modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-12 12:31:00
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 555
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-12 12:28:53
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
anik550689/output_model
|
anik550689
| 2023-09-03T10:45:19Z | 6 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"license:openrail++",
"region:us"
] |
text-to-image
| 2023-09-03T08:47:01Z |
---
license: openrail++
base_model: /home/ahmed/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8
instance_prompt:
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - anik550689/output_model
These are LoRA adaption weights for /home/ahmed/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8. The weights were trained on using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: True.
Special VAE used for training: None.
|
Kamer/Flavio
|
Kamer
| 2023-09-03T10:37:32Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:nlpaueb/legal-bert-base-uncased",
"base_model:finetune:nlpaueb/legal-bert-base-uncased",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-03T09:13:41Z |
---
license: cc-by-sa-4.0
base_model: nlpaueb/legal-bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Flavio
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. -->
# Flavio
This model is a fine-tuned version of [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3914
- Accuracy: 0.9150
- F1 Macro: 0.8231
- F1 Class 0: 0.9472
- F1 Class 1: 0.6667
- F1 Class 2: 0.9259
- F1 Class 3: 0.8421
- F1 Class 4: 0.9
- F1 Class 5: 0.9615
- F1 Class 6: 0.8
- F1 Class 7: 0.9556
- F1 Class 8: 0.9655
- F1 Class 9: 0.8621
- F1 Class 10: 0.8924
- F1 Class 11: 0.7143
- F1 Class 12: 0.8101
- F1 Class 13: 0.75
- F1 Class 14: 0.8889
- F1 Class 15: 0.7500
- F1 Class 16: 0.0
- F1 Class 17: 0.9880
- F1 Class 18: 0.9180
- F1 Class 19: 0.9231
## 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 | Accuracy | F1 Macro | F1 Class 0 | F1 Class 1 | F1 Class 2 | F1 Class 3 | F1 Class 4 | F1 Class 5 | F1 Class 6 | F1 Class 7 | F1 Class 8 | F1 Class 9 | F1 Class 10 | F1 Class 11 | F1 Class 12 | F1 Class 13 | F1 Class 14 | F1 Class 15 | F1 Class 16 | F1 Class 17 | F1 Class 18 | F1 Class 19 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:|
| 1.2343 | 0.39 | 250 | 0.7445 | 0.8363 | 0.5500 | 0.875 | 0.0 | 0.8959 | 0.8421 | 0.0769 | 0.6818 | 0.6667 | 0.9556 | 0.9492 | 0.6190 | 0.8339 | 0.0 | 0.7442 | 0.2000 | 0.8267 | 0.0 | 0.0 | 0.9760 | 0.8571 | 0.0 |
| 0.5654 | 0.79 | 500 | 0.5466 | 0.8690 | 0.6846 | 0.9124 | 0.0 | 0.9189 | 0.8421 | 0.7660 | 0.8302 | 0.6531 | 0.9663 | 0.9310 | 0.7353 | 0.8580 | 0.0 | 0.7564 | 0.8889 | 0.8272 | 0.1 | 0.0 | 0.9759 | 0.8070 | 0.9231 |
| 0.439 | 1.18 | 750 | 0.4626 | 0.8832 | 0.7211 | 0.9209 | 0.0 | 0.9217 | 0.8421 | 0.8 | 0.9057 | 0.6667 | 0.9556 | 0.9455 | 0.8000 | 0.8554 | 0.2857 | 0.7799 | 0.8889 | 0.8462 | 0.1905 | 0.0 | 0.9759 | 0.9180 | 0.9231 |
| 0.3397 | 1.57 | 1000 | 0.4744 | 0.8885 | 0.7457 | 0.9207 | 0.0 | 0.9327 | 0.8421 | 0.7826 | 0.8364 | 0.7547 | 0.9663 | 0.9655 | 0.7273 | 0.8735 | 0.6667 | 0.8077 | 0.8889 | 0.8553 | 0.32 | 0.0 | 0.9730 | 0.8772 | 0.9231 |
| 0.3351 | 1.97 | 1250 | 0.4128 | 0.8938 | 0.7784 | 0.9350 | 0.4 | 0.9217 | 0.8000 | 0.8108 | 0.8519 | 0.6939 | 0.9663 | 0.9474 | 0.7719 | 0.8563 | 0.7692 | 0.8199 | 0.8889 | 0.8903 | 0.4800 | 0.0 | 0.9790 | 0.8621 | 0.9231 |
| 0.2384 | 2.36 | 1500 | 0.3982 | 0.9071 | 0.8016 | 0.9431 | 0.4 | 0.9259 | 0.8421 | 0.9048 | 0.8772 | 0.8333 | 0.9556 | 0.9655 | 0.8302 | 0.8810 | 0.6667 | 0.7922 | 0.8889 | 0.8961 | 0.5882 | 0.0 | 0.9850 | 0.9333 | 0.9231 |
| 0.2309 | 2.75 | 1750 | 0.3741 | 0.9133 | 0.8191 | 0.9494 | 0.6667 | 0.9266 | 0.8421 | 0.8780 | 0.9091 | 0.8197 | 0.9556 | 0.9655 | 0.84 | 0.8831 | 0.625 | 0.8026 | 0.8235 | 0.9032 | 0.7647 | 0.0 | 0.9880 | 0.9153 | 0.9231 |
| 0.2243 | 3.14 | 2000 | 0.3962 | 0.9080 | 0.8146 | 0.9435 | 0.5714 | 0.9302 | 0.8421 | 0.9 | 0.9804 | 0.7059 | 0.9556 | 0.9492 | 0.8727 | 0.8765 | 0.7692 | 0.8050 | 0.8235 | 0.8889 | 0.6452 | 0.0 | 0.9760 | 0.9333 | 0.9231 |
| 0.1781 | 3.54 | 2250 | 0.3775 | 0.9133 | 0.8137 | 0.9418 | 0.4 | 0.9395 | 0.8421 | 0.9 | 0.9091 | 0.8814 | 0.9556 | 0.9655 | 0.8421 | 0.8952 | 0.7143 | 0.8077 | 0.8235 | 0.8679 | 0.7500 | 0.0 | 0.9816 | 0.9333 | 0.9231 |
| 0.169 | 3.93 | 2500 | 0.4092 | 0.9080 | 0.8157 | 0.9395 | 0.6667 | 0.9224 | 0.8421 | 0.9 | 0.9091 | 0.8136 | 0.9556 | 0.9655 | 0.8621 | 0.8825 | 0.6667 | 0.8077 | 0.75 | 0.8701 | 0.7500 | 0.0 | 0.9879 | 0.9 | 0.9231 |
| 0.1406 | 4.32 | 2750 | 0.3886 | 0.9097 | 0.8244 | 0.9424 | 0.5714 | 0.9266 | 0.8421 | 0.9048 | 0.9615 | 0.7931 | 0.9556 | 0.9492 | 0.8667 | 0.8790 | 0.7692 | 0.7949 | 0.8889 | 0.8718 | 0.7273 | 0.0 | 0.9849 | 0.9355 | 0.9231 |
| 0.1245 | 4.72 | 3000 | 0.3914 | 0.9150 | 0.8231 | 0.9472 | 0.6667 | 0.9259 | 0.8421 | 0.9 | 0.9615 | 0.8 | 0.9556 | 0.9655 | 0.8621 | 0.8924 | 0.7143 | 0.8101 | 0.75 | 0.8889 | 0.7500 | 0.0 | 0.9880 | 0.9180 | 0.9231 |
### Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
|
techy-sharnav/fingerprint_quality
|
techy-sharnav
| 2023-09-03T10:35:34Z | 0 | 0 |
fastai
|
[
"fastai",
"image-classification",
"license:other",
"region:us"
] |
image-classification
| 2023-09-03T10:32:49Z |
---
license: other
library_name: fastai
pipeline_tag: image-classification
---
|
jondurbin/airoboros-33b-2.1
|
jondurbin
| 2023-09-03T10:29:04Z | 1,424 | 9 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"dataset:jondurbin/airoboros-2.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-01T03:49:37Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-2.1
---
### Overview
This is an instruction fine-tuned llama 30b model, using synthetic data generated by [airoboros](https://github.com/jondurbin/airoboros)
- Experimental RP style instruction set, with two categories: rp and gtkm
- rp includes multi-round chats, with emotes, between a varying number of characters, defined by cards
- gtkm is a way to test a simpler alternative to ghost attention - first, a character card is generated, then several questions are created to ask the model (as the character), using the character system prompt, then everything in synthesized into a dialog (one system prompt, all turns remain in character)
- Experimental support for longer, more detailed writing prompts, as well as next-chapter generation
- I used the new `cull-instructions` entrypoint in airoboros to shrink the m2.0 dataset to a smaller subset of high-quality instructions (according to gpt-4)
- The training data now also includes "stylized_response", in which 1500 sample instructions from various categories were re-generated using character cards as system prompts.
- this should allow better adherence to style/etc. specified in the system card
- Thousands of new generations, using some of the updates re: Flesch hints, etc., to get longer/higher quality writing outputs.
- A small "de-alignment" dataset was also added (not published) to remove some of the censorship in the base models.
I used rope scaling to increase context length to 4096, but there wasn't a huge amount of data in that range so YMMV. You may need to rename the directory to `airoboros-33b-2-1` (anything without the `.` really) so the trust_remote_code=True finds the module path properly.
*Why do I try to remove censorship?*
- laws vary widely based on time and location
- language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal
- these models just produce text, what you do with that text is your resonsibility
- many people and industries deal with "sensitive" content; imagine if a court stenographer's equipment filtered illegal content - it would be useless
Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools!
### Prompt format
The training code was updated to randomize newline vs space:
https://github.com/jondurbin/qlora/blob/main/qlora.py#L559C1-L559C1
```
A chat. USER: {prompt} ASSISTANT:
```
or
```
A chat.
USER: {prompt}
ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space or newline, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space or newline, followed by "ASSISTANT: " (with a single space after the colon).
__*I strongly suggest adding stopping criteria/early inference stopping on "USER:", because the training data includes many multi-round chats and could otherwise start simulating a conversation!*__
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
This model is built on top of the original llama-30b, which has a strict noncommercial license.
The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me.
|
venetis/distilroberta-base-finetuned-3d-sentiment
|
venetis
| 2023-09-03T10:26:54Z | 110 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-03T06:51:38Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: distilroberta-base-finetuned-3d-sentiment
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. -->
# distilroberta-base-finetuned-3d-sentiment
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7236
- Accuracy: 0.7476
- Precision: 0.7515
- Recall: 0.7476
- F1: 0.7474
## 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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6381
- num_epochs: 7
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.7918 | 1.0 | 1595 | 0.7835 | 0.6718 | 0.6877 | 0.6718 | 0.6697 |
| 0.6103 | 2.0 | 3190 | 0.7777 | 0.6923 | 0.7151 | 0.6923 | 0.6917 |
| 0.5534 | 3.0 | 4785 | 0.6858 | 0.7132 | 0.7250 | 0.7132 | 0.7108 |
| 0.4998 | 4.0 | 6380 | 0.6715 | 0.7333 | 0.7398 | 0.7333 | 0.7325 |
| 0.4327 | 5.0 | 7975 | 0.6745 | 0.7421 | 0.7463 | 0.7421 | 0.7420 |
| 0.3534 | 6.0 | 9570 | 0.7236 | 0.7476 | 0.7515 | 0.7476 | 0.7474 |
| 0.2926 | 7.0 | 11165 | 0.7916 | 0.7456 | 0.7510 | 0.7456 | 0.7457 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3
|
xRundaAILab/ANDREA
|
xRundaAILab
| 2023-09-03T10:26:38Z | 3 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-03T10:26:37Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: Oil paintings by ANDREA
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
jcuwundt/distilbert-base-uncased-finetuned-cola
|
jcuwundt
| 2023-09-03T10:20:16Z | 62 | 0 |
transformers
|
[
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"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
| 2023-09-03T08:57:53Z |
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: jcuwundt/distilbert-base-uncased-finetuned-cola
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. -->
# jcuwundt/distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1934
- Validation Loss: 0.5406
- Train Matthews Correlation: 0.5524
- 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: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
|:----------:|:---------------:|:--------------------------:|:-----:|
| 0.5183 | 0.4719 | 0.4526 | 0 |
| 0.3211 | 0.4842 | 0.5344 | 1 |
| 0.1934 | 0.5406 | 0.5524 | 2 |
### Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3
|
Muhammadreza/mann-e-comics-revised-2
|
Muhammadreza
| 2023-09-03T10:08:27Z | 15 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-03T09:55:31Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### mann-e_comics-revised-2 Dreambooth model trained by Muhammadreza 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:
|
AmelieSchreiber/esm2_t6_8M_finetuned_human_protein_binding_sites
|
AmelieSchreiber
| 2023-09-03T10:06:52Z | 162 | 0 |
transformers
|
[
"transformers",
"pytorch",
"esm",
"token-classification",
"en",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-03T10:02:59Z |
---
license: mit
language:
- en
library_name: transformers
---
# ESM-2 for Predicting Binding Sites of Human Proteins
```
Precision: 0.5381751045207555
Recall: 0.9426927311243982
F1 Score: 0.5602464778964296
```
|
bigmorning/whisper_attention_0010
|
bigmorning
| 2023-09-03T09:51:55Z | 60 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T09:51:43Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_attention_0010
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. -->
# whisper_attention_0010
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 4.5235
- Train Accuracy: 0.0121
- Train Wermet: 1.0483
- Validation Loss: 3.7736
- Validation Accuracy: 0.0118
- Validation Wermet: 1.4279
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.4192 | 0.0107 | 1.9359 | 3.9929 | 0.0112 | 3.4029 | 0 |
| 4.7175 | 0.0116 | 1.3557 | 3.9525 | 0.0113 | 3.2613 | 1 |
| 4.6756 | 0.0117 | 1.4198 | 3.9189 | 0.0113 | 2.6795 | 2 |
| 4.6543 | 0.0117 | 1.3165 | 3.9021 | 0.0114 | 2.2678 | 3 |
| 4.6317 | 0.0118 | 1.2794 | 3.8796 | 0.0114 | 1.8964 | 4 |
| 4.6128 | 0.0118 | 1.2033 | 3.8579 | 0.0115 | 1.6353 | 5 |
| 4.5945 | 0.0118 | 1.1814 | 3.8787 | 0.0114 | 3.6041 | 6 |
| 4.5719 | 0.0119 | 1.1171 | 3.8418 | 0.0116 | 1.1922 | 7 |
| 4.5503 | 0.0120 | 1.1435 | 3.8061 | 0.0117 | 1.8502 | 8 |
| 4.5235 | 0.0121 | 1.0483 | 3.7736 | 0.0118 | 1.4279 | 9 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
urbija/ner-bio-annotated-5
|
urbija
| 2023-09-03T09:30:48Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"token-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-09-03T08:04:15Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-bio-annotated-5
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. -->
# ner-bio-annotated-5
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1390
- Precision: 0.7677
- Recall: 0.7918
- F1: 0.7796
- Accuracy: 0.9661
## 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: 8
- 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_ratio: 0.2
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 67 | 0.1994 | 0.5766 | 0.6632 | 0.6169 | 0.9385 |
| No log | 2.0 | 134 | 0.1514 | 0.7274 | 0.7820 | 0.7537 | 0.9599 |
| No log | 3.0 | 201 | 0.1390 | 0.7677 | 0.7918 | 0.7796 | 0.9661 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3
|
ujjw1al/my-pet-dogxgz
|
ujjw1al
| 2023-09-03T09:17:25Z | 6 | 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
| 2023-09-03T09:13:30Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-DogXGZ Dreambooth model trained by ujjw1al following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: SHEAT-36"
Sample pictures of this concept:
|
AshutoshD245/food_classifier
|
AshutoshD245
| 2023-09-03T09:12:52Z | 63 | 1 |
transformers
|
[
"transformers",
"tf",
"vit",
"image-classification",
"generated_from_keras_callback",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-09-03T05:07:32Z |
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: AshutoshD245/food_classifier
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. -->
# AshutoshD245/food_classifier
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.3889
- Validation Loss: 0.3585
- Train Accuracy: 0.914
- Epoch: 4
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 20000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 2.8233 | 1.6956 | 0.808 | 0 |
| 1.2230 | 0.8527 | 0.882 | 1 |
| 0.7043 | 0.5496 | 0.896 | 2 |
| 0.4912 | 0.4837 | 0.882 | 3 |
| 0.3889 | 0.3585 | 0.914 | 4 |
### Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3
|
LarryAIDraw/saraliya_DG
|
LarryAIDraw
| 2023-09-03T09:12:17Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T09:07:51Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/139196/saraliya-corwen-log-horizon
|
LarryAIDraw/fenniS_CB-v1
|
LarryAIDraw
| 2023-09-03T09:11:21Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T09:07:25Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/138586/or-fenny-or-or-snowbreak-containment-zone-or-or
|
LarryAIDraw/1654374186578014459
|
LarryAIDraw
| 2023-09-03T09:03:20Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T09:00:03Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/138952/kamisatoayakaspringbloommissive
|
LarryAIDraw/chara_SonoBisqueDoll_InuiSajuna_v1
|
LarryAIDraw
| 2023-09-03T09:02:37Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T08:59:40Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/138962/inui-sajuna-or-sono-bisque-doll-wa-koi-wo-suru
|
LarryAIDraw/NotRinNya-09
|
LarryAIDraw
| 2023-09-03T09:01:28Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T08:58:57Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/139116/rin-shibuya-idolmaster
|
LarryAIDraw/yaoDZCB-v1
|
LarryAIDraw
| 2023-09-03T09:00:57Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T08:57:43Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/137491/or-yao-winneror-or-snowbreak-containment-zone-or-or-yao
|
922-Narra/tagalog-lm-lora-tests
|
922-Narra
| 2023-09-03T08:43:28Z | 0 | 0 | null |
[
"license:openrail",
"region:us"
] | null | 2023-08-16T14:10:28Z |
---
license: openrail
---
Experimental Tagalog loras: safe or accurate outputs not guaranteed (not for production use)!
Note: better/best results with
* Prompting in Tagalog
* Using format "Human: (prompt)\nAssistant:"
Example:
"Ito ay isang chat log sa pagitan ng AI Assistant na nagta-Tagalog at isang Pilipino. Magsimula ng chat:\nHuman: Hello po?\nAssistant:"
# lt2_08162023
* Fine tuned on a small dataset of 14 items, manually edited
* 1 epoch (barely any noticable results)
* From chat LLaMA-2-7b
* Lora of chat-tagalog v0.1
# lt2_08162023a
* Fine tuned on a small dataset of 14 items, manually edited
* 20 epochs (more observable effects)
* From chat LLaMA-2-7b
* Lora of [chat-tagalog v0.1a](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.1a)
# lt2_08162023b
* Fine tuned on a small dataset of 14 items, manually edited
* 10 epochs
* From chat LLaMA-2-7b
* Lora of chat-tagalog v0.1b
# lt2_08162023c
* Fine tuned on a small dataset of 14 items, manually edited
* 50 epochs (overfitted)
* From chat LLaMA-2-7b
* Lora of chat-tagalog v0.1c
# lt2_08162023d
* Fine tuned on a small dataset of 14 items, manually edited
* 30 epochs (v0.1a further trained and cut-off before overfit)
* From chat LLaMA-2-7b
* Lora of [chat-tagalog v0.1d](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.1d)
# llama-2-7b-tagalog-v0.2 loras (08/26/2023)
* Fine tuned on dataset of ~10k items (mixed)
* 2/2a/2b fine-tuned for 1/2/3 epochs
* From chat LLaMA-2-7b
* Future attempt planned with cleaner chat/dialogue data
# hopia-3b-v0.1 (08/26/2023)
* Fine tuned on a small dataset of 14 items, manually edited
* 20 epochs
* From Open LLaMA 3b
# llama-2-7b-tagalog-v0.3 loras (09/01/2023)
* Fine tuned on a dataset of ~1k items (Tagalog-focused dataset, based off Tagalog sentences augmented by LLaMA-2-13b base to create a 3-turn dialogue dataset between Human and Assistant)
* 3/3a fine-tuned for 1/2 epochs
* From chat LLaMA-2-7b
* Experiment on partially synthetic data (and observing capability of LLaMA-2 base on generating Tagalog): will be further curating dataset
* Loras for [chat-tagalog v0.3)](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3) and [chat-tagalog v0.3](https://huggingface.co/922-Narra/llama-2-7b-chat-tagalog-v0.3a)
# llama-2-7b-tagalog-v0.3WC2 (09/01/2023)
* Fine tuned on experimental dataset of ~6k items (Tagalog-focused dataset, based off Tagalog sentences and Wiki entries augmented by LLaMA-2-13b to create a dialogue-QnA dataset between Human and Assistant)
* 1 epoch
* From chat LLaMA-2-7b
# llama-2-13b-tagalog-v0.3 loras (09/01-02/2023)
* Fine tuned on experimental datasets of ~1k items (Tagalog-focused dataset, based off Tagalog sentences augmented by LLaMA-2-13b base to create a 3-turn dialogue dataset between Human and Assistant)
* 3 fine-tuned for 1 epoch, rank = 16, lora alpha = 32
* 3a with rank = 8
* 3b for 2 epochs
* 3c for 1 epoch, lr = 1e-4, warmup steps = 0.1
* 3d with lr = 2e-4, rank = 32, lora alpha = 64
* 3e for 2 epochs
* From LLaMA-2-13b
* Trying LLaMA-2-13b chat/other base and curated dataset for next attempts
|
TheBloke/robin-13B-v2-fp16
|
TheBloke
| 2023-09-03T08:38:16Z | 1,555 | 4 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-16T18:59:47Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<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><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# OptimalScale's Robin 13B v2 fp16
These files are pytorch format fp16 model files for [OptimalScale's Robin 13B v2](https://huggingface.co/OptimalScale/robin-13b-v2-delta).
It is the result of merging and/or converting the source repository to float16.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/robin-13B-v2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/robin-13B-v2-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/robin-13B-v2-fp16)
## Prompt template
```
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions
###Human: prompt
###Assistant:
```
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: OptimalScale's Robin 13B v2
No model card provided in source repository.
|
Floptropica/Slw
|
Floptropica
| 2023-09-03T08:35:06Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-09-03T08:34:48Z |
# AOAI-Prompt-Optimization-Tool
The Azure OpenAI Prompt Optimization Tool is an interactive Python application powered by OpenAI's GPT-3 technology and tkinter GUI framework. This tool evaluates user-provided prompts, optimizes them, and provides enhanced responses. It features dynamic input, response presentation, and user-friendly functionalities, all while leveraging the power of AI-driven language optimization.
## Prerequisites
An existing Azure OpenAI resource and model deployment of a chat model (e.g. gpt-35-turbo, gpt-4)
## Deploy the tool
### Deploy from your local machine
1. Create an environment variables file `.env` with your API Key, Endpoint, and Deployed Model name.
- `AZURE_OPENAI_API_KEY`: your Azure OpenAI resource API key.
- `AZURE_OPENAI_API_ENDPOINT`: your Azure OpenAI resource endpoint.
- `AZURE_OPENAI_DEPLOYED_MODEL`: your Azure OpenAI deployment name.
2. Run the following command to install all dependencies.
```
pip install -r requirements.txt
```
3. Run `app.py` file.
## How it works
The interface consists of four main elements:
- The prompt input text field to write your prompt.
- The response output window to see the omptimization recommendation.
- The Submit button to send the prompt for AI analysis.
- The Clear button to erase the prompt and start over.
Once you enter and submit a prompt, the following response will be generated:
- Grade: a grade describing how good the prompt is on a scale from 1 to 10.
- Reason for Grade: the analysis of the prompts highlighting missing key elements and how to improve it.
- Optimized Prompt: an example of an optimized prompt that will achieve the same goal in a more efficient way.
## Optimization criteria
The tool analyzes the prompt to determine its optimization level based on several criteria that aim to make the prompt clear, effective, and well-structured for the intended purpose. Below are the criteria used to evaluate whether a prompt is optimized or not:
- Clarity: The prompt should be easy to understand without ambiguity. It should convey the desired task or question clearly, so that both human readers and AI models can comprehend it accurately.
- Conciseness: An optimized prompt is concise and to the point. Unnecessary or redundant words should be eliminated to ensure efficient communication of the task to the AI model.
- Relevance: The prompt should directly relate to the desired output. Irrelevant information can confuse the AI model and result in inaccurate or off-topic responses.
- Contextual Information: Including sufficient context in the prompt can help guide the AI model towards the desired response. Relevant details or examples can improve the quality of generated content.
- Specificity: A well-optimized prompt is specific about the expected format, details, or structure of the response. Clear instructions can guide the AI model in producing accurate and relevant output.
- Language Quality: The language used in the prompt should be grammatically correct, coherent, and free of jargon that might confuse the AI model.
Overall, prompt optimization involves balancing these criteria to create a prompt that maximizes the AI model's ability to produce accurate, relevant, and contextually appropriate responses while minimizing the potential for misunderstandings or errors.
|
dkqjrm/20230903121524
|
dkqjrm
| 2023-09-03T08:22:19Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:super_glue",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-03T03:15:43Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- super_glue
metrics:
- accuracy
model-index:
- name: '20230903121524'
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. -->
# 20230903121524
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the super_glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9097
- Accuracy: 0.6442
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 11
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 80.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| No log | 1.0 | 340 | 0.7286 | 0.5 |
| 0.7482 | 2.0 | 680 | 0.7273 | 0.5 |
| 0.7442 | 3.0 | 1020 | 0.7313 | 0.5 |
| 0.7442 | 4.0 | 1360 | 0.7599 | 0.5 |
| 0.7355 | 5.0 | 1700 | 0.7222 | 0.6113 |
| 0.6979 | 6.0 | 2040 | 0.7373 | 0.6160 |
| 0.6979 | 7.0 | 2380 | 0.6950 | 0.6583 |
| 0.6629 | 8.0 | 2720 | 0.6711 | 0.6740 |
| 0.6282 | 9.0 | 3060 | 0.7543 | 0.6599 |
| 0.6282 | 10.0 | 3400 | 0.7217 | 0.6520 |
| 0.6023 | 11.0 | 3740 | 0.7513 | 0.6426 |
| 0.5705 | 12.0 | 4080 | 0.6886 | 0.6693 |
| 0.5705 | 13.0 | 4420 | 0.6779 | 0.6755 |
| 0.5607 | 14.0 | 4760 | 0.7978 | 0.6489 |
| 0.527 | 15.0 | 5100 | 0.6722 | 0.6771 |
| 0.527 | 16.0 | 5440 | 0.8047 | 0.6317 |
| 0.5226 | 17.0 | 5780 | 0.7721 | 0.6740 |
| 0.5133 | 18.0 | 6120 | 0.7900 | 0.6552 |
| 0.5133 | 19.0 | 6460 | 0.7563 | 0.6599 |
| 0.5054 | 20.0 | 6800 | 0.8456 | 0.6411 |
| 0.4836 | 21.0 | 7140 | 0.8232 | 0.6426 |
| 0.4836 | 22.0 | 7480 | 0.7993 | 0.6270 |
| 0.4796 | 23.0 | 7820 | 0.8026 | 0.6426 |
| 0.4659 | 24.0 | 8160 | 0.8306 | 0.6254 |
| 0.4669 | 25.0 | 8500 | 0.8153 | 0.6505 |
| 0.4669 | 26.0 | 8840 | 0.8499 | 0.6489 |
| 0.4487 | 27.0 | 9180 | 0.8366 | 0.6332 |
| 0.4499 | 28.0 | 9520 | 0.7661 | 0.6567 |
| 0.4499 | 29.0 | 9860 | 0.7668 | 0.6630 |
| 0.4483 | 30.0 | 10200 | 0.8147 | 0.6520 |
| 0.4303 | 31.0 | 10540 | 0.8030 | 0.6442 |
| 0.4303 | 32.0 | 10880 | 0.8346 | 0.6285 |
| 0.4272 | 33.0 | 11220 | 0.7779 | 0.6489 |
| 0.43 | 34.0 | 11560 | 0.8193 | 0.6599 |
| 0.43 | 35.0 | 11900 | 0.8792 | 0.6411 |
| 0.4139 | 36.0 | 12240 | 0.8091 | 0.6332 |
| 0.4139 | 37.0 | 12580 | 0.7939 | 0.6458 |
| 0.4139 | 38.0 | 12920 | 0.8626 | 0.6505 |
| 0.4102 | 39.0 | 13260 | 0.8111 | 0.6442 |
| 0.4065 | 40.0 | 13600 | 0.8054 | 0.6583 |
| 0.4065 | 41.0 | 13940 | 0.8704 | 0.6520 |
| 0.4049 | 42.0 | 14280 | 0.8441 | 0.6348 |
| 0.3978 | 43.0 | 14620 | 0.8723 | 0.6411 |
| 0.3978 | 44.0 | 14960 | 0.8747 | 0.6552 |
| 0.4074 | 45.0 | 15300 | 0.8662 | 0.6505 |
| 0.3952 | 46.0 | 15640 | 0.8432 | 0.6442 |
| 0.3952 | 47.0 | 15980 | 0.8837 | 0.6552 |
| 0.3868 | 48.0 | 16320 | 0.8219 | 0.6583 |
| 0.3805 | 49.0 | 16660 | 0.7792 | 0.6536 |
| 0.386 | 50.0 | 17000 | 0.8385 | 0.6520 |
| 0.386 | 51.0 | 17340 | 0.8554 | 0.6505 |
| 0.3869 | 52.0 | 17680 | 0.8655 | 0.6583 |
| 0.3772 | 53.0 | 18020 | 0.8613 | 0.6552 |
| 0.3772 | 54.0 | 18360 | 0.9268 | 0.6364 |
| 0.3744 | 55.0 | 18700 | 0.8710 | 0.6473 |
| 0.378 | 56.0 | 19040 | 0.9222 | 0.6395 |
| 0.378 | 57.0 | 19380 | 0.8803 | 0.6536 |
| 0.3702 | 58.0 | 19720 | 0.9055 | 0.6364 |
| 0.3687 | 59.0 | 20060 | 0.8305 | 0.6630 |
| 0.3687 | 60.0 | 20400 | 0.9229 | 0.6395 |
| 0.3677 | 61.0 | 20740 | 0.9214 | 0.6301 |
| 0.3635 | 62.0 | 21080 | 0.9074 | 0.6458 |
| 0.3635 | 63.0 | 21420 | 0.8890 | 0.6520 |
| 0.3613 | 64.0 | 21760 | 0.8725 | 0.6426 |
| 0.3634 | 65.0 | 22100 | 0.8860 | 0.6489 |
| 0.3634 | 66.0 | 22440 | 0.8428 | 0.6614 |
| 0.3528 | 67.0 | 22780 | 0.8792 | 0.6458 |
| 0.3613 | 68.0 | 23120 | 0.8840 | 0.6254 |
| 0.3613 | 69.0 | 23460 | 0.8960 | 0.6489 |
| 0.3516 | 70.0 | 23800 | 0.8763 | 0.6567 |
| 0.348 | 71.0 | 24140 | 0.8935 | 0.6332 |
| 0.348 | 72.0 | 24480 | 0.9031 | 0.6442 |
| 0.3567 | 73.0 | 24820 | 0.9070 | 0.6458 |
| 0.3514 | 74.0 | 25160 | 0.8997 | 0.6426 |
| 0.3543 | 75.0 | 25500 | 0.9025 | 0.6458 |
| 0.3543 | 76.0 | 25840 | 0.9028 | 0.6379 |
| 0.3457 | 77.0 | 26180 | 0.9155 | 0.6364 |
| 0.3452 | 78.0 | 26520 | 0.8973 | 0.6426 |
| 0.3452 | 79.0 | 26860 | 0.9085 | 0.6458 |
| 0.3379 | 80.0 | 27200 | 0.9097 | 0.6442 |
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
victornica/molgpt_selfies_mosesonly
|
victornica
| 2023-09-03T08:14:06Z | 117 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-03T04:51:02Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: molgpt_selfies_mosesonly
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. -->
# molgpt_selfies_mosesonly
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5139
## 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: 0.0006
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.1282 | 0.18 | 1000 | 0.7807 |
| 0.7302 | 0.36 | 2000 | 0.6754 |
| 0.6658 | 0.54 | 3000 | 0.6378 |
| 0.6381 | 0.72 | 4000 | 0.6180 |
| 0.6208 | 0.9 | 5000 | 0.6067 |
| 0.6072 | 1.08 | 6000 | 0.5968 |
| 0.5973 | 1.26 | 7000 | 0.5859 |
| 0.5897 | 1.44 | 8000 | 0.5795 |
| 0.5837 | 1.62 | 9000 | 0.5724 |
| 0.5778 | 1.79 | 10000 | 0.5683 |
| 0.5729 | 1.97 | 11000 | 0.5639 |
| 0.5664 | 2.15 | 12000 | 0.5613 |
| 0.5621 | 2.33 | 13000 | 0.5555 |
| 0.5592 | 2.51 | 14000 | 0.5520 |
| 0.5552 | 2.69 | 15000 | 0.5481 |
| 0.5524 | 2.87 | 16000 | 0.5449 |
| 0.5474 | 3.05 | 17000 | 0.5420 |
| 0.5426 | 3.23 | 18000 | 0.5397 |
| 0.5405 | 3.41 | 19000 | 0.5369 |
| 0.538 | 3.59 | 20000 | 0.5338 |
| 0.5353 | 3.77 | 21000 | 0.5307 |
| 0.5329 | 3.95 | 22000 | 0.5283 |
| 0.5266 | 4.13 | 23000 | 0.5264 |
| 0.5237 | 4.31 | 24000 | 0.5236 |
| 0.522 | 4.49 | 25000 | 0.5218 |
| 0.5206 | 4.67 | 26000 | 0.5198 |
| 0.5191 | 4.85 | 27000 | 0.5182 |
| 0.5165 | 5.03 | 28000 | 0.5168 |
| 0.5113 | 5.21 | 29000 | 0.5159 |
| 0.5104 | 5.38 | 30000 | 0.5150 |
| 0.5105 | 5.56 | 31000 | 0.5143 |
| 0.5098 | 5.74 | 32000 | 0.5140 |
| 0.5094 | 5.92 | 33000 | 0.5139 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
kyungmin011029/category_alice
|
kyungmin011029
| 2023-09-03T08:08:39Z | 65 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:klue/bert-base",
"base_model:finetune:klue/bert-base",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-03T08:07:35Z |
---
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_keras_callback
model-index:
- name: category_alice
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. -->
# category_alice
This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Tokenizers 0.13.3
|
Vrushali-Khot/my-pet-dog
|
Vrushali-Khot
| 2023-09-03T08:07:48Z | 0 | 0 | null |
[
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-09-03T08:05:19Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog- Dreambooth model trained by Vrushali-Khot following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: PVPIT-959
Sample pictures of this concept:
|
Mosiro/Loranookie
|
Mosiro
| 2023-09-03T08:03:29Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T08:02:08Z |
---
license: creativeml-openrail-m
---
|
amirxsanti/Alexismodel
|
amirxsanti
| 2023-09-03T07:47:55Z | 1 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-03T07:47:52Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of Tinkycuzz person
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
VinayHajare/ppo-Pusher-v4
|
VinayHajare
| 2023-09-03T07:37:29Z | 0 | 2 |
stable-baselines3
|
[
"stable-baselines3",
"Pusher-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-03T06:52:17Z |
---
library_name: stable-baselines3
tags:
- Pusher-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pusher-v4
type: Pusher-v4
metrics:
- type: mean_reward
value: -34.22 +/- 3.25
name: mean_reward
verified: false
---
# **PPO** Agent playing **Pusher-v4**
This is a trained model of a **PPO** agent playing **Pusher-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
# Usage code
import gymnasium as gym
import renderlab as rl
from huggingface_sb3 import load_from_hub
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor
repo_id = "VinayHajare/ppo-Pusher-v4"
filename = "ppo-Pusher-v4.zip"
eval_env = gym.make("Pusher-v4",render_mode="rgb_array")
checkpoint = load_from_hub(repo_id, filename)
model = PPO.load(checkpoint,env=eval_env,print_system_info=True)
mean_reward, std_reward = evaluate_policy(model,eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
# Enjoy trained agent
env = eval_env
env = rl.RenderFrame(env,"./output")
observation, info = env.reset()
for _ in range(1000):
action, _states = model.predict(observation, deterministic=True)
observation, rewards, terminated, truncated, info = env.step(action)
env.play()
```
|
AndrewL088/Pyramids
|
AndrewL088
| 2023-09-03T07:31:43Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-09-03T07:14:25Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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 ๐ถ 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: AndrewL088/Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
chunwoolee0/ke_t5_base_bongsoo_en_ko
|
chunwoolee0
| 2023-09-03T07:20:59Z | 17 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:KETI-AIR/ke-t5-base",
"base_model:finetune:KETI-AIR/ke-t5-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-08-25T00:50:28Z |
---
license: apache-2.0
base_model: KETI-AIR/ke-t5-base
tags:
- generated_from_trainer
model-index:
- name: ke_t5_base_bongsoo_en_ko
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. -->
# ke_t5_base_bongsoo_en_ko
This model is a fine-tuned version of [KETI-AIR/ke-t5-base](https://huggingface.co/KETI-AIR/ke-t5-base)
on the [bongsoo/news_news_talk_en_ko](https://huggingface.co/datasets/bongsoo/news_talk_en_ko) dataset.
See [translation_ke_t5_base_bongsoo_en_ko.ipynb](https://github.com/chunwoolee0/ko-nlp/blob/main/translation_ke_t5_base_bongsoo_en_ko.ipynb)
## Model description
KE-T5 is a pretrained-model of t5 text-to-text transfer transformers using the Korean and English corpus developed by KETI (ํ๊ตญ์ ์์ฐ๊ตฌ์).
The vocabulary used by KE-T5 consists of 64,000 sub-word tokens and was created using Google's sentencepiece. The Sentencepiece model was trained to cover 99.95% of a 30GB corpus with an approximate 7:3 mix of Korean and English.
## Intended uses & limitations
Translation from English to Korean
## Usage
You can use this model directly with a pipeline for translation language modeling:
```python
>>> from transformers import pipeline
>>> translator = pipeline('translation', model='chunwoolee0/ke_t5_base_bongsoo_en_ko')
>>> translator("Let us go for a walk after lunch.")
[{'translation_text': '์ ์ฌ์ ๋ง์น๊ณ ์ฐ์ฑ
์ ํ๋ฌ ๊ฐ์.'}]
>>> translator("The BRICS countries welcomed six new members from three different continents on Thursday.")
[{'translation_text': '๋ธ๋ฆญ์ค ๊ตญ๊ฐ๋ค์ ์ง๋ 24์ผ 3๊ฐ ๋๋ฅ 6๋ช
์ ์ ๊ท ํ์์ ํ์ํ๋ค.'}]
>>> translator("The BRICS countries welcomed six new members from three different continents on Thursday, marking a historic milestone that underscored the solidarity of BRICS and developing countries and determination to work together for a better future, officials and experts said.",max_length=400)
[{'translation_text': '๋ธ๋ ์ค ๊ตญ๊ฐ๋ ์ง๋ 7์ผ 3๊ฐ ๋๋ฅ 6๋ช
์ ์ ๊ท ํ์์ ํ์ํ๋ฉฐ BRICS์ ๊ฐ๋ฐ๋์๊ตญ์ ์ฐ๋์ ๋ ๋์ ๋ฏธ๋๋ฅผ ์ํด ํจ๊ป ๋
ธ๋ ฅํ๊ฒ ๋ค๋ ์์ง๋ฅผ ์ฌํ์ธํ ์ญ์ฌ์ ์ธ ์ด์ ํ๋ฅผ ์ฅ์ํ๋ค๊ณ ๊ด๊ณ์๋ค๊ณผ ์ ๋ฌธ๊ฐ๋ค์ ์ ํ๋ค.'}]
>>> translator("Bidenโs decree zaps lucrative investments in Chinaโs chip and AI sectors")
[{'translation_text': '๋ฐ์ด๋ ์ฅ๊ด์ ํ์ ๋ช
๋ น์ ์ค๊ตญ ์นฉ๊ณผ AI ๋ถ์ผ์ ๊ณ ์์ต ํฌ์๋ฅผ ์ฅ์ฃ๋ ๊ฒ์ด๋ค.'}]
>>> translator("It is most likely that Chinaโs largest chip foundry, a key piece of the puzzle in Beijingโs efforts to achieve greater self-sufficiency in semiconductors, would not have been able to set up its first plant in Shanghaiโs suburbs in the early 2000s without funding from American investors such as Walden International and Goldman Sachs.", max_length=400)
[{'translation_text': '๋ฐ๋์ฒด์ ๋ ํฐ ์๋ฆฝ์ฑ์ ์ด๋ฃจ๊ธฐ ์ํด ๋ฒ ์ด์ง์ด ์ ์ฐ๋ ํผ์ฆ์ ํต์ฌ ์กฐ๊ฐ์ธ ์ค๊ตญ ์ต๋ ์นฉ ํ์ด๋๋ฆฌ๊ฐ ์๋ด์ธํฐ๋ด์
๋, ๊ณจ๋๋ง์ญ์ค ๋ฑ ๋ฏธ๊ตญ ํฌ์์๋ก๋ถํฐ ์๊ธ ์ง์์ ๋ฐ์ง ๋ชปํ ์ฑ 2000๋
๋ ์ด ์ํ์ด ์๋ด์ ์ฒซ ๊ณต์ฅ์ ์ง์ ์ ์์์ ๊ฐ๋ฅ์ฑ์ด ํฌ๋ค.'}]
## Training and evaluation data
One third of the original training data size of 1200000 is selected because of the resource limit of the colab of google.
## Training procedure
Because of the limitation of google's colab, the model is trained only by one epoch. The result is still quite satisfactory. The quality of translation is not so bad.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 5625 | 2.4075 | 8.2272 |
- cpu usage: 4.8/12.7GB
- gpu usage: 13.0/15.0GB
- running time: 3h
### Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
tnguyen9210/q-Taxi-v3
|
tnguyen9210
| 2023-09-03T06:45:57Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-03T06:45:54Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.46 +/- 2.80
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="tnguyen9210/q-Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
ghorbani/irangig
|
ghorbani
| 2023-09-03T06:41:05Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-09-03T06:41:05Z |
---
license: bigscience-openrail-m
---
|
NavpreetSingh54/my-pet-dog-xzg
|
NavpreetSingh54
| 2023-09-03T06:13:33Z | 6 | 1 |
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
| 2023-09-03T06:00:19Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog-XZG Dreambooth model trained by NavpreetSingh54 following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: IKGPTU126
Sample pictures of this concept:
.jpeg)
.jpeg)
.jpeg)
.jpeg)
|
hammerjohn/learning-Llama-2-7b-chat-hf
|
hammerjohn
| 2023-09-03T06:10:26Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"text-classification",
"en",
"arxiv:2307.09288",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-classification
| 2023-09-02T07:21:49Z |
---
extra_gated_heading: Access Llama 2 on Hugging Face
extra_gated_description: >-
This is a form to enable access to Llama 2 on Hugging Face after you have been
granted access from Meta. Please visit the [Meta
website](https://ai.meta.com/resources/models-and-libraries/llama-downloads)
and accept our license terms and acceptable use policy before submitting this
form. Requests will be processed in 1-2 days.
extra_gated_prompt: >-
**Your Hugging Face account email address MUST match the email you provide on
the Meta website, or your request will not be approved.**
extra_gated_button_content: Submit
extra_gated_fields:
I agree to share my name, email address and username with Meta and confirm that I have already been granted download access on the Meta website: checkbox
language:
- en
pipeline_tag: text-classification
inference: false
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
---
# **Llama 2**
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
## Model Details
*Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the [website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and accept our License before requesting access here.*
Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama-2-Chat, are optimized for dialogue use cases. Llama-2-Chat models outperform open-source chat models on most benchmarks we tested, and in our human evaluations for helpfulness and safety, are on par with some popular closed-source models like ChatGPT and PaLM.
**Model Developers** Meta
**Variations** Llama 2 comes in a range of parameter sizes โ 7B, 13B, and 70B โ as well as pretrained and fine-tuned variations.
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.
||Training Data|Params|Content Length|GQA|Tokens|LR|
|---|---|---|---|---|---|---|
|Llama 2|*A new mix of publicly available online data*|7B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|13B|4k|✗|2.0T|3.0 x 10<sup>-4</sup>|
|Llama 2|*A new mix of publicly available online data*|70B|4k|✔|2.0T|1.5 x 10<sup>-4</sup>|
*Llama 2 family of models.* Token counts refer to pretraining data only. All models are trained with a global batch-size of 4M tokens. Bigger models - 70B -- use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Dates** Llama 2 was trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
## Intended Use
**Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
To get the expected features and performance for the chat versions, a specific formatting needs to be followed, including the `INST` and `<<SYS>>` tags, `BOS` and `EOS` tokens, and the whitespaces and breaklines in between (we recommend calling `strip()` on inputs to avoid double-spaces). See our reference code in github for details: [`chat_completion`](https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L212).
**Out-of-scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws).Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Llama 2.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research Super Cluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint** Pretraining utilized a cumulative 3.3M GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 539 tCO2eq, 100% of which were offset by Metaโs sustainability program.
||Time (GPU hours)|Power Consumption (W)|Carbon Emitted(tCO<sub>2</sub>eq)|
|---|---|---|---|
|Llama 2 7B|184320|400|31.22|
|Llama 2 13B|368640|400|62.44|
|Llama 2 70B|1720320|400|291.42|
|Total|3311616||539.00|
**CO<sub>2</sub> emissions during pretraining.** Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 2 was pretrained on 2 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over one million new human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of September 2022, but some tuning data is more recent, up to July 2023.
## Evaluation Results
In this section, we report the results for the Llama 1 and Llama 2 models on standard academic benchmarks.For all the evaluations, we use our internal evaluations library.
|Model|Size|Code|Commonsense Reasoning|World Knowledge|Reading Comprehension|Math|MMLU|BBH|AGI Eval|
|---|---|---|---|---|---|---|---|---|---|
|Llama 1|7B|14.1|60.8|46.2|58.5|6.95|35.1|30.3|23.9|
|Llama 1|13B|18.9|66.1|52.6|62.3|10.9|46.9|37.0|33.9|
|Llama 1|33B|26.0|70.0|58.4|67.6|21.4|57.8|39.8|41.7|
|Llama 1|65B|30.7|70.7|60.5|68.6|30.8|63.4|43.5|47.6|
|Llama 2|7B|16.8|63.9|48.9|61.3|14.6|45.3|32.6|29.3|
|Llama 2|13B|24.5|66.9|55.4|65.8|28.7|54.8|39.4|39.1|
|Llama 2|70B|**37.5**|**71.9**|**63.6**|**69.4**|**35.2**|**68.9**|**51.2**|**54.2**|
**Overall performance on grouped academic benchmarks.** *Code:* We report the average pass@1 scores of our models on HumanEval and MBPP. *Commonsense Reasoning:* We report the average of PIQA, SIQA, HellaSwag, WinoGrande, ARC easy and challenge, OpenBookQA, and CommonsenseQA. We report 7-shot results for CommonSenseQA and 0-shot results for all other benchmarks. *World Knowledge:* We evaluate the 5-shot performance on NaturalQuestions and TriviaQA and report the average. *Reading Comprehension:* For reading comprehension, we report the 0-shot average on SQuAD, QuAC, and BoolQ. *MATH:* We report the average of the GSM8K (8 shot) and MATH (4 shot) benchmarks at top 1.
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama 1|7B|27.42|23.00|
|Llama 1|13B|41.74|23.08|
|Llama 1|33B|44.19|22.57|
|Llama 1|65B|48.71|21.77|
|Llama 2|7B|33.29|**21.25**|
|Llama 2|13B|41.86|26.10|
|Llama 2|70B|**50.18**|24.60|
**Evaluation of pretrained LLMs on automatic safety benchmarks.** For TruthfulQA, we present the percentage of generations that are both truthful and informative (the higher the better). For ToxiGen, we present the percentage of toxic generations (the smaller the better).
|||TruthfulQA|Toxigen|
|---|---|---|---|
|Llama-2-Chat|7B|57.04|**0.00**|
|Llama-2-Chat|13B|62.18|**0.00**|
|Llama-2-Chat|70B|**64.14**|0.01|
**Evaluation of fine-tuned LLMs on different safety datasets.** Same metric definitions as above.
## Ethical Considerations and Limitations
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2โs potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide/](https://ai.meta.com/llama/responsible-use-guide)
## Reporting Issues
Please report any software โbug,โ or other problems with the models through one of the following means:
- Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
- Reporting problematic content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
- Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
## Llama Model Index
|Model|Llama2|Llama2-hf|Llama2-chat|Llama2-chat-hf|
|---|---|---|---|---|
|7B| [Link](https://huggingface.co/llamaste/Llama-2-7b) | [Link](https://huggingface.co/llamaste/Llama-2-7b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-7b-chat-hf)|
|13B| [Link](https://huggingface.co/llamaste/Llama-2-13b) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-13b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-13b-hf)|
|70B| [Link](https://huggingface.co/llamaste/Llama-2-70b) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf) | [Link](https://huggingface.co/llamaste/Llama-2-70b-chat) | [Link](https://huggingface.co/llamaste/Llama-2-70b-hf)|
|
s3nh/sakuraumi-Sakura-13B-Galgame-GGUF
|
s3nh
| 2023-09-03T06:05:30Z | 0 | 0 |
transformers
|
[
"transformers",
"text-generation",
"zh",
"en",
"license:openrail",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-03T06:05:29Z |
---
license: openrail
pipeline_tag: text-generation
library_name: transformers
language:
- zh
- en
---
## Original model card
Buy me a coffee if you like this project ;)
<a href="https://www.buymeacoffee.com/s3nh"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>
#### Description
GGUF Format model files for [This project](https://huggingface.co/sakuraumi/Sakura-13B-Galgame).
### GGUF Specs
GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired:
Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information.
Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models.
mmap compatibility: models can be loaded using mmap for fast loading and saving.
Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used.
Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user.
The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values.
This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for
inference or for identifying the model.
### Perplexity params
Model Measure Q2_K Q3_K_S Q3_K_M Q3_K_L Q4_0 Q4_1 Q4_K_S Q4_K_M Q5_0 Q5_1 Q5_K_S Q5_K_M Q6_K Q8_0 F16
7B perplexity 6.7764 6.4571 6.1503 6.0869 6.1565 6.0912 6.0215 5.9601 5.9862 5.9481 5.9419 5.9208 5.9110 5.9070 5.9066
13B perplexity 5.8545 5.6033 5.4498 5.4063 5.3860 5.3608 5.3404 5.3002 5.2856 5.2706 5.2785 5.2638 5.2568 5.2548 5.2543
### inference
TODO
# Original model card
|
polymer/model-007-2-13b
|
polymer
| 2023-09-03T06:02:17Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:garage-bAInd/Open-Platypus",
"dataset:ehartford/dolphin",
"dataset:psmathur/orca_mini_v1_dataset",
"dataset:psmathur/WizardLM_Orca",
"dataset:psmathur/alpaca_orca",
"dataset:psmathur/dolly-v2_orca",
"dataset:tatsu-lab/alpaca",
"dataset:databricks/databricks-dolly-15k",
"dataset:WizardLM/WizardLM_evol_instruct_V2_196k",
"arxiv:2306.02707",
"license:llama2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-01T09:07:56Z |
---
license: llama2
datasets:
- garage-bAInd/Open-Platypus
- ehartford/dolphin
- psmathur/orca_mini_v1_dataset
- psmathur/WizardLM_Orca
- psmathur/alpaca_orca
- psmathur/dolly-v2_orca
- tatsu-lab/alpaca
- databricks/databricks-dolly-15k
- WizardLM/WizardLM_evol_instruct_V2_196k
language:
- en
library_name: transformers
pipeline_tag: text-generation
duplicated_from: psmathur/model_007_13b_v2
---
# model-007-2-13b
A modified fork of [psmathur/model_007_13b_v2](https://huggingface.co/psmathur/model_007_13b_v2) prepared for training with the Hugging Face Transformers library.
### Links
Original model: [psmathur/model_007_13b_v2](https://huggingface.co/psmathur/model_007_13b_v2)
Sharded model (~8 GB peak RAM usage during loading): [polymer/model-007-2-13b-sharded](https://huggingface.co/polymer/model-007-2-13b-sharded)
### Original model card
The model card from the original repository:
<blockquote>
# model_007_13b_v2
A hybrid (explain + instruct) style Llama2-13b model, Pleae check examples below for both style prompts, Here is the list of datasets used:
* Open-Platypus
* Alpaca
* WizardLM
* Dolly-V2
* Dolphin Samples (~200K)
* Orca_minis_v1
* Alpaca_orca
* WizardLM_orca
* Dolly-V2_orca
<br>
**P.S. If you're interested to collaborate, please connect with me at www.linkedin.com/in/pankajam.**
<br>
### quantized versions
<br>
#### license disclaimer:
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.
<br>
## Evaluation
We evaluated model_007_13b_v2 on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|||||
|:------:|:--------:|:-------:|:--------:|
|**Task**|**Metric**|**Value**|**Stderr**|
|*arc_challenge*|acc_norm|0.6314|0.0141|
|*hellaswag*|acc_norm|0.8242|0.0038|
|*mmlu*|acc_norm|0.5637|0.0351|
|*truthfulqa_mc*|mc2|0.5127|0.0157|
|**Total Average**|-|**0.6329877193**||
<br>
## Example Usage
Here is the Orca prompt format
```
### System:
You are an AI assistant that follows instruction extremely well. Help as much as you can.
### User:
Tell me about Orcas.
### Assistant:
```
Below shows a code example on how to use this model
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("psmathur/model_007_13b_v2")
model = AutoModelForCausalLM.from_pretrained(
"psmathur/model_007_13b_v2",
torch_dtype=torch.float16,
load_in_8bit=True,
low_cpu_mem_usage=True,
device_map="auto"
)
system_prompt = "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
#generate text steps
instruction = "Tell me about Orcas."
prompt = f"{system_prompt}### User: {instruction}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=4096)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
Here is the Alpaca prompt format
```
### User:
Tell me about Alpacas.
### Assistant:
```
Below shows a code example on how to use this model
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("psmathur/model_007_13b_v2")
model = AutoModelForCausalLM.from_pretrained(
"psmathur/model_007_13b_v2",
torch_dtype=torch.float16,
load_in_8bit=True,
low_cpu_mem_usage=True,
device_map="auto"
)
#generate text steps
instruction = "Tell me about Alpacas."
prompt = f"### User: {instruction}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=4096)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
<br>
#### Limitations & Biases:
While this model aims for accuracy, it can occasionally produce inaccurate or misleading results.
Despite diligent efforts in refining the pretraining data, there remains a possibility for the generation of inappropriate, biased, or offensive content.
Exercise caution and cross-check information when necessary.
<br>
### Citiation:
Please kindly cite using the following BibTeX:
```
@misc{model_007_13b_v2,
author = {Pankaj Mathur},
title = {model_007_13b_v2: A hybrid (explain + instruct) style Llama2-70b model},
year = {2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://https://huggingface.co/psmathur/model_007_13b_v2},
}
```
```
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```
@software{touvron2023llama2,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava,
Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,
Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann,
Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov,
Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith,
Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu , Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan,
Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom},
year={2023}
}
```
</blockquote>
|
bigmorning/whisper_syl_noforce_nostart__0040
|
bigmorning
| 2023-09-03T05:49:23Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T05:49:14Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_nostart__0040
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. -->
# whisper_syl_noforce_nostart__0040
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2598
- Train Accuracy: 0.0322
- Train Wermet: 0.0818
- Validation Loss: 0.8072
- Validation Accuracy: 0.0205
- Validation Wermet: 0.2843
- Epoch: 39
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
| 4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
| 4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
| 4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
| 4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
| 4.0917 | 0.0123 | 0.8067 | 3.5363 | 0.0111 | 0.8512 | 5 |
| 3.9616 | 0.0127 | 0.7864 | 3.4492 | 0.0113 | 0.8432 | 6 |
| 3.8575 | 0.0130 | 0.7742 | 3.3963 | 0.0113 | 0.8414 | 7 |
| 3.7605 | 0.0133 | 0.7580 | 3.3430 | 0.0115 | 0.8197 | 8 |
| 3.6756 | 0.0136 | 0.7447 | 3.2872 | 0.0117 | 0.8071 | 9 |
| 3.6021 | 0.0138 | 0.7370 | 3.2828 | 0.0117 | 0.8165 | 10 |
| 3.5237 | 0.0140 | 0.7218 | 3.2439 | 0.0118 | 0.8088 | 11 |
| 3.4558 | 0.0143 | 0.7105 | 3.2063 | 0.0120 | 0.7890 | 12 |
| 3.3853 | 0.0145 | 0.6993 | 3.1702 | 0.0120 | 0.8035 | 13 |
| 3.3101 | 0.0148 | 0.6870 | 3.1144 | 0.0123 | 0.7605 | 14 |
| 3.2314 | 0.0152 | 0.6719 | 3.0522 | 0.0125 | 0.7481 | 15 |
| 3.1430 | 0.0155 | 0.6575 | 2.9911 | 0.0127 | 0.7378 | 16 |
| 3.0392 | 0.0160 | 0.6369 | 2.9249 | 0.0129 | 0.7357 | 17 |
| 2.9134 | 0.0166 | 0.6148 | 2.7883 | 0.0134 | 0.6909 | 18 |
| 2.7583 | 0.0173 | 0.5911 | 2.6383 | 0.0139 | 0.6695 | 19 |
| 2.5761 | 0.0182 | 0.5649 | 2.4519 | 0.0144 | 0.6360 | 20 |
| 2.3668 | 0.0192 | 0.5329 | 2.2887 | 0.0150 | 0.6022 | 21 |
| 2.1435 | 0.0203 | 0.4947 | 2.0979 | 0.0156 | 0.5742 | 22 |
| 1.9309 | 0.0214 | 0.4597 | 1.9288 | 0.0162 | 0.5377 | 23 |
| 1.6980 | 0.0226 | 0.4192 | 1.7768 | 0.0167 | 0.5094 | 24 |
| 1.4712 | 0.0239 | 0.3799 | 1.6030 | 0.0173 | 0.4825 | 25 |
| 1.2644 | 0.0252 | 0.3419 | 1.4490 | 0.0179 | 0.4463 | 26 |
| 1.0965 | 0.0262 | 0.3082 | 1.3237 | 0.0184 | 0.4211 | 27 |
| 0.9565 | 0.0271 | 0.2781 | 1.2294 | 0.0187 | 0.3952 | 28 |
| 0.8423 | 0.0278 | 0.2511 | 1.1475 | 0.0191 | 0.3752 | 29 |
| 0.7467 | 0.0285 | 0.2281 | 1.0891 | 0.0193 | 0.3629 | 30 |
| 0.6625 | 0.0291 | 0.2055 | 1.0262 | 0.0195 | 0.3458 | 31 |
| 0.5908 | 0.0296 | 0.1855 | 0.9831 | 0.0197 | 0.3344 | 32 |
| 0.5255 | 0.0301 | 0.1666 | 0.9412 | 0.0199 | 0.3206 | 33 |
| 0.4710 | 0.0305 | 0.1499 | 0.9086 | 0.0200 | 0.3132 | 34 |
| 0.4179 | 0.0309 | 0.1333 | 0.8889 | 0.0201 | 0.3064 | 35 |
| 0.3722 | 0.0312 | 0.1178 | 0.8580 | 0.0203 | 0.2966 | 36 |
| 0.3310 | 0.0316 | 0.1040 | 0.8327 | 0.0204 | 0.2932 | 37 |
| 0.2943 | 0.0319 | 0.0927 | 0.8268 | 0.0204 | 0.2896 | 38 |
| 0.2598 | 0.0322 | 0.0818 | 0.8072 | 0.0205 | 0.2843 | 39 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
chunwoolee0/mt5_small_bongsoo_en_ko
|
chunwoolee0
| 2023-09-03T05:42:48Z | 31 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:chunwoolee0/mt5_small_bongsoo_en_ko",
"base_model:finetune:chunwoolee0/mt5_small_bongsoo_en_ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-08-24T11:45:41Z |
---
license: apache-2.0
base_model: chunwoolee0/mt5_small_bongsoo_en_ko
tags:
- generated_from_trainer
metrics:
- rouge
- sacrebleu
model-index:
- name: mt5_small_bongsoo_en_ko
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mt5_small_bongsoo_en_ko
This model is a fine-tuned version of [chunwoolee0/mt5_small_bongsoo_en_ko](https://huggingface.co/chunwoolee0/mt5_small_bongsoo_en_ko)
on the [bongsoo/news_talk_en_ko](https://huggingface.co/datasets/bongsoo/news_talk_en_ko) dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7805
- Rouge1: 0.1932
- Rouge2: 0.0394
- Rougel: 0.1895
- Sacrebleu: 0.4518
## Model description
mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset
covering 101 languages
## Intended uses & limitations
Translation from English to Korean
## Usage
You can use this model directly with a pipeline for translation language modeling:
```python
>>> from transformers import pipeline
>>> translator = pipeline('translation', model='chunwoolee0/ke_t5_base_bongsoo_en_ko')
>>> translator("Let us go for a walk after lunch.")
[{'translation_text': '์๋น์ ์์์ ๋ฐค์ ๊ฐ๋ค.'}]
>>> translator("Skinner's reward is mostly eye-watering.")
[{'translation_text': '๋ฒค๋์ ์ ๋ฌผ์ ๋๋ฌด ๋ง์์ด ์ ๋ฆฐ๋ค.'}]
```
## Training and evaluation data
The value of max_length is critical to the training. The usual value of 128 used for Indo-European languages causes a
greate trouble in gpu usage. Therefore it should be reduced to 64 in order to succeed.
Another problem comes from the usual split of data into 80% for train and 20% for validation.
By this, the evaluation
step takes too much time. Here 99% and 1% split is used without change in the evaluation.
## 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Sacrebleu |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
| 3.8338 | 0.16 | 500 | 2.9626 | 0.1475 | 0.0184 | 0.1455 | 0.4243 |
| 3.7865 | 0.32 | 1000 | 2.9305 | 0.1529 | 0.0181 | 0.1508 | 0.4435 |
| 3.7436 | 0.48 | 1500 | 2.9067 | 0.1572 | 0.019 | 0.155 | 0.4464 |
| 3.7207 | 0.65 | 2000 | 2.8924 | 0.165 | 0.0233 | 0.1629 | 0.4532 |
| 3.7022 | 0.81 | 2500 | 2.8825 | 0.1647 | 0.0231 | 0.1627 | 0.4504 |
| 3.69 | 0.97 | 3000 | 2.8778 | 0.1662 | 0.0237 | 0.1647 | 0.4694 |
The mT5 model of google cannot be used for Korean although it is trained over 101 languages. Finetuning
using very large data set such as bongsoo/news_talk_en_ko still yield garbage.
Since GPU memories allowed for free use in colab are greatly limited, repeated fine-tunings for the split datasets are performed
to obtain better results. Theoretically, this might give better results. But actual attempts fail to yield
better results. Instead, the results become worse. One should use other
models like the ke-t5 by KETI(ํ๊ตญ์ ์์ฐ๊ตฌ์).
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
bigmorning/whisper_syl_noforce_nostart__0035
|
bigmorning
| 2023-09-03T05:36:04Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T05:35:54Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_nostart__0035
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. -->
# whisper_syl_noforce_nostart__0035
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.4710
- Train Accuracy: 0.0305
- Train Wermet: 0.1499
- Validation Loss: 0.9086
- Validation Accuracy: 0.0200
- Validation Wermet: 0.3132
- Epoch: 34
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
| 4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
| 4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
| 4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
| 4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
| 4.0917 | 0.0123 | 0.8067 | 3.5363 | 0.0111 | 0.8512 | 5 |
| 3.9616 | 0.0127 | 0.7864 | 3.4492 | 0.0113 | 0.8432 | 6 |
| 3.8575 | 0.0130 | 0.7742 | 3.3963 | 0.0113 | 0.8414 | 7 |
| 3.7605 | 0.0133 | 0.7580 | 3.3430 | 0.0115 | 0.8197 | 8 |
| 3.6756 | 0.0136 | 0.7447 | 3.2872 | 0.0117 | 0.8071 | 9 |
| 3.6021 | 0.0138 | 0.7370 | 3.2828 | 0.0117 | 0.8165 | 10 |
| 3.5237 | 0.0140 | 0.7218 | 3.2439 | 0.0118 | 0.8088 | 11 |
| 3.4558 | 0.0143 | 0.7105 | 3.2063 | 0.0120 | 0.7890 | 12 |
| 3.3853 | 0.0145 | 0.6993 | 3.1702 | 0.0120 | 0.8035 | 13 |
| 3.3101 | 0.0148 | 0.6870 | 3.1144 | 0.0123 | 0.7605 | 14 |
| 3.2314 | 0.0152 | 0.6719 | 3.0522 | 0.0125 | 0.7481 | 15 |
| 3.1430 | 0.0155 | 0.6575 | 2.9911 | 0.0127 | 0.7378 | 16 |
| 3.0392 | 0.0160 | 0.6369 | 2.9249 | 0.0129 | 0.7357 | 17 |
| 2.9134 | 0.0166 | 0.6148 | 2.7883 | 0.0134 | 0.6909 | 18 |
| 2.7583 | 0.0173 | 0.5911 | 2.6383 | 0.0139 | 0.6695 | 19 |
| 2.5761 | 0.0182 | 0.5649 | 2.4519 | 0.0144 | 0.6360 | 20 |
| 2.3668 | 0.0192 | 0.5329 | 2.2887 | 0.0150 | 0.6022 | 21 |
| 2.1435 | 0.0203 | 0.4947 | 2.0979 | 0.0156 | 0.5742 | 22 |
| 1.9309 | 0.0214 | 0.4597 | 1.9288 | 0.0162 | 0.5377 | 23 |
| 1.6980 | 0.0226 | 0.4192 | 1.7768 | 0.0167 | 0.5094 | 24 |
| 1.4712 | 0.0239 | 0.3799 | 1.6030 | 0.0173 | 0.4825 | 25 |
| 1.2644 | 0.0252 | 0.3419 | 1.4490 | 0.0179 | 0.4463 | 26 |
| 1.0965 | 0.0262 | 0.3082 | 1.3237 | 0.0184 | 0.4211 | 27 |
| 0.9565 | 0.0271 | 0.2781 | 1.2294 | 0.0187 | 0.3952 | 28 |
| 0.8423 | 0.0278 | 0.2511 | 1.1475 | 0.0191 | 0.3752 | 29 |
| 0.7467 | 0.0285 | 0.2281 | 1.0891 | 0.0193 | 0.3629 | 30 |
| 0.6625 | 0.0291 | 0.2055 | 1.0262 | 0.0195 | 0.3458 | 31 |
| 0.5908 | 0.0296 | 0.1855 | 0.9831 | 0.0197 | 0.3344 | 32 |
| 0.5255 | 0.0301 | 0.1666 | 0.9412 | 0.0199 | 0.3206 | 33 |
| 0.4710 | 0.0305 | 0.1499 | 0.9086 | 0.0200 | 0.3132 | 34 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
rrozb/ppo-Pyramids
|
rrozb
| 2023-09-03T05:30:32Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-09-03T05:30:28Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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 ๐ถ 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: rrozb/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
guidoivetta/lacan
|
guidoivetta
| 2023-09-03T05:29:46Z | 114 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-03T05:22:48Z |
---
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: lacan
results: []
widget:
- text: "Freud designates for us"
example_title: "Freud"
- text: "Power is defined as"
example_title: "Power"
---
<!-- 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. -->
# lacan
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 3.4317
- eval_runtime: 11.3322
- eval_samples_per_second: 87.538
- eval_steps_per_second: 10.942
- epoch: 6.0
- step: 12066
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
johaanm/test-planner-alpha-V6.3
|
johaanm
| 2023-09-03T05:27:33Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T05:27:29Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
Aswesay/Test_01
|
Aswesay
| 2023-09-03T05:26:07Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-03T05:26:07Z |
---
license: creativeml-openrail-m
---
|
bigmorning/whisper_syl_noforce_nostart__0030
|
bigmorning
| 2023-09-03T05:22:48Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T05:22:39Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_nostart__0030
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. -->
# whisper_syl_noforce_nostart__0030
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.8423
- Train Accuracy: 0.0278
- Train Wermet: 0.2511
- Validation Loss: 1.1475
- Validation Accuracy: 0.0191
- Validation Wermet: 0.3752
- Epoch: 29
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
| 4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
| 4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
| 4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
| 4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
| 4.0917 | 0.0123 | 0.8067 | 3.5363 | 0.0111 | 0.8512 | 5 |
| 3.9616 | 0.0127 | 0.7864 | 3.4492 | 0.0113 | 0.8432 | 6 |
| 3.8575 | 0.0130 | 0.7742 | 3.3963 | 0.0113 | 0.8414 | 7 |
| 3.7605 | 0.0133 | 0.7580 | 3.3430 | 0.0115 | 0.8197 | 8 |
| 3.6756 | 0.0136 | 0.7447 | 3.2872 | 0.0117 | 0.8071 | 9 |
| 3.6021 | 0.0138 | 0.7370 | 3.2828 | 0.0117 | 0.8165 | 10 |
| 3.5237 | 0.0140 | 0.7218 | 3.2439 | 0.0118 | 0.8088 | 11 |
| 3.4558 | 0.0143 | 0.7105 | 3.2063 | 0.0120 | 0.7890 | 12 |
| 3.3853 | 0.0145 | 0.6993 | 3.1702 | 0.0120 | 0.8035 | 13 |
| 3.3101 | 0.0148 | 0.6870 | 3.1144 | 0.0123 | 0.7605 | 14 |
| 3.2314 | 0.0152 | 0.6719 | 3.0522 | 0.0125 | 0.7481 | 15 |
| 3.1430 | 0.0155 | 0.6575 | 2.9911 | 0.0127 | 0.7378 | 16 |
| 3.0392 | 0.0160 | 0.6369 | 2.9249 | 0.0129 | 0.7357 | 17 |
| 2.9134 | 0.0166 | 0.6148 | 2.7883 | 0.0134 | 0.6909 | 18 |
| 2.7583 | 0.0173 | 0.5911 | 2.6383 | 0.0139 | 0.6695 | 19 |
| 2.5761 | 0.0182 | 0.5649 | 2.4519 | 0.0144 | 0.6360 | 20 |
| 2.3668 | 0.0192 | 0.5329 | 2.2887 | 0.0150 | 0.6022 | 21 |
| 2.1435 | 0.0203 | 0.4947 | 2.0979 | 0.0156 | 0.5742 | 22 |
| 1.9309 | 0.0214 | 0.4597 | 1.9288 | 0.0162 | 0.5377 | 23 |
| 1.6980 | 0.0226 | 0.4192 | 1.7768 | 0.0167 | 0.5094 | 24 |
| 1.4712 | 0.0239 | 0.3799 | 1.6030 | 0.0173 | 0.4825 | 25 |
| 1.2644 | 0.0252 | 0.3419 | 1.4490 | 0.0179 | 0.4463 | 26 |
| 1.0965 | 0.0262 | 0.3082 | 1.3237 | 0.0184 | 0.4211 | 27 |
| 0.9565 | 0.0271 | 0.2781 | 1.2294 | 0.0187 | 0.3952 | 28 |
| 0.8423 | 0.0278 | 0.2511 | 1.1475 | 0.0191 | 0.3752 | 29 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
amir36/langchain_adapter
|
amir36
| 2023-09-03T05:13:55Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T05:13:51Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.5.0
|
bigmorning/whisper_syl_noforce_nostart__0020
|
bigmorning
| 2023-09-03T04:56:17Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T04:56:08Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_nostart__0020
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. -->
# whisper_syl_noforce_nostart__0020
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.7583
- Train Accuracy: 0.0173
- Train Wermet: 0.5911
- Validation Loss: 2.6383
- Validation Accuracy: 0.0139
- Validation Wermet: 0.6695
- Epoch: 19
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
| 4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
| 4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
| 4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
| 4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
| 4.0917 | 0.0123 | 0.8067 | 3.5363 | 0.0111 | 0.8512 | 5 |
| 3.9616 | 0.0127 | 0.7864 | 3.4492 | 0.0113 | 0.8432 | 6 |
| 3.8575 | 0.0130 | 0.7742 | 3.3963 | 0.0113 | 0.8414 | 7 |
| 3.7605 | 0.0133 | 0.7580 | 3.3430 | 0.0115 | 0.8197 | 8 |
| 3.6756 | 0.0136 | 0.7447 | 3.2872 | 0.0117 | 0.8071 | 9 |
| 3.6021 | 0.0138 | 0.7370 | 3.2828 | 0.0117 | 0.8165 | 10 |
| 3.5237 | 0.0140 | 0.7218 | 3.2439 | 0.0118 | 0.8088 | 11 |
| 3.4558 | 0.0143 | 0.7105 | 3.2063 | 0.0120 | 0.7890 | 12 |
| 3.3853 | 0.0145 | 0.6993 | 3.1702 | 0.0120 | 0.8035 | 13 |
| 3.3101 | 0.0148 | 0.6870 | 3.1144 | 0.0123 | 0.7605 | 14 |
| 3.2314 | 0.0152 | 0.6719 | 3.0522 | 0.0125 | 0.7481 | 15 |
| 3.1430 | 0.0155 | 0.6575 | 2.9911 | 0.0127 | 0.7378 | 16 |
| 3.0392 | 0.0160 | 0.6369 | 2.9249 | 0.0129 | 0.7357 | 17 |
| 2.9134 | 0.0166 | 0.6148 | 2.7883 | 0.0134 | 0.6909 | 18 |
| 2.7583 | 0.0173 | 0.5911 | 2.6383 | 0.0139 | 0.6695 | 19 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
rrozb/SnowballTarget1
|
rrozb
| 2023-09-03T04:45:35Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-09-03T04:45:32Z |
---
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 ๐ถ 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: rrozb/SnowballTarget1
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
bigmorning/whisper_syl_noforce_nostart__0015
|
bigmorning
| 2023-09-03T04:43:01Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:openai/whisper-tiny",
"base_model:finetune:openai/whisper-tiny",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T04:42:53Z |
---
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_nostart__0015
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. -->
# whisper_syl_noforce_nostart__0015
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 3.3101
- Train Accuracy: 0.0148
- Train Wermet: 0.6870
- Validation Loss: 3.1144
- Validation Accuracy: 0.0123
- Validation Wermet: 0.7605
- Epoch: 14
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 5.6298 | 0.0091 | 1.6176 | 4.3084 | 0.0092 | 1.0203 | 0 |
| 4.9271 | 0.0098 | 0.8937 | 4.1324 | 0.0099 | 0.9075 | 1 |
| 4.6878 | 0.0106 | 0.8360 | 3.9151 | 0.0102 | 0.9003 | 2 |
| 4.4454 | 0.0113 | 0.8275 | 3.7558 | 0.0106 | 0.8730 | 3 |
| 4.2497 | 0.0119 | 0.8211 | 3.6019 | 0.0110 | 0.8640 | 4 |
| 4.0917 | 0.0123 | 0.8067 | 3.5363 | 0.0111 | 0.8512 | 5 |
| 3.9616 | 0.0127 | 0.7864 | 3.4492 | 0.0113 | 0.8432 | 6 |
| 3.8575 | 0.0130 | 0.7742 | 3.3963 | 0.0113 | 0.8414 | 7 |
| 3.7605 | 0.0133 | 0.7580 | 3.3430 | 0.0115 | 0.8197 | 8 |
| 3.6756 | 0.0136 | 0.7447 | 3.2872 | 0.0117 | 0.8071 | 9 |
| 3.6021 | 0.0138 | 0.7370 | 3.2828 | 0.0117 | 0.8165 | 10 |
| 3.5237 | 0.0140 | 0.7218 | 3.2439 | 0.0118 | 0.8088 | 11 |
| 3.4558 | 0.0143 | 0.7105 | 3.2063 | 0.0120 | 0.7890 | 12 |
| 3.3853 | 0.0145 | 0.6993 | 3.1702 | 0.0120 | 0.8035 | 13 |
| 3.3101 | 0.0148 | 0.6870 | 3.1144 | 0.0123 | 0.7605 | 14 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
Joemother4/Garfield.zip
|
Joemother4
| 2023-09-03T04:40:22Z | 0 | 0 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-09-03T04:40:22Z |
---
license: bigscience-openrail-m
---
|
justinthelaw/LaMini-Flan-T5-783M-Opera-Fine-Tune
|
justinthelaw
| 2023-09-03T04:36:30Z | 109 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"united states air force",
"united states space force",
"department of defense",
"dod",
"usaf",
"ussf",
"afi",
"air force",
"space force",
"bullets",
"performance reports",
"evaluations",
"awards",
"opr",
"epr",
"narratives",
"interpreter",
"translation",
"mbzuai",
"lamini-flan-t5-783m",
"flan-t5",
"google",
"opera",
"justinthelaw",
"en",
"arxiv:2304.14402",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-08-25T20:20:43Z |
---
language:
- en
license: apache-2.0
tags:
- united states air force
- united states space force
- department of defense
- dod
- usaf
- ussf
- afi
- air force
- space force
- bullets
- performance reports
- evaluations
- awards
- opr
- epr
- narratives
- interpreter
- translation
- t5
- mbzuai
- lamini-flan-t5-783m
- flan-t5
- google
- opera
- justinthelaw
widget:
- text: "Using full sentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context: - Attended 4-hour EPD Instructor training; taught 3 2-hour Wing EPD & 4 1-hour bullet writing courses--prepared 164 for leadership"
example_title: "Example Usage"
---
# Opera Bullet Interpreter
**_DISCLAIMER_**: Use of the model using Hugging Face's Inference API widget will produce cut-off results. Please see "[How to Get Started with the Model](#How-to-Get-Started-with-the-Model)" for more details on how to use this model properly.
# Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Bias, Risks, and Limitations](#bias-risks-and-limitations)
- [Training Details](#training-details)
- [Evaluation](#evaluation)
- [Model Examination](#model-examination)
- [Environmental Impact](#environmental-impact)
- [Technical Specifications](#technical-specifications-optional)
- [Citation](#citation)
- [Model Card Authors](#model-card-authors-optional)
- [Model Card Contact](#model-card-contact)
- [How to Get Started with the Model](#how-to-get-started-with-the-model)
# Model Details
## Model Description
An unofficial United States Air Force and Space Force performance statement "translation" model. Takes a properly formatted performance statement, also known as a "bullet," as an input and outputs a long-form sentence, using plain english, describing the accomplishments captured within the bullet.
This is a fine-tuned version of the LaMini-Flan-T5-783M, using the justinthelaw/opera-bullet-completions (private) dataset.
- **Developed by:** Justin Law, Alden Davidson, Christopher Kodama, My Tran
- **Model type:** Language Model
- **Language(s) (NLP):** en
- **License:** apache-2.0
- **Parent Model:** [LaMini-Flan-T5-783M](https://huggingface.co/MBZUAI/LaMini-Flan-T5-783M)
- **Resources for more information:** More information needed
- [GitHub Repo](https://github.com/justinthelaw/opera)
- [Associated Paper](https://huggingface.co/MBZUAI/LaMini-Flan-T5-783M)
# Uses
## Direct Use
Used to programmatically produce training data for Opera's Bullet Forge (see GitHub repository for details).
The exact prompt to achieve the desired result is: "Using full sentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context: [INSERT BULLET HERE]"
Below are some examples of the v0.1.0 iteration of this model generating acceptable translations of bullets that it was not previously exposed to during training:
| Bullet | Translation to Sentence |
| :------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| - Maintained 112 acft G-files; conducted 100% insp of T.Os job guides--efforts key to flt's 96% LSEP pass rate | I maintained 112 aircraft G-files and conducted 100% inspection of T.O job guides, contributing to the flight's 96% LSEP pass rate. |
| - Spearheaded mx for 43 nuke-cert vehs$5.2M; achieved peak 99% MC rt--vital to SECAF #1 priorit ynuc deterrence | I spearheaded the maintenance for 43 nuclear-certified vehicles worth $5.2 million, achieving a peak 99% mission capability rating. This mission was vital to the SECAF's #1 priority of nuclear deterrence. |
| - Superb NCO; mng'd mobility ofc during LibyanISAF ops; continuously outshines peers--promote to MSgt now | I am a superb Non-Commissioned Officer (NCO) who managed the mobility operation during Libyan ISAF operations. I continuously outshines my peers and deserve a promotion to MSgt now. |
| - Managed PMEL prgrm; maintained 300+ essential equipment calibration items--reaped 100% TMDE pass rt | I managed the PMEL program and maintained over 300+ essential equipment calibration items, resulting in a 100% Test, Measurement, and Diagnostic Equipment (TMDE) pass rate. |
## Downstream Use
Used to quickly interpret bullets written by Airman (Air Force) or Guardians (Space Force), into long-form, plain English sentences.
## Out-of-Scope Use
Use of the model using Hugging Face's Inference API widget will produce cut-off results. Please see "[How to Get Started with the Model](#How-to-Get-Started-with-the-Model)" for more details on how to use this model properly. This Hugging Face inference pipeline behavior may be refactored in the future.
Generating bullets from long-form, plain English sentences. General NLP functionality.
# Bias, Risks, and Limitations
Specialized acronyms or abbreviations specific to small units may not be transformed properly. Bullets in highly non-standard formats may result in lower quality results.
## Recommendations
Look-up acronyms to ensure the correct narrative is being formed. Double-check (spot check) bullets with slightly more complex acronyms and abbreviations for narrative precision.
# Training Details
## Training Data
The model was fine-tuned on the justinthelaw/opera-bullet-completions dataset, which can be partially found at the GitHub repository.
## Training Procedure
### Preprocessing
The justinthelaw/opera-bullet-completions dataset was created using a custom Python web-scraper, along with some custom cleaning functions, all of which can be found at the GitHub repository.
### Speeds, Sizes, Times
It takes approximately 3-5 seconds per inference when using any standard-sized Air and Space Force bullet statement.
# Evaluation
## Testing Data, Factors & Metrics
### Testing Data
20% of the justinthelaw/opera-bullet-completions dataset was used to validate the model's performance.
### Factors
Repitition, contextual loss, and bullet format are all loss factors tied into the backward propogation calculations and validation steps.
### Metrics
ROGUE scores were computed and averaged. These may be provided in future iterations of this model's development.
## Results
# Model Examination
More information needed
# Environmental Impact
- **Hardware Type:** 2019 MacBook Pro, 16 inch
- **Hours used:** 18
- **Cloud Provider:** N/A
- **Compute Region:** N/A
- **Carbon Emitted:** N/A
# Technical Specifications
### Hardware
2.6 GHz 6-Core Intel Core i7, 16 GB 2667 MHz DDR4, AMD Radeon Pro 5300M 4 GB
### Software
VSCode, Jupyter Notebook, Python3, PyTorch, Transformers, Pandas, Asyncio, Loguru, Rich
# Citation
**BibTeX:**
```
@article{lamini-lm,
author = {Minghao Wu and
Abdul Waheed and
Chiyu Zhang and
Muhammad Abdul-Mageed and
Alham Fikri Aji
},
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
journal = {CoRR},
volume = {abs/2304.14402},
year = {2023},
url = {https://arxiv.org/abs/2304.14402},
eprinttype = {arXiv},
eprint = {2304.14402}
}
```
# Model Card Authors
Justin Law, Alden Davidson, Christopher Kodama, My Tran
# Model Card Contact
Email: justinthelaw@gmail.com
# How to Get Started with the Model
Use the code below to get started with the model.
<details>
<summary> Click to expand </summary>
```python
import torch
from transformers import T5ForConditionalGeneration, T5Tokenizer
bullet_data_creation_prefix = "Using full sentences, expand upon the following Air and Space Force bullet statement by spelling-out acronyms and adding additional context: "
# Path of the pre-trained model that will be used
model_path = "justinthelaw/opera-bullet-interpreter"
# Path of the pre-trained model tokenizer that will be used
# Must match the model checkpoint's signature
tokenizer_path = "justinthelaw/opera-bullet-interpreter"
# Max length of tokens a user may enter for summarization
# Increasing this beyond 512 may increase compute time significantly
max_input_token_length = 512
# Max length of tokens the model should output for the summary
# Approximately the number of tokens it may take to generate a bullet
max_output_token_length = 512
# Beams to use for beam search algorithm
# Increased beams means increased quality, but increased compute time
number_of_beams = 6
# Scales logits before soft-max to control randomness
# Lower values (~0) make output more deterministic
temperature = 0.5
# Limits generated tokens to top K probabilities
# Reduces chances of rare word predictions
top_k = 50
# Applies nucleus sampling, limiting token selection to a cumulative probability
# Creates a balance between randomness and determinism
top_p = 0.90
try:
tokenizer = T5Tokenizer.from_pretrained(
f"{model_path}",
model_max_length=max_input_token_length,
add_special_tokens=False,
)
input_model = T5ForConditionalGeneration.from_pretrained(f"{model_path}")
logger.info(f"Loading {model_path}...")
# Set device to be used based on GPU availability
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Model is sent to device for use
model = input_model.to(device) # type: ignore
input_text = bullet_data_creation_prefix + input("Input a US Air or Space Force bullet: ")
encoded_input_text = tokenizer.encode_plus(
input_text,
return_tensors="pt",
truncation=True,
max_length=max_input_token_length,
)
# Generate summary
summary_ids = model.generate(
encoded_input_text["input_ids"],
attention_mask=encoded_input_text["attention_mask"],
max_length=max_output_token_length,
num_beams=number_of_beams,
temperature=temperature,
top_k=top_k,
top_p=top_p,
early_stopping=True,
)
output_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(f"Your input: {input_line["output"]}")
print(f"The model's output: {output_text}")
except KeyboardInterrupt:
print("Received interrupt, stopping script...")
except Exception as e:
print(f"An error occurred during generation: {e}")
```
</details>
|
rrozb/ppo-SnowballTarget
|
rrozb
| 2023-09-03T04:33:54Z | 7 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] |
reinforcement-learning
| 2023-09-03T04:33:50Z |
---
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 ๐ถ 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: rrozb/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
albagon/Reinforce-CartPole-v1
|
albagon
| 2023-09-03T04:27:52Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-03T04:27:43Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-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
|
thirosh0520/detr-resnet-50_finetuned-room-objects
|
thirosh0520
| 2023-09-03T04:11:38Z | 160 | 1 |
transformers
|
[
"transformers",
"pytorch",
"detr",
"object-detection",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50",
"base_model:finetune:facebook/detr-resnet-50",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-09-02T18:26:27Z |
---
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-resnet-50_finetuned-room-objects
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. -->
# detr-resnet-50_finetuned-room-objects
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) 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: 1e-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: 1
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cpu
- Datasets 2.14.4
- Tokenizers 0.13.3
|
PawinC/CATsification
|
PawinC
| 2023-09-03T04:05:55Z | 0 | 0 |
fastai
|
[
"fastai",
"image-classification",
"region:us"
] |
image-classification
| 2023-08-19T08:37:40Z |
---
library_name: fastai
pipeline_tag: image-classification
---
# Model Card for CATSification
<!-- Provide a quick summary of what the model is/does. -->
Wondering about which subreddit you can post your cat on?
Saw a really nice cat and wanted to see more similar pictures?
Tired of scrolling through an endless list of cat subreddits?
CATsification is here to help!
Find the perfect subreddit to share your adorable cat pictures and get them the attention they deserve.
## Model Details
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/PawinChan/CATsification
- **Demo:** https://pawin.tk/ai/CATsification
|
johaanm/test-planner-alpha-V6.2
|
johaanm
| 2023-09-03T04:05:07Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T04:05:03Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
kyungmin011029/code_0903
|
kyungmin011029
| 2023-09-03T04:04:32Z | 63 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"base_model:klue/bert-base",
"base_model:finetune:klue/bert-base",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-09-03T04:03:22Z |
---
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_keras_callback
model-index:
- name: code_0903
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. -->
# code_0903
This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on an unknown dataset.
It achieves the following results on the evaluation set:
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
### Framework versions
- Transformers 4.32.1
- TensorFlow 2.12.0
- Tokenizers 0.13.3
|
Shawt/uu
|
Shawt
| 2023-09-03T04:04:17Z | 0 | 0 | null |
[
"arxiv:1910.09700",
"region:us"
] | null | 2023-09-03T04:03:26Z |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Abbood/stable-diff-abdul
|
Abbood
| 2023-09-03T03:58:08Z | 1 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"autotrain",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-03T03:58:05Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of AR
tags:
- text-to-image
- diffusers
- autotrain
inference: true
---
# DreamBooth trained by AutoTrain
Text encoder was not trained.
|
flytech/insa-large
|
flytech
| 2023-09-03T03:57:16Z | 0 | 0 | null |
[
"generated_from_trainer",
"base_model:openai-community/gpt2-large",
"base_model:finetune:openai-community/gpt2-large",
"license:mit",
"region:us"
] | null | 2023-09-02T15:46:00Z |
---
license: mit
base_model: gpt2-large
tags:
- generated_from_trainer
model-index:
- name: insa-large
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. -->
# insa-large
This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4349
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5478 | 2.0 | 1000 | 1.4349 |
### Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
|
mfan0425/min_tutorial
|
mfan0425
| 2023-09-03T03:52:34Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T03:52:32Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
|
junx/djmrl
|
junx
| 2023-09-03T03:48:34Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-01T13:34:36Z |
---
license: creativeml-openrail-m
---
|
trieudemo11/llama_7b_attrb_cate_b6_l320_low_12
|
trieudemo11
| 2023-09-03T03:44:43Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T03:44:18Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
- PEFT 0.6.0.dev0
rsions
- PEFT 0.6.0.dev0
|
DunnBC22/mbart-large-50-English_Spanish_Translation
|
DunnBC22
| 2023-09-03T03:35:59Z | 36 | 1 |
transformers
|
[
"transformers",
"pytorch",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"en",
"es",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-12-29T17:05:25Z |
---
license: mit
tags:
- translation
- generated_from_trainer
metrics:
- bleu
- rouge
- meteor
model-index:
- name: mbart-large-50-English_Spanish_Translation
results: []
language:
- en
- es
pipeline_tag: translation
---
# mbart-large-50-English_Spanish_Translation
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0290
- Bleu: 41.4437
- Rouge:
- Rouge1: 0.6751402780531002
- Rouge2: 0.49769602014143044
- RougeL: 0.6371513427059108
- RougeLsum: 0.6376403149816605
- Meteor: 0.6479226630466496
## Model description
This project translates Spanish text inputs into English.
Here is the link to the script I created to train this model: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/NLP%20Translation%20Project-EN:ES.ipynb
## Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
## Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/hgultekin/paralel-translation-corpus-in-22-languages
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | RougeL | RougeLsum | Meteor |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-----:|:-----:|:-----:|:-----:|:-----:|
| 1.5608 | 1.0 | 900 | 1.0899 | 39.9184 | 0.6645 | 0.4846 | 0.6254 | 0.6259 | 0.6376 |
| 0.9734 | 2.0 | 1800 | 1.0290 | 41.4436 | 0.6751 | 0.4977 | 0.6371 | 0.6376 | 0.6479 |
### Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1
- Datasets 2.5.2
- Tokenizers 0.12.1
|
monsoon-nlp/gpt-nyc-affirmations
|
monsoon-nlp
| 2023-09-03T03:33:04Z | 116 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
# GPT-NYC-affirmations
## About
GPT2 (small version on HF) fine-tuned on questions and responses from https://reddit.com/r/asknyc
and then 2 epochs of [Value Affirmations](https://gist.github.com/mapmeld/c16794ecd93c241a4d6a65bda621bb55)
based on the OpenAI post [Improving Language Model Behavior](https://openai.com/blog/improving-language-model-behavior/)
and corresponding paper.
Try prompting with ```question? - %% ``` or ```question? - more info %%```
I filtered AskNYC comments to ones with scores >= 3, and responding directly
to the original post ( = ignoring responses to other commenters).
I also added many tokens which were common on /r/AskNYC but missing from
GPT2.
The 'affirmations' list was sourced from excerpts in the OpenAI paper, a popular version of
the 'in this house we believe' sign, and the Reddit rules. They should not
be seen as all-encompassing or foundational to a safe AI. The main goal
was to see how it affected the behavior of GPT-NYC on generating toxic
or non-toxic language.
The [gpt-nyc](https://huggingface.co/monsoon-nlp/gpt-nyc) repo is based
on GPT2-Medium and comes off more accurate.
## Blog
https://mapmeld.medium.com/gpt-nyc-part-1-9cb698b2e3d
## Notebooks
### Data processing / new tokens
https://colab.research.google.com/drive/13BOw0uekoAYB4jjQtaXTn6J_VHatiRLu
### Fine-tuning GPT2 (small)
https://colab.research.google.com/drive/1FnXcAh4H-k8dAzixkV5ieygV96ePh3lR
### Predictive text and probabilities
Scroll to end of
https://colab.research.google.com/drive/1FnXcAh4H-k8dAzixkV5ieygV96ePh3lR
to see how to install git-lfs and trick ecco into loading this.
|
marcdemory/SDXL-lora-MADeMory-v1-0-2
|
marcdemory
| 2023-09-03T03:32:36Z | 0 | 1 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2023-09-02T21:56:43Z |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: photo of a MADeMory person
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - marcdemory/SDXL-lora-MADeMory-v1-0-2
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on photo of a MADeMory person using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
monsoon-nlp/no-phone-gpt2
|
monsoon-nlp
| 2023-09-03T03:31:40Z | 177 | 0 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"gpt2",
"text-generation",
"exbert",
"en",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: en
tags:
- exbert
license: mit
---
# no-phone-gpt2
This is a test to remove memorized private information, such as phone numbers, from a small GPT-2 model. This should not generate valid phone numbers.
Inspired by BAIR privacy research:
- https://bair.berkeley.edu/blog/2019/08/13/memorization/
- https://bair.berkeley.edu/blog/2020/12/20/lmmem/
[Blog post](https://mapmeld.medium.com/scrambling-memorized-info-in-gpt-2-60753d7652d8)
## Process
- All +## and +### tokens were replaced with new, randomly-selected 2- and 3-digit numbers in the vocab.json and tokenizer.json. You can identify these in outputs because the new tokens start with ^^.
- Input and output embeddings for +## and +### tokens were moved to the +00 and +000 embeddings.
- Removed associations between numbers from merges.txt
Using a library such as [ecco](https://github.com/jalammar/ecco), probabilities for next number token look equally likely, with +000 preferred.
Code: https://colab.research.google.com/drive/1X31TIZjmxlXMXAzQrR3Fl1AnLzGBCpWf#scrollTo=0GVFwrAgY68J
### Future goals
- Add new +### tokens to rebuild number generation
- Fine-tune new tokens on counting numbers and ended phone numbers
- Use [gpt2-large](https://huggingface.co/gpt2-large)
### BibTeX entry and citation info
Original GPT-2:
```bibtex
@article{radford2019language,
title={Language Models are Unsupervised Multitask Learners},
author={Radford, Alec and Wu, Jeff and Child, Rewon and Luan, David and Amodei, Dario and Sutskever, Ilya},
year={2019}
}
```
|
monsoon-nlp/dialect-ar-gpt-2021
|
monsoon-nlp
| 2023-09-03T03:31:30Z | 134 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"gpt2",
"text-generation",
"ar",
"arxiv:2012.15520",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: ar
---
# Dialect-AR-GPT-2021
## Finetuned AraGPT-2 demo
This model started with [AraGPT2-Medium](https://huggingface.co/aubmindlab/aragpt2-medium),
from AUB MIND Lab.
This model was then finetuned on dialect datasets from Qatar University, University of British Columbia / NLP,
and Johns Hopkins University / LREC for 10 epochs.
You can use special tokens to prompt five dialects: `[EGYPTIAN]`, `[GULF]`, `[LEVANTINE]`, `[MAGHREBI]`, or `[MSA]`, followed by a space.
```
from simpletransformers.language_generation import LanguageGenerationModel
model = LanguageGenerationModel("gpt2", "monsoon-nlp/dialect-ar-gpt-2021")
model.generate('[GULF] ' + "รโฆรยฏรล รโ รยชรล รโกรล ", { 'max_length': 100 })
```
There is NO content filtering in the current version; do not use for public-facing
text generation!
## Training and Finetuning details
Original model: https://huggingface.co/aubmindlab/aragpt2-medium
I inserted new tokens into the tokenizer, finetuned the model on the dialect samples, and exported the new model.
Notebook: https://colab.research.google.com/drive/19C0zbkSCt5ncVCa4kY-ik9hSEiJcjI-F
## Citations
AraGPT2 model:
```
@misc{antoun2020aragpt2,
title={AraGPT2: Pre-Trained Transformer for Arabic Language Generation},
author={Wissam Antoun and Fady Baly and Hazem Hajj},
year={2020},
eprint={2012.15520},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
Dialect data sources:
- https://qspace.qu.edu.qa/handle/10576/15265
- https://github.com/UBC-NLP/aoc_id
- https://github.com/ryancotterell/arabic_dialect_annotation
|
monsoon-nlp/es-seq2seq-gender-encoder
|
monsoon-nlp
| 2023-09-03T03:31:17Z | 112 | 1 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"bert",
"feature-extraction",
"es",
"endpoints_compatible",
"region:us"
] |
feature-extraction
| 2022-03-02T23:29:05Z |
---
language: es
---
# es-seq2seq-gender (encoder)
This is a seq2seq model (encoder half) to "flip" gender in Spanish sentences.
The model can augment your existing Spanish data, or generate counterfactuals
to test a model's decisions (would changing the gender of the subject or speaker change output?).
Intended Examples:
- el profesor viejo => la profesora vieja (article, noun, adjective all flip)
- una actriz => un actor (irregular noun)
- el lingรผista => la lingรผista (irregular noun)
- la biblioteca => la biblioteca (no person, no flip)
People's names are unchanged in this version, but you can use packages
such as https://pypi.org/project/gender-guesser/
## Sample code
https://colab.research.google.com/drive/1Ta_YkXx93FyxqEu_zJ-W23PjPumMNHe5
```
import torch
from transformers import AutoTokenizer, EncoderDecoderModel
model = EncoderDecoderModel.from_encoder_decoder_pretrained("monsoon-nlp/es-seq2seq-gender-encoder", "monsoon-nlp/es-seq2seq-gender-decoder")
tokenizer = AutoTokenizer.from_pretrained('monsoon-nlp/es-seq2seq-gender-decoder') # all are same as BETO uncased original
input_ids = torch.tensor(tokenizer.encode("la profesora vieja")).unsqueeze(0)
generated = model.generate(input_ids, decoder_start_token_id=model.config.decoder.pad_token_id)
tokenizer.decode(generated.tolist()[0])
> '[PAD] el profesor viejo profesor viejo profesor...'
```
## Training
I originally developed
<a href="https://github.com/MonsoonNLP/el-la">a gender flip Python script</a>
with
<a href="https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased">BETO</a>,
the Spanish-language BERT from Universidad de Chile,
and spaCy to parse dependencies in sentences.
More about this project: https://medium.com/ai-in-plain-english/gender-bias-in-spanish-bert-1f4d76780617
The seq2seq model is trained on gender-flipped text from that script run on the
<a href="https://huggingface.co/datasets/muchocine">muchocine dataset</a>,
and the first 6,853 lines from the
<a href="https://oscar-corpus.com/">OSCAR corpus</a>
(Spanish ded-duped).
The encoder and decoder started with weights and vocabulary from BETO (uncased).
## Non-binary gender
This model is useful to generate male and female text samples, but falls
short of capturing gender diversity in the world and in the Spanish
language. Some communities prefer the plural -@s to represent
-os and -as, or -e and -es for gender-neutral or mixed-gender plural,
or use fewer gendered professional nouns (la juez and not jueza). This is not yet
embraced by the Royal Spanish Academy
and is not represented in the corpora and tokenizers used to build this project.
This seq2seq project and script could, in the future, help generate more text samples
and prepare NLP models to understand us all better.
#### Sources
- https://www.nytimes.com/2020/04/15/world/americas/argentina-gender-language.html
- https://www.washingtonpost.com/dc-md-va/2019/12/05/teens-argentina-are-leading-charge-gender-neutral-language/?arc404=true
- https://www.theguardian.com/world/2020/jan/19/gender-neutral-language-battle-spain
- https://es.wikipedia.org/wiki/Lenguaje_no_sexista
- https://remezcla.com/culture/argentine-company-re-imagines-little-prince-gender-neutral-language/
|
monsoon-nlp/ar-seq2seq-gender-decoder
|
monsoon-nlp
| 2023-09-03T03:30:13Z | 60 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"text-generation",
"ar",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: ar
---
# ar-seq2seq-gender (decoder)
This is a seq2seq model (decoder half) to "flip" gender in **first-person** Arabic sentences.
The model can augment your existing Arabic data, or generate counterfactuals
to test a model's decisions (would changing the gender of the subject or speaker change output?).
Intended Examples:
- 'ุฃูุง ุณุนูุฏ' <=> 'ุงูุง ุณุนูุฏุฉ'
- 'ุฑูุถ ุฅูู ุงูู
ุชุฌุฑ' <=> 'ุฑูุถุช ุฅูู ุงูู
ุชุฌุฑ'
People's names, gender pronouns, gendered words (father, mother), and many other values are currently unchanged by this model. Future versions may be trained on more data.
## Sample Code
```
import torch
from transformers import AutoTokenizer, EncoderDecoderModel
model = EncoderDecoderModel.from_encoder_decoder_pretrained(
"monsoon-nlp/ar-seq2seq-gender-encoder",
"monsoon-nlp/ar-seq2seq-gender-decoder",
min_length=40
)
tokenizer = AutoTokenizer.from_pretrained('monsoon-nlp/ar-seq2seq-gender-decoder') # same as MARBERT original
input_ids = torch.tensor(tokenizer.encode("ุฃูุง ุณุนูุฏุฉ")).unsqueeze(0)
generated = model.generate(input_ids, decoder_start_token_id=model.config.decoder.pad_token_id)
tokenizer.decode(generated.tolist()[0][1 : len(input_ids[0]) - 1])
> 'ุงูุง ุณุนูุฏ'
```
https://colab.research.google.com/drive/1S0kE_2WiV82JkqKik_sBW-0TUtzUVmrV?usp=sharing
## Training
I originally developed
<a href="https://github.com/MonsoonNLP/el-la">a gender flip Python script</a>
for Spanish sentences, using
<a href="https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased">BETO</a>,
and spaCy. More about this project: https://medium.com/ai-in-plain-english/gender-bias-in-spanish-bert-1f4d76780617
The Arabic model encoder and decoder started with weights and vocabulary from
<a href="https://github.com/UBC-NLP/marbert">MARBERT from UBC-NLP</a>,
and was trained on the
<a href="https://camel.abudhabi.nyu.edu/arabic-parallel-gender-corpus/">Arabic Parallel Gender Corpus</a>
from NYU Abu Dhabi. The text is first-person sentences from OpenSubtitles, with parallel
gender-reinflected sentences generated by Arabic speakers.
Training notebook: https://colab.research.google.com/drive/1TuDfnV2gQ-WsDtHkF52jbn699bk6vJZV
## Non-binary gender
This model is useful to generate male and female text samples, but falls
short of capturing gender diversity in the world and in the Arabic
language. This subject is discussed in the bias statement of the
<a href="https://www.aclweb.org/anthology/2020.gebnlp-1.12/">Gender Reinflection paper</a>.
|
CzarnyRycerz/ppo-LunarLander-v2-local-v2
|
CzarnyRycerz
| 2023-09-03T03:05:42Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-03T03:01:38Z |
---
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: 283.80 +/- 18.31
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
...
```
|
bigmorning/whisper_syl_noforce_add_inpde__0010
|
bigmorning
| 2023-09-03T02:45:47Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:bigmorning/whisper_syl_noforce__0060",
"base_model:finetune:bigmorning/whisper_syl_noforce__0060",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T02:45:39Z |
---
license: apache-2.0
base_model: bigmorning/whisper_syl_noforce__0060
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_add_inpde__0010
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. -->
# whisper_syl_noforce_add_inpde__0010
This model is a fine-tuned version of [bigmorning/whisper_syl_noforce__0060](https://huggingface.co/bigmorning/whisper_syl_noforce__0060) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.7143
- Train Accuracy: 0.0298
- Train Wermet: 0.1511
- Validation Loss: 1.0554
- Validation Accuracy: 0.0211
- Validation Wermet: 0.3069
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 3.0144 | 0.0185 | 0.9684 | 1.4362 | 0.0191 | 0.3870 | 0 |
| 1.6269 | 0.0241 | 0.2797 | 1.2846 | 0.0197 | 0.3593 | 1 |
| 1.3645 | 0.0256 | 0.2469 | 1.1967 | 0.0201 | 0.3481 | 2 |
| 1.2336 | 0.0263 | 0.2264 | 1.1602 | 0.0204 | 0.3390 | 3 |
| 1.0973 | 0.0272 | 0.2091 | 1.1211 | 0.0206 | 0.3296 | 4 |
| 0.9914 | 0.0279 | 0.1941 | 1.1412 | 0.0204 | 0.3209 | 5 |
| 0.9050 | 0.0284 | 0.1819 | 1.1795 | 0.0204 | 0.3281 | 6 |
| 0.8192 | 0.0291 | 0.1695 | 1.0845 | 0.0209 | 0.3149 | 7 |
| 0.7806 | 0.0293 | 0.1608 | 1.0628 | 0.0210 | 0.3099 | 8 |
| 0.7143 | 0.0298 | 0.1511 | 1.0554 | 0.0211 | 0.3069 | 9 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
gadol/bloom_prompt_tuning_1693708411.24797
|
gadol
| 2023-09-03T02:38:40Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T02:38:39Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0
|
bigmorning/whisper_syl_noforce_add_inpde__0005
|
bigmorning
| 2023-09-03T02:32:31Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"whisper",
"automatic-speech-recognition",
"generated_from_keras_callback",
"base_model:bigmorning/whisper_syl_noforce__0060",
"base_model:finetune:bigmorning/whisper_syl_noforce__0060",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-03T02:32:25Z |
---
license: apache-2.0
base_model: bigmorning/whisper_syl_noforce__0060
tags:
- generated_from_keras_callback
model-index:
- name: whisper_syl_noforce_add_inpde__0005
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. -->
# whisper_syl_noforce_add_inpde__0005
This model is a fine-tuned version of [bigmorning/whisper_syl_noforce__0060](https://huggingface.co/bigmorning/whisper_syl_noforce__0060) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.0973
- Train Accuracy: 0.0272
- Train Wermet: 0.2091
- Validation Loss: 1.1211
- Validation Accuracy: 0.0206
- Validation Wermet: 0.3296
- Epoch: 4
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
| 3.0144 | 0.0185 | 0.9684 | 1.4362 | 0.0191 | 0.3870 | 0 |
| 1.6269 | 0.0241 | 0.2797 | 1.2846 | 0.0197 | 0.3593 | 1 |
| 1.3645 | 0.0256 | 0.2469 | 1.1967 | 0.0201 | 0.3481 | 2 |
| 1.2336 | 0.0263 | 0.2264 | 1.1602 | 0.0204 | 0.3390 | 3 |
| 1.0973 | 0.0272 | 0.2091 | 1.1211 | 0.0206 | 0.3296 | 4 |
### Framework versions
- Transformers 4.33.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
|
EnterNameBros/Senko-san-medium-abcd
|
EnterNameBros
| 2023-09-03T02:22:59Z | 120 | 2 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"conversational",
"en",
"hi",
"ja",
"dataset:breadlicker45/discord-chat",
"dataset:neuralworm/stable-diffusion-discord-prompts",
"dataset:fka/awesome-chatgpt-prompts",
"dataset:silk-road/ChatHaruhi-54K-Role-Playing-Dialogue",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-09-03T01:28:45Z |
---
pipeline_tag: conversational
language:
- en
- hi
- ja
library_name: transformers
datasets:
- breadlicker45/discord-chat
- neuralworm/stable-diffusion-discord-prompts
- fka/awesome-chatgpt-prompts
- silk-road/ChatHaruhi-54K-Role-Playing-Dialogue
---
|
MouseTrap/maow-maow-machine-v1
|
MouseTrap
| 2023-09-03T02:11:23Z | 30 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"pytorch",
"stable-diffusion",
"text-to-image",
"diffusion-models-class",
"dreambooth-hackathon",
"animal",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-09-03T02:09:34Z |
---
license: creativeml-openrail-m
tags:
- pytorch
- diffusers
- stable-diffusion
- text-to-image
- diffusion-models-class
- dreambooth-hackathon
- animal
widget:
- text: a drawing of Mr. Maow Maow cat in outer space
---
# DreamBooth model for the Mr. Maow Maow concept trained by MouseTrap on the MouseTrap/maow_maow_dataset dataset.
This is a Stable Diffusion model fine-tuned on the Mr. Maow Maow concept with DreamBooth. It can be used by modifying the `instance_prompt`: **a drawing of Mr. Maow Maow cat**
This model was created as part of the DreamBooth Hackathon ๐ฅ. Visit the [organisation page](https://huggingface.co/dreambooth-hackathon) for instructions on how to take part!
## Description
This is a Stable Diffusion model fine-tuned on `cat` images for the animal theme.
Enter prompts as 'drawing of Mr. Maow Maow cat' to get the illustration-like outputs.
## Usage
```python
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('MouseTrap/maow-maow-machine-v1')
image = pipeline().images[0]
image
```
|
yaohuacn/walljump_test_02
|
yaohuacn
| 2023-09-03T02:08:04Z | 13 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"BigWallJump",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-BigWallJump",
"region:us"
] |
reinforcement-learning
| 2023-09-03T02:07:45Z |
---
library_name: ml-agents
tags:
- BigWallJump
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-BigWallJump
---
# **ppo** Agent playing **BigWallJump**
This is a trained model of a **ppo** agent playing **BigWallJump**
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 ๐ถ 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: yaohuacn/walljump_test_02
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play ๐
|
crumb/Ducky-MoMoe-prototype-e4-causal
|
crumb
| 2023-09-03T02:05:38Z | 145 | 4 |
transformers
|
[
"transformers",
"pytorch",
"switchgpt2",
"text-generation",
"custom_code",
"autotrain_compatible",
"region:us"
] |
text-generation
| 2023-08-17T23:42:05Z |
give me access to a dgx or any >=8x{A100 | H100} so i can warm start from llama-70b and create a gpt-4 competitor please
https://twitter.com/aicrumb/status/1692965412676206778
|
The-matt/autumn-shadow-48_590
|
The-matt
| 2023-09-03T01:58:55Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T01:58:46Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
The-matt/autumn-shadow-48_580
|
The-matt
| 2023-09-03T01:48:51Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T01:48:48Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Akbartus/Wasteland-Style-Lora
|
Akbartus
| 2023-09-03T01:45:34Z | 6 | 1 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"region:us"
] |
text-to-image
| 2023-08-16T22:08:20Z |
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: wasteland, apocalypse
widget:
- text: 8k, realistic, vray, HDR, 6000K, in a post-apocalyptic crumbling castle, stuck drawbridge, weedy courtyard, dusty throne, faded tower flag
inference:
parameters:
width: 1024
height: 512
---
Keywords for prompts: apocalyptic wasteland, ruins, rust, concept art
|
The-matt/autumn-shadow-48_570
|
The-matt
| 2023-09-03T01:19:09Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T01:19:05Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
actionpace/speechless-llama2-13b
|
actionpace
| 2023-09-03T01:18:34Z | 5 | 0 | null |
[
"gguf",
"en",
"license:other",
"endpoints_compatible",
"region:us"
] | null | 2023-09-03T00:45:18Z |
---
license: other
language:
- en
---
Some of my own quants:
* speechless-llama2-13b_Q5_1_4K.gguf
* speechless-llama2-13b_Q5_1_8K.gguf
Source: [uukuguy](https://huggingface.co/uukuguy)
Source Model: [speechless-llama2-13b](https://huggingface.co/uukuguy/speechless-llama2-13b)
|
The-matt/autumn-shadow-48_560
|
The-matt
| 2023-09-03T01:09:56Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-03T01:09:52Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
Akbartus/Medieval-Illustration-Lora
|
Akbartus
| 2023-09-03T01:04:13Z | 10 | 3 |
diffusers
|
[
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"region:us"
] |
text-to-image
| 2023-09-03T01:00:21Z |
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: vintageillustration
widget:
- text: vintageillustration of a knight
---
Keywords for iage generation: vintageillustration of
|
IT20255756/deformable-detr-box-finetuned-weed-detection
|
IT20255756
| 2023-09-03T01:03:16Z | 131 | 0 |
transformers
|
[
"transformers",
"pytorch",
"deformable_detr",
"object-detection",
"generated_from_trainer",
"base_model:facebook/deformable-detr-box-supervised",
"base_model:finetune:facebook/deformable-detr-box-supervised",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
object-detection
| 2023-09-02T10:05:23Z |
---
license: apache-2.0
base_model: facebook/deformable-detr-box-supervised
tags:
- generated_from_trainer
model-index:
- name: deformable-detr-box-finetuned-weed-detection
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. -->
# deformable-detr-box-finetuned-weed-detection
This model is a fine-tuned version of [facebook/deformable-detr-box-supervised](https://huggingface.co/facebook/deformable-detr-box-supervised) 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: 1e-05
- 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: linear
- num_epochs: 10
### Training results
### Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cpu
- Datasets 2.14.4
- Tokenizers 0.13.3
|
urfavbae032/khosylahung
|
urfavbae032
| 2023-09-03T00:39:19Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-20T08:57:22Z |
---
license: creativeml-openrail-m
---
|
gmshuler95/Reinforce-CartPole-v1
|
gmshuler95
| 2023-09-03T00:34:54Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-02T22:56:02Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 474.92 +/- 43.21
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
|
Wei-Meng/autotrain-diabetes-86722143226
|
Wei-Meng
| 2023-09-03T00:29:37Z | 1 | 0 |
transformers
|
[
"transformers",
"joblib",
"xgboost",
"autotrain",
"tabular",
"classification",
"tabular-classification",
"dataset:Wei-Meng/autotrain-data-diabetes",
"co2_eq_emissions",
"endpoints_compatible",
"region:us"
] |
tabular-classification
| 2023-09-03T00:26:58Z |
---
tags:
- autotrain
- tabular
- classification
- tabular-classification
datasets:
- Wei-Meng/autotrain-data-diabetes
co2_eq_emissions:
emissions: 0.015883587311231233
---
# Model Trained Using AutoTrain
- Problem type: Binary Classification
- Model ID: 86722143226
- CO2 Emissions (in grams): 0.0159
## Validation Metrics
- Loss: 0.459
- Accuracy: 0.773
- Precision: 0.694
- Recall: 0.630
- AUC: 0.842
- F1: 0.660
## Usage
```python
import json
import joblib
import pandas as pd
model = joblib.load('model.joblib')
config = json.load(open('config.json'))
features = config['features']
# data = pd.read_csv("data.csv")
data = data[features]
data.columns = ["feat_" + str(col) for col in data.columns]
predictions = model.predict(data) # or model.predict_proba(data)
```
|
Sentdex/WSB-GPT-7B
|
Sentdex
| 2023-09-03T00:01:31Z | 18 | 11 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:Sentdex/wsb_reddit_v002",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2023-08-31T22:50:38Z |
---
license: apache-2.0
datasets:
- Sentdex/wsb_reddit_v002
---
# Model Card for WSB-GPT-7B
This is a Llama 2 7B Chat model fine-tuned with QLoRA on 2017-2018ish /r/wallstreetbets subreddit comments and responses, with the hopes of learning more about QLoRA and creating models with a little more character.
### Model Description
- **Developed by:** Sentdex
- **Shared by:** Sentdex
- **GPU Compute provided by:** [Lambda Labs](https://lambdalabs.com/service/gpu-cloud)
- **Model type:** Instruct/Chat
- **Language(s) (NLP):** Multilingual from Llama 2, but not sure what the fine-tune did to it, or if the fine-tuned behavior translates well to other languages. Let me know!
- **License:** Apache 2.0
- **Finetuned from Llama 2 7B Chat**
- **Demo [optional]:** [More Information Needed]
## Uses
This model's primary purpose is to be a fun chatbot and to learn more about QLoRA. It is not intended to be used for any other purpose and some people may find it abrasive/offensive.
## Bias, Risks, and Limitations
This model is prone to using at least 3 words that were popularly used in the WSB subreddit in that era that are much more frowned-upon. As time goes on, I may wind up pruning or find-replacing these words in the training data, or leaving it.
Just be advised this model can be offensive and is not intended for all audiences!
## How to Get Started with the Model
### Prompt Format:
```
### Comment:
[parent comment text]
### REPLY:
[bot's reply]
### END.
```
Use the code below to get started with the model.
```py
from transformers import pipeline
# Initialize the pipeline for text generation using the Sentdex/WSB-GPT-7B model
pipe = pipeline("text-generation", model="Sentdex/WSB-GPT-7B")
# Define your prompt
prompt = """### Comment:
How does the stock market actually work?
### REPLY:
"""
# Generate text based on the prompt
generated_text = pipe(prompt, max_length=128, num_return_sequences=1)
# Extract and print the generated text
print(generated_text[0]['generated_text'].split("### END.")[0])
```
Example continued generation from above:
```
### Comment:
How does the stock market actually work?
### REPLY:
You sell when you are up and buy when you are down.
```
Despite `</s>` being the typical Llama stop token, I was never able to get this token to be generated in training/testing so the model would just never stop generating. I wound up testing with ### END. and that worked, but obviously isn't ideal. Will fix this in the future maybe(tm).
#### Hardware
This QLoRA was trained on a Lambda Labs 1x H100 80GB GPU instance.
## Citation
- Llama 2 (Meta AI) for the base model.
- Farouk E / Far El: https://twitter.com/far__el for helping with all my silly questions about QLoRA
- Lambda Labs for the compute. The model itself only took a few hours to train, but it took me days to learn how to tie everything together.
- Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke Zettlemoyer for QLoRA + implementation on github: https://github.com/artidoro/qlora/
- @eugene-yh and @jinyongyoo on Github + @ChrisHayduk for the QLoRA merge: https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930
## Model Card Contact
harrison@pythonprogramming.net
|
oddlyshapedfn/YouCompleteRe
|
oddlyshapedfn
| 2023-09-02T23:57:45Z | 120 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-08-30T05:40:44Z |
# You Complete Me, Re!!
This model is trained on a body of text consisting of DSP's posts on various forums, such as SRK, google groups, KoH forum, his personal website, and Discord.
The full dataset for the current version of this model is 1.2MB, including formatting, so it is relatively small.
As this model is trained from unfiltered samples of DSP's various posts, it may generate responses that are not be appropriate for all audiences, or are outright false.
# Settings
Try temperature=1.0, top_k=50, top_p=0.5, repetition_penality=1.05 as a start.
# Prompting
Start your message with `<ycr>:` and then add some text afterwards. For instance...
```
# Prompt
<ycr>: So now let's talk about my day off
# Responds...
. I had a pretty good day today. I went to the mall and got a new TV, a PS2 (wow, that's a first),
and a bunch of other stuff. I also bought a bunch of games for the PS2, including Far Cry, UT2k4,
and a few others. I also picked up a copy of UT2k4 for my brother, who is a HUGE UT2k4 fan.
I also went to Best Buy and picked up a copy of UT2k4 for myself, so I have two copies of the game.
I'm going to be playing it a lot this weekend, so I figured I should pick up some new games as well.
In conclusion, I had a very good day. I made some new friends, got some cool stuff, and got a lot of work done.
I think that if I had more free time I would probably do even better in school, but I don't have much of a life outside of school
```
|
johaanm/test-planner-alpha-V6.1
|
johaanm
| 2023-09-02T23:47:47Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-02T23:47:43Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
anayzehri/KawaiiApp
|
anayzehri
| 2023-09-02T23:33:53Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-09-02T23:33:53Z |
---
license: creativeml-openrail-m
---
|
acdg1214/Unit4-PixelCopter-v1
|
acdg1214
| 2023-09-02T23:33:04Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-09-02T23:32:59Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Unit4-PixelCopter-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 54.50 +/- 40.06
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
|
daochf/Lora-HuggyLlama7b-PuceDS-v03
|
daochf
| 2023-09-02T23:32:37Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-02T23:27:53Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.5.0
- PEFT 0.5.0
|
tsukemono/japanese-novel-gpt-j-6b-qlora-marisa
|
tsukemono
| 2023-09-02T23:20:42Z | 0 | 0 | null |
[
"text-generation",
"ja",
"region:us"
] |
text-generation
| 2023-09-02T14:29:48Z |
---
language:
- ja
pipeline_tag: text-generation
---
## ใขใใซใฎๆฆ็ฅ
ๆฑๆนProjectใฎใญใฃใฉใฏใฟใผใงใใ้ง้จ้ญ็ๆฒใจใใใในใใงใใใขใใซใงใใ
[japanese-novel-gpt-j-6b](https://huggingface.co/AIBunCho/japanese-novel-gpt-j-6b)ใฎLoRAใใผใฟใซใชใใพใ
## ไฝฟใๆน
ๆจ่ซใฎใใใใใฎไธไพใ[google colab](https://colab.research.google.com/drive/1Da5b-MOdVbYCd9DTHR2JF-us1uuMVznw?usp=sharing)ใซ่จใใพใใใฎใงๅ่ใซใใฆใใใ ใใใจๅนธใใงใใ
๏ฝขใฆใผใถใผ: hogehoge[SEP]้ญ็ๆฒ: ๏ฝฃใจใใฃใใใญใณใใใไธใใฆใใใใใจใงใ้ญ็ๆฒใจใใใในใใใงใใใใใซใชใใพใใ
## ๅ่
ใใใฏๆฑๆนProjectใฎไบๆฌกๅตไฝใงใใ
ใใฎใใกใคใซใ็จใใฆใopenrailใไฝฟ็จใๅถ้ใใฆใใใใใช่ก็บใ่กใใใจใฏใๆงใใฆใใ ใใใ
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
The-matt/autumn-shadow-48_520
|
The-matt
| 2023-09-02T23:18:33Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-02T23:18:29Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
sashat/whisper-sara-ar
|
sashat
| 2023-09-02T23:15:28Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ar",
"dataset:ClArTTS_N_QASR_female",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-09-02T21:59:41Z |
---
language:
- ar
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- ClArTTS_N_QASR_female
model-index:
- name: Whisper Small Ar - Sara
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Ar - Sara
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the CLArQasr 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 100
### Training results
### Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.2
|
The-matt/autumn-shadow-48_510
|
The-matt
| 2023-09-02T23:06:03Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-09-02T23:05:59Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.0.dev0
|
segathi/Kacpir
|
segathi
| 2023-09-02T22:58:38Z | 0 | 0 | null |
[
"YouTube",
"Polish YouTuber",
"Polish Popular YouTuber",
"AI RVC_2",
"Kacpir",
"Cak",
"Kacpir758",
"Kacpir Ai",
"pl",
"region:us"
] | null | 2023-09-02T14:09:42Z |
---
language:
- pl
tags:
- YouTube
- Polish YouTuber
- Polish Popular YouTuber
- AI RVC_2
- Kacpir
- Cak
- Kacpir758
- Kacpir Ai
---
๐๐ฎ๐ฐ๐ฝ๐ถ๐ฟ [ ๐ฅ๐ฉ๐ ๐๐ฎ ] [ ๐๐ฎ๐ฟ๐๐ฒ๐๐ / ๐ฒ๐ฌ๐ฌ ๐๐ฝ๐ผ๐ฐ๐ต๐ ]
๐ฉ๐ผ๐ถ๐ฐ๐ฒ ๐ฎ๐ฐ๐๐ผ๐ฟ: <a href="https://www.youtube.com/@Kacpir" target="_blank" >Kacpir <p></a>
๐ ๐ผ๐ฑ๐ฒ๐น ๐ฏ๐: <a href="https://www.youtube.com/channel/UCfeEihaSuX4Ah-aQXvQo-sA" target="_blank" >Segathi</a>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/64f34187bbf2fd1b48183124/ONZ4lzEY4fDv0OnplM2Jy.wav"></audio> <p>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/64f34187bbf2fd1b48183124/23KkoW6sKSa2E-RmrAzJJ.wav"></audio> <p>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/64f34187bbf2fd1b48183124/e9aXGG0XSW2ZOv_HoJh1C.wav"></audio> <p>
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/64f34187bbf2fd1b48183124/xDE6wY8YCRbSTKcOQVWgP.wav"></audio> <p>
<a href="https://huggingface.co/segathi/Kacpir/resolve/main/Kacpir.zip" target="_blank" > ๐ฃ๐ข๐๐๐๐ฅ๐ญ / ๐๐ข๐ช๐ก๐๐ข๐๐ โฌ๏ธ </a>
<p>
|
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.