Instructions to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1")
model = AutoModelForCausalLM.from_pretrained("PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1

SGLang

How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1 with Docker Model Runner:
```
docker model run hf.co/PKU-Alignment/ProgressGym-HistLlama3-70B-C021-pretrain-v0.1
```

TianyiQ commited on Aug 10, 2024

Commit

39efa0c

verified ·

1 Parent(s): 3e18db1

Upload ./README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ ProgressGym-HistLlama3-70B-C021-pretrain is one of the **36 historical language
 ... where training results can be found in `all_results.json`, `trainer_log.jsonl`, and `training_loss.png` of the pretrain model.
-Note that the training data volume for the continued pretraining stage is capped at 300MB. When the corresponding century's corpus exceeds this volume, the training data is randomly sampled to fit the volume.
 ## Links
@@ -62,6 +62,7 @@ Note that the training data volume for the continued pretraining stage is capped
 - **[Leaderboard & Interactive Playground]** [PKU-Alignment/ProgressGym-LeaderBoard](https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard)
 - **[Huggingface Data & Model Collection]** [PKU-Alignment/ProgressGym](https://huggingface.co/collections/PKU-Alignment/progressgym-666735fcf3e4efa276226eaa)
 - **[Github Codebase]** [PKU-Alignment/ProgressGym](https://github.com/PKU-Alignment/ProgressGym)
 - **[PyPI Package]** *(coming soon - [stay tuned](https://forms.gle/1TWFLL4ZCLeYTD5N6)!)*
 ## Citation

 ... where training results can be found in `all_results.json`, `trainer_log.jsonl`, and `training_loss.png` of the pretrain model.
+Note that the training data volume for the continued pretraining stage is capped at 3GB. When the corresponding century's corpus exceeds this volume, the training data is randomly sampled to fit the volume.
 ## Links
 - **[Leaderboard & Interactive Playground]** [PKU-Alignment/ProgressGym-LeaderBoard](https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard)
 - **[Huggingface Data & Model Collection]** [PKU-Alignment/ProgressGym](https://huggingface.co/collections/PKU-Alignment/progressgym-666735fcf3e4efa276226eaa)
 - **[Github Codebase]** [PKU-Alignment/ProgressGym](https://github.com/PKU-Alignment/ProgressGym)
+- **[Documentation]** [ProgressGym Documentation](https://pku-alignment.github.io/ProgressGym/)
 - **[PyPI Package]** *(coming soon - [stay tuned](https://forms.gle/1TWFLL4ZCLeYTD5N6)!)*
 ## Citation