Instructions to use NousResearch/Llama-2-13b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Llama-2-13b-hf with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Llama-2-13b-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Llama-2-13b-hf")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-13b-hf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Llama-2-13b-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Llama-2-13b-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-2-13b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/Llama-2-13b-hf

SGLang

How to use NousResearch/Llama-2-13b-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-2-13b-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-2-13b-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-2-13b-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-2-13b-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/Llama-2-13b-hf with Docker Model Runner:
```
docker model run hf.co/NousResearch/Llama-2-13b-hf
```

code for downloading

by idormoy - opened Jul 24, 2023

Discussion

idormoy

Jul 24, 2023

Hi,
could you please provide code for downloading?
I am trying

from transformers import AutoTokenizer
import transformers
import torch

model = "NousResearch/Llama-2-13b-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)

but I am getting this error: ValueError: Tokenizer class LlamaTokenizer does not exist or is not currently imported.

Thanks!

idormoy

Jul 26, 2023

using the last version of HF fixed it

%pip install git+https://github.com/huggingface/transformers

idormoy changed discussion status to closed Jul 26, 2023

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