Instructions to use Mercury7353/PyLlama3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mercury7353/PyLlama3 with Transformers:

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

pipe = pipeline("text-generation", model="Mercury7353/PyLlama3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mercury7353/PyLlama3")
model = AutoModelForCausalLM.from_pretrained("Mercury7353/PyLlama3")
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

vLLM

How to use Mercury7353/PyLlama3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mercury7353/PyLlama3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mercury7353/PyLlama3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mercury7353/PyLlama3

SGLang

How to use Mercury7353/PyLlama3 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 "Mercury7353/PyLlama3" \
    --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": "Mercury7353/PyLlama3",
		"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 "Mercury7353/PyLlama3" \
        --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": "Mercury7353/PyLlama3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mercury7353/PyLlama3 with Docker Model Runner:
```
docker model run hf.co/Mercury7353/PyLlama3
```

Mercury7353 commited on Aug 2, 2024

Commit

721a51e

verified ·

1 Parent(s): 046f135

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -1,4 +1,4 @@
-<h1 align="center"> PyBench: Evaluate LLM Agent on Real World Tasks </h1>
 <p align="center">
 <a href="https://arxiv.org/abs/2407.16732">📃 Paper</a>
@@ -7,10 +7,11 @@
 •
 <a href="https://huggingface.co/Mercury7353/PyLlama3" >🤗 Model (PyLlama3)</a>
 •
-<a href=" https://github.com/Mercury7353/PyBench" > Code </a>
 •
 </p>
 PyBench is a comprehensive benchmark evaluating LLM on real-world coding tasks including **chart analysis**, **text analysis**, **image/ audio editing**, **complex math** and **software/website development**.
  We collect files from Kaggle, arXiv, and other sources and automatically generate queries according to the type and content of each file.

+<h1 align="center"> PyBench: Evaluate LLM Agent on Real World Coding Tasks </h1>
 <p align="center">
 <a href="https://arxiv.org/abs/2407.16732">📃 Paper</a>
 •
 <a href="https://huggingface.co/Mercury7353/PyLlama3" >🤗 Model (PyLlama3)</a>
 •
+<a href=" https://github.com/Mercury7353/PyBench" > 🚗Code </a>
 •
 </p>
+This is the PyLlama3 model, fine-tuned for <a href=" https://github.com/Mercury7353/PyBench" > PyBench </a>.
 PyBench is a comprehensive benchmark evaluating LLM on real-world coding tasks including **chart analysis**, **text analysis**, **image/ audio editing**, **complex math** and **software/website development**.
  We collect files from Kaggle, arXiv, and other sources and automatically generate queries according to the type and content of each file.