Instructions to use reach-vb/Devstral-Small-2505 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reach-vb/Devstral-Small-2505 with Transformers:

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

pipe = pipeline("text-generation", model="reach-vb/Devstral-Small-2505")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("reach-vb/Devstral-Small-2505")
model = AutoModelForMultimodalLM.from_pretrained("reach-vb/Devstral-Small-2505")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reach-vb/Devstral-Small-2505 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reach-vb/Devstral-Small-2505"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reach-vb/Devstral-Small-2505",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/reach-vb/Devstral-Small-2505

SGLang

How to use reach-vb/Devstral-Small-2505 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 "reach-vb/Devstral-Small-2505" \
    --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": "reach-vb/Devstral-Small-2505",
		"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 "reach-vb/Devstral-Small-2505" \
        --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": "reach-vb/Devstral-Small-2505",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use reach-vb/Devstral-Small-2505 with Docker Model Runner:
```
docker model run hf.co/reach-vb/Devstral-Small-2505
```

Devstral-Small-2505 / assets /swe_bench.png

reach-vb

Duplicate from mistralai/Devstral-Small-2505

014a78d verified about 1 year ago

download

history blame contribute delete

113 kB

Xet Pointer Details

( Raw pointer file )

Xet hash:: 303bb07439e1fda7c731a791cb290d2db4d001c81cfa669ab875154693a3fdbc
Size of remote file:: 113 kB
SHA256:: ccfcfc1b8546fb57a82a99a37e55757ddc971f3b8126701811a81cd63d146d10

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