Instructions to use ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco with Transformers:

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

pipe = pipeline("text-generation", model="ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco")
model = AutoModelForCausalLM.from_pretrained("ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco

SGLang

How to use ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco 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 "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco" \
    --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": "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco",
		"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 "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco" \
        --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": "ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco with Docker Model Runner:
```
docker model run hf.co/ArnaudHureaux/Llama-2-70b-chat-hf-miniguanaco
```

Llama-2-70b-chat-hf-miniguanaco / pytorch_model-00008-of-00015.bin

ArnaudHureaux

Upload LlamaForCausalLM

0f306a4 over 2 years ago

download

history blame contribute delete

9.8 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: be6a1ccf344037a46c2811b578ceb150d62b3b9faae94af09dbfa41d2d567ead
Size of remote file:: 9.8 GB
SHA256:: 29e9f9cef88958a5e48cfcca9b2739ceb0142755894c81d020689c1f7ebe41e8

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.