google.com/drive/1Fz3OSRF3PZEF_dlnyJ3KZ8Bq35DfUrIB?usp=sharing)
<img width="537" alt="BiGS" src="https://user-images.githubusercontent.com/16102460/221464744-06b6538a-7e84-4c95-909f-239eab1dba71.png">
This [repository](https://github.com/jxiw/BiGS) contains BiGS's jax model definitions, pretrained models weights, training and fintuning code for our paper exploring using state space models for pretraining. You can find more details in our paper.
[**Pretraining Without Attention**](https://arxiv.org/abs/2212.10544)<br>
[Junxiong Wang](), [Jing Nathan Yan](), [Albert Gu](), [Alexander M.Rush]()
<br>Cornell University, Cornell Tech, DeepMind<br>
Transformers have been essential to pretraining success in NLP. While other architectures have been used, downstream accuracy is either significantly worse, or requires attention layers to match standard benchmarks such as GLUE. This work explores pretraining without attention by using recent advances in sequence routing based on state-space models (SSMs). Our proposed model, Bidirectional Gated SSM (BiGS), combines SSM layers with a multiplicative gating architecture that has been effective in simplified sequence modeling architectures. The model learns static layers that do not consider pair-wise interactions. Even so, BiGS is able to match BERT pretraining accuracy on GLUE and can be extended to long-form pretraining of 4096 tokens without approximation. Analysis shows that while the models have similar accuracy, the approach has significantly different inductive biases than BERT in terms of interactions and syntactic representations.
### Load Sequence Classification Model
```python
from BiGS.modeling_flax_bigs import FlaxBiGSForSequenceClassification
model = FlaxBiGSForSequenceClassification.from_pretrained('JunxiongWang/BiGS_128_MNLI')
```
### GLUE
For MRPC, STS-B and RTE, we finetune on the MNLI model
```
export TASK_NAME=mrpc
python run_glue.py \
--model_name_or_path JunxiongWang/BiGS_128_MNLI \
--task_name $TASK_NAME \
--max_seq_length 128 \
--learning_rate 2e-5 \
--num_train_epochs 3 \
--per_device_train_batch_size 2 \
--logging_steps 100 \
--eval_steps 500 \
--weight_decay 0.01 \
--output_dir BiGS_$TASK_NAME/
```
| Task | Metric | Result |
|-------|------------------------------|-------------|
| MRPC | F1/Accuracy | 88.4/83.6 |
| STS-B | Pearson/Spearman corr. | 89.3/89.2 |
| RTE | Accuracy | 80.1 |
|
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.