Instructions to use NousResearch/Llama-2-7b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Llama-2-7b-hf with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Llama-2-7b-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-hf")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Llama-2-7b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Llama-2-7b-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Llama-2-7b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/Llama-2-7b-hf

SGLang

How to use NousResearch/Llama-2-7b-hf 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 "NousResearch/Llama-2-7b-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Llama-2-7b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NousResearch/Llama-2-7b-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Llama-2-7b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/Llama-2-7b-hf with Docker Model Runner:
```
docker model run hf.co/NousResearch/Llama-2-7b-hf
```

FFN is not the same as https://huggingface.co/meta-llama/Llama-2-7b-hf

by Muennighoff - opened Oct 14, 2023

Discussion

Muennighoff

Oct 14, 2023

I am seeing tiny differences in the FFN hence the performance does also not match exactly w/ meta-llama/Llama-2-7b-hf

teknium

NousResearch org Oct 15, 2023

I am seeing tiny differences in the FFN hence the performance does also not match exactly w/ meta-llama/Llama-2-7b-hf

Whats the cause?

alpindale

Oct 20, 2023

I just checked the checkpoint hashes and they all seem to match. The meta-llama repo updated the pytorch binaries with FP16 variants, but I matched the ones here (FP32) against the older commits:

PyTorch bins

ckpt 1 - Nous / ckpt 1 - meta
ckpt 2 - Nous / ckpt 2 - meta
ckpt 3 - Nous / ckpt 3 - meta

Safetensors

ckpt 1 - Nous / ckpt 1 - meta
ckpt 2 - Nous / ckpt 2 - meta

I'd perhaps recommend swapping the misc files (such as the JSON files) with the official ones in the meta repo.

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