Instructions to use borekboissy/Millesime-2026-4b-phase2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use borekboissy/Millesime-2026-4b-phase2 with Transformers:

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

pipe = pipeline("text-generation", model="borekboissy/Millesime-2026-4b-phase2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("borekboissy/Millesime-2026-4b-phase2")
model = AutoModelForCausalLM.from_pretrained("borekboissy/Millesime-2026-4b-phase2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use borekboissy/Millesime-2026-4b-phase2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "borekboissy/Millesime-2026-4b-phase2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "borekboissy/Millesime-2026-4b-phase2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/borekboissy/Millesime-2026-4b-phase2

SGLang

How to use borekboissy/Millesime-2026-4b-phase2 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 "borekboissy/Millesime-2026-4b-phase2" \
    --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": "borekboissy/Millesime-2026-4b-phase2",
		"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 "borekboissy/Millesime-2026-4b-phase2" \
        --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": "borekboissy/Millesime-2026-4b-phase2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use borekboissy/Millesime-2026-4b-phase2 with Docker Model Runner:
```
docker model run hf.co/borekboissy/Millesime-2026-4b-phase2
```

Millesime-202608-4B-phase2

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 on the comparia_dpo dataset. It achieves the following results on the evaluation set:

Loss: 0.8321
Rewards/chosen: 1.1462
Rewards/rejected: -3.0919
Rewards/accuracies: 0.7660
Rewards/margins: 4.2381
Logps/chosen: -1016.5903
Logps/rejected: -1058.3787
Logits/chosen: -3.0804
Logits/rejected: -3.1843

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/chosen	Logps/rejected	Logits/chosen	Logits/rejected
0.7084	0.1055	50	0.5794	-1.2842	-3.4253	0.7372	2.1411	-1040.8944	-1061.7122	-2.9093	-3.0172
1.3953	0.2110	100	0.9903	-0.9245	-5.2865	0.7340	4.3620	-1037.2972	-1080.3245	-3.0515	-3.1622
1.1409	0.3165	150	1.0129	1.0182	-2.7772	0.7468	3.7955	-1017.8700	-1055.2316	-3.0271	-3.1316
1.2015	0.4221	200	1.0720	0.2541	-4.8643	0.7468	5.1184	-1025.5115	-1076.1021	-2.9604	-3.0636
1.4030	0.5276	250	1.0206	2.6027	-1.4402	0.7276	4.0430	-1002.0249	-1041.8613	-2.9602	-3.0647
2.0725	0.6331	300	0.9071	-0.4076	-5.2369	0.7788	4.8293	-1032.1279	-1079.8281	-3.0332	-3.1352
0.5974	0.7386	350	0.8837	0.7087	-3.8638	0.7821	4.5724	-1020.9659	-1066.0969	-3.0906	-3.1961
0.7703	0.8441	400	0.8303	0.3155	-4.1147	0.7821	4.4302	-1024.8973	-1068.6063	-3.0833	-3.1875
0.8016	0.9496	450	0.8429	1.1231	-3.0798	0.7756	4.2030	-1016.8212	-1058.2578	-3.0821	-3.1860
0.7013	1.0	474	0.8321	1.1462	-3.0919	0.7660	4.2381	-1016.5903	-1058.3787	-3.0804	-3.1843

Framework versions

Transformers 5.8.0
Pytorch 2.13.0+cu130
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 216

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for borekboissy/Millesime-2026-4b-phase2

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(2102)

this model