Instructions to use chargoddard/llama3-42b-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chargoddard/llama3-42b-v0 with Transformers:

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

pipe = pipeline("text-generation", model="chargoddard/llama3-42b-v0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chargoddard/llama3-42b-v0")
model = AutoModelForCausalLM.from_pretrained("chargoddard/llama3-42b-v0", 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 chargoddard/llama3-42b-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chargoddard/llama3-42b-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chargoddard/llama3-42b-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chargoddard/llama3-42b-v0

SGLang

How to use chargoddard/llama3-42b-v0 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 "chargoddard/llama3-42b-v0" \
    --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": "chargoddard/llama3-42b-v0",
		"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 "chargoddard/llama3-42b-v0" \
        --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": "chargoddard/llama3-42b-v0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chargoddard/llama3-42b-v0 with Docker Model Runner:
```
docker model run hf.co/chargoddard/llama3-42b-v0
```

Hoping this work out well!

by Olafangensan - opened Apr 21, 2024

Discussion

Olafangensan

Apr 21, 2024

I was so annoyed that there wasn't an in-between model for llama 3 family. 8b is great, but it's no 70b.

Having a 42b means that anyone with a 3090/4090 might actually get to play with a quantized SOTA model.

Bless you, sir!

chargoddard

Owner Apr 21, 2024

Me too! I have a 3090 locally and that VRAM size has been increasingly neglected lately. Hopefully it works out.

Thanks for the support!

JayhC

Apr 21, 2024

Very interesting! Any plans on doing the same with instruct version?

jukofyork

Apr 21, 2024

Wow, really interesting!

This gives some hope of running the llama-405b monster!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment