Instructions to use Ailiance-fr/devstral-v3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ailiance-fr/devstral-v3-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Devstral-Small-2507-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Ailiance-fr/devstral-v3-sft")

Transformers

How to use Ailiance-fr/devstral-v3-sft with Transformers:

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

pipe = pipeline("text-generation", model="Ailiance-fr/devstral-v3-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ailiance-fr/devstral-v3-sft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ailiance-fr/devstral-v3-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ailiance-fr/devstral-v3-sft

SGLang

How to use Ailiance-fr/devstral-v3-sft 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 "Ailiance-fr/devstral-v3-sft" \
    --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": "Ailiance-fr/devstral-v3-sft",
		"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 "Ailiance-fr/devstral-v3-sft" \
        --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": "Ailiance-fr/devstral-v3-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Ailiance-fr/devstral-v3-sft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ailiance-fr/devstral-v3-sft to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ailiance-fr/devstral-v3-sft",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ailiance-fr/devstral-v3-sft with Docker Model Runner:
```
docker model run hf.co/Ailiance-fr/devstral-v3-sft
```

clemsail commited on 1 day ago

Commit

7a1cb9f

verified ·

1 Parent(s): 8dbae86

docs: add upstream base model official evaluations

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -157,3 +157,27 @@ This model is referenced in the [Ailiance benchmark suite](https://github.com/ai
 See the full scoreboard:
 [ailiance-bench README#scoreboard-lora-phase-6](https://github.com/ailiance/ailiance-bench#scoreboard-lora-phase-6--2026-05-11).

 See the full scoreboard:
 [ailiance-bench README#scoreboard-lora-phase-6](https://github.com/ailiance/ailiance-bench#scoreboard-lora-phase-6--2026-05-11).
+## Upstream base model — official evaluations
+This LoRA fine-tunes [`mistralai/Devstral-Small-2-24B-Instruct-2512`](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512),
+Mistral's coding-specialist LLM. Headline software-engineering benchmarks
+from the upstream model card:
+| Benchmark                | Devstral Small 2 (24B) | Devstral 2 (123B) | DeepSeek v3.2 (671B) | Claude Sonnet 4.5 |
+|--------------------------|-----------------------:|------------------:|---------------------:|------------------:|
+| **SWE Bench Verified**   | **68.0 %**             | 72.2 %            | 73.1 %               | 77.2 %            |
+| **SWE Bench Multilingual** | **55.7 %**           | 61.3 %            | 70.2 %               | 68.0 %            |
+| **Terminal Bench 2**     | **22.5 %**             | 32.6 %            | 46.4 %               | 42.8 %            |
+(For reference, GPT-5.1 Codex High: 73.7 % SWE Verified · 52.8 % Terminal Bench 2.)
+Devstral Small 2 (24B) is competitive with much larger open models on
+SWE Bench Verified (e.g. matches GLM-4.6 at 355B). Architecture uses
+rope-scaling per Llama 4 + Scalable-Softmax ([arXiv:2501.19399](https://arxiv.org/abs/2501.19399)).
+**Source:** [official Devstral-Small-2-24B-Instruct-2512 model card](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512).
+> **Reading these alongside this LoRA:** Devstral Small 2 is a strong
+> coding base. This LoRA inherits its SWE-Bench performance and adds
+> language- or domain-specific specialization.