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 18 days ago

Commit

611a651

verified ·

1 Parent(s): afb5696

chore: upload lm-eval-harness results

Browse files

Files changed (1) hide show

evals/results_2026-04-15T15-32-15.795505.json +140 -0

evals/results_2026-04-15T15-32-15.795505.json ADDED Viewed

	@@ -0,0 +1,140 @@

+{
+  "results": {
+    "ifeval": {
+      "alias": "ifeval",
+      "prompt_level_strict_acc,none": 0.6913123844731978,
+      "prompt_level_strict_acc_stderr,none": 0.019879245251116444,
+      "inst_level_strict_acc,none": 0.7733812949640287,
+      "inst_level_strict_acc_stderr,none": "N/A",
+      "prompt_level_loose_acc,none": 0.7245841035120147,
+      "prompt_level_loose_acc_stderr,none": 0.01922392319624193,
+      "inst_level_loose_acc,none": 0.8009592326139089,
+      "inst_level_loose_acc_stderr,none": "N/A"
+    }
+  },
+  "group_subtasks": {
+    "ifeval": []
+  },
+  "configs": {
+    "ifeval": {
+      "task": "ifeval",
+      "dataset_path": "google/IFEval",
+      "test_split": "train",
+      "doc_to_text": "prompt",
+      "doc_to_target": 0,
+      "unsafe_code": false,
+      "process_results": "def process_results(doc, results):\n    inp = InputExample(\n        key=doc[\"key\"],\n        instruction_id_list=doc[\"instruction_id_list\"],\n        prompt=doc[\"prompt\"],\n        kwargs=doc[\"kwargs\"],\n    )\n    response = results[0]\n\n    out_strict = test_instruction_following_strict(inp, response)\n    out_loose = test_instruction_following_loose(inp, response)\n\n    return {\n        \"prompt_level_strict_acc\": out_strict.follow_all_instructions,\n        \"inst_level_strict_acc\": out_strict.follow_instruction_list,\n        \"prompt_level_loose_acc\": out_loose.follow_all_instructions,\n        \"inst_level_loose_acc\": out_loose.follow_instruction_list,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "default",
+        "split": null,
+        "process_docs": null,
+        "fewshot_indices": null,
+        "samples": null,
+        "doc_to_text": "prompt",
+        "doc_to_choice": null,
+        "doc_to_target": 0,
+        "gen_prefix": null,
+        "fewshot_delimiter": "\n\n",
+        "target_delimiter": " "
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "prompt_level_strict_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "inst_level_strict_acc",
+          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
+          "higher_is_better": true
+        },
+        {
+          "metric": "prompt_level_loose_acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "inst_level_loose_acc",
+          "aggregation": "def agg_inst_level_acc(items):\n    flat_items = [item for sublist in items for item in sublist]\n    inst_level_acc = sum(flat_items) / len(flat_items)\n    return inst_level_acc\n",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [],
+        "do_sample": false,
+        "temperature": 0.0,
+        "max_gen_toks": 1280
+      },
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 4.0,
+        "base_url": "http://localhost:8000/v1/chat/completions",
+        "model": "devstral",
+        "num_concurrent": 1
+      }
+    }
+  },
+  "versions": {
+    "ifeval": 4.0
+  },
+  "n-shot": {
+    "ifeval": 0
+  },
+  "higher_is_better": {
+    "ifeval": {
+      "prompt_level_strict_acc": true,
+      "inst_level_strict_acc": true,
+      "prompt_level_loose_acc": true,
+      "inst_level_loose_acc": true
+    }
+  },
+  "n-samples": {
+    "ifeval": {
+      "original": 541,
+      "effective": 541
+    }
+  },
+  "config": {
+    "model": "local-chat-completions",
+    "model_args": {
+      "base_url": "http://localhost:8000/v1/chat/completions",
+      "model": "devstral",
+      "num_concurrent": 1
+    },
+    "batch_size": "1",
+    "batch_sizes": [],
+    "device": "cuda:0",
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": {},
+    "random_seed": 0,
+    "numpy_seed": 1234,
+    "torch_seed": 1234,
+    "fewshot_seed": 1234
+  },
+  "git_hash": null,
+  "date": 1776256793.262322,
+  "pretty_env_info": "N/A (torch not installed)",
+  "transformers_version": "N/A",
+  "lm_eval_version": "0.4.11",
+  "upper_git_hash": null,
+  "task_hashes": {
+    "ifeval": "33ea6c342001769a1e568f8fb1f146e8b8c2d7ad1420ed0770c7e67a7a121685"
+  },
+  "model_source": "local-chat-completions",
+  "model_name": "devstral",
+  "model_name_sanitized": "devstral",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "fewshot_as_multiturn": true,
+  "chat_template": "",
+  "chat_template_sha": null,
+  "total_evaluation_time_seconds": "3143.920960575342"
+}