Instructions to use lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2

SGLang

How to use lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2 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 "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2" \
    --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": "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2",
		"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 "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2" \
        --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": "lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2 with Docker Model Runner:
```
docker model run hf.co/lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2
```

exl2 quant (measurement.json in main branch)

check revisions for quants

Mistral-Small-3.1-DRAFT-0.5B

This model is meant to be used as draft model for speculative decoding with mistralai/Mistral-Small-3.1-24B-Instruct-2503 or mistralai/Mistral-Small-24B-Instruct-2501

Data info

The data are Mistral's outputs and includes all kind of tasks from various datasets in English, French, German, Spanish, Italian and Portuguese. It has been trained for 2 epochs on 20k unique examples, for a total of 12 million tokens per epoch.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2

Base model

Qwen/Qwen2.5-0.5B

Finetuned

alamios/Qwenstral-Small-3.1-0.5B

Finetuned

(3)

this model

lucyknada
/

alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2

exl2 quant (measurement.json in main branch)

check revisions for quants

Mistral-Small-3.1-DRAFT-0.5B

Data info

Model tree for lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2

Dataset used to train lucyknada/alamios_Mistral-Small-3.1-DRAFT-0.5B-exl2