Instructions to use minpeter/Voxtral-Mini-3B-Text-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minpeter/Voxtral-Mini-3B-Text-2507 with Transformers:

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

pipe = pipeline("text-generation", model="minpeter/Voxtral-Mini-3B-Text-2507")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("minpeter/Voxtral-Mini-3B-Text-2507", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use minpeter/Voxtral-Mini-3B-Text-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minpeter/Voxtral-Mini-3B-Text-2507"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minpeter/Voxtral-Mini-3B-Text-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/minpeter/Voxtral-Mini-3B-Text-2507

SGLang

How to use minpeter/Voxtral-Mini-3B-Text-2507 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 "minpeter/Voxtral-Mini-3B-Text-2507" \
    --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": "minpeter/Voxtral-Mini-3B-Text-2507",
		"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 "minpeter/Voxtral-Mini-3B-Text-2507" \
        --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": "minpeter/Voxtral-Mini-3B-Text-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use minpeter/Voxtral-Mini-3B-Text-2507 with Docker Model Runner:
```
docker model run hf.co/minpeter/Voxtral-Mini-3B-Text-2507
```

Voxtral-Mini-3B-Text-2507 / params.json

minpeter

Upload folder using huggingface_hub

41b11d1 verified about 1 year ago

Raw History Blame Contribute Delete

222 Bytes

	{
	"dim": 3072,
	"n_layers": 30,
	"head_dim": 128,
	"hidden_dim": 8192,
	"n_heads": 32,
	"n_kv_heads": 8,
	"rope_theta": 100000000.0,
	"norm_eps": 1e-05,
	"vocab_size": 131072,
	"max_position_embeddings": 32768
	}