Instructions to use LeoLM/leo-mistral-hessianai-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LeoLM/leo-mistral-hessianai-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="LeoLM/leo-mistral-hessianai-7b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LeoLM/leo-mistral-hessianai-7b-chat")
model = AutoModelForCausalLM.from_pretrained("LeoLM/leo-mistral-hessianai-7b-chat")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LeoLM/leo-mistral-hessianai-7b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LeoLM/leo-mistral-hessianai-7b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeoLM/leo-mistral-hessianai-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LeoLM/leo-mistral-hessianai-7b-chat

SGLang

How to use LeoLM/leo-mistral-hessianai-7b-chat 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 "LeoLM/leo-mistral-hessianai-7b-chat" \
    --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": "LeoLM/leo-mistral-hessianai-7b-chat",
		"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 "LeoLM/leo-mistral-hessianai-7b-chat" \
        --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": "LeoLM/leo-mistral-hessianai-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LeoLM/leo-mistral-hessianai-7b-chat with Docker Model Runner:
```
docker model run hf.co/LeoLM/leo-mistral-hessianai-7b-chat
```

Jupyter notebook and embedding model suggestion ?

by Tim1785 - opened Dec 2, 2023

Discussion

Tim1785

Dec 2, 2023

Hi, I am wondering if there is a jupyternotebook that could be used to play around with. I am wondering also which particular embedding model should be used together with llama index for RAG related applications?

Lue-C

Jan 12, 2024

Hi Tim1785,
the embedding model depends very much on the language and also somehow on the data you want to feed your RAG application with. I currently use this one https://huggingface.co/intfloat/multilingual-e5-base
for a German application. Did you make progress on your RAG app?

Tim1785

Jan 22, 2024

Hi , i actually used , exactly the embedding model you used and mistral 7b instruct version 1. It yeielded descent results

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