Instructions to use Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3 with Transformers:

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

pipe = pipeline("text-generation", model="Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3")
model = AutoModelForCausalLM.from_pretrained("Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3")
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

vLLM

How to use Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3

SGLang

How to use Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3 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 "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3" \
    --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": "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3",
		"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 "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3" \
        --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": "Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3 with Docker Model Runner:
```
docker model run hf.co/Trelis/Mixtral-8x7B-Instruct-v0.1-function-calling-v3
```

How to use it with vLLM

by sadaq19 - opened Mar 27, 2024

Discussion

sadaq19

Mar 27, 2024

I'm having issue using the model on vLLM. I just don't know how to write the body of the request (API) for the function calling

sadaq19 changed discussion title from How to use it owith vLLM to How to use it with vLLM Mar 27, 2024

RonanMcGovern

Trelis org Mar 28, 2024

Try this video: https://www.youtube.com/watch?v=hHn_cV5WUDI

and you can also tweak a vllm template from the one-click-llms repo on github under TrelisResearch.

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