初始化项目，由ModelHub XC社区提供模型

Model: kurakurai/Luth-LFM2-1.2B Source: Original Platform
2026-07-14 00:17:05 +08:00
commit 5804c608e4
14 changed files with 4400 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,96 @@
+---
+library_name: transformers
+license: other
+license_name: lfm1.0
+license_link: LICENSE
+datasets:
+- kurakurai/luth-sft
+language:
+- fr
+- en
+base_model:
+- LiquidAI/LFM2-1.2B
+pipeline_tag: text-generation
+tags:
+- liquid
+- lfm2
+- luth
+---
+
+![Luth x LFM2](media/logo_collab.png)
+
+
+# Luth-LFM2-1.2B
+
+**Luth-LFM2-1.2B** is a French fine-tuned version of [LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B) in collaboration with Liquid AI, trained on the [Luth-SFT](https://huggingface.co/datasets/kurakurai/luth-sft) dataset. The model has improved its French capabilities in instruction following, math, and general knowledge. Additionally, its English capabilities have remained stable or slightly improved such as in Maths.
+
+Our Evaluation, training and data scripts are available on [GitHub](https://github.com/kurakurai/Luth), along with the [Blog](https://huggingface.co/blog/MaxLSB/luth) we wrote, to further detail our recipe.
+
+![Luth-LFM2 graph](media/lfm2-luth.png)
+
+## Model Details
+
+The model was trained using full fine-tuning on the Luth-SFT dataset with [Axolotl](https://github.com/axolotl-ai-cloud/axolotl). The resulting model was then merged back with LFM2-1.2B. This process successfully retained the model's English capabilities while improving its performance in French.
+
+## Benchmark Results
+
+We used LightEval for evaluation, with custom tasks for the French benchmarks. The models were evaluated with a `temperature=0`.
+
+### French Benchmark Scores
+
+| Model                 | IFEval<br>French | GPQA-Diamond<br>French | MMLU<br>French | Math500<br>French | Arc-Challenge<br>French | Hellaswag<br>French |
+| --------------------- | ---------------- | ---------------------- | -------------- | ----------------- | ----------------------- | ------------------- |
+| **Luth-LFM2-1.2B**    | <u>59.95</u>     | 28.93                  | <u>48.02</u>   | 45.80             | 38.98                   | 36.81               |
+| LFM2-1.2B             | 54.41            | 22.84                  | 47.59          | 36.80             | <u>39.44</u>            | 33.05               |
+| Qwen3-1.7B            | 54.71            | <u>31.98</u>           | 28.49          | <u>60.40</u>      | 33.28                   | 24.86               |
+| SmolLM2-1.7B-Instruct | 30.93            | 20.30                  | 33.73          | 10.20             | 28.57                   | <u>49.58</u>        |
+| Qwen2.5-1.5B-Instruct | 31.30            | 27.41                  | 46.25          | 33.20             | 32.68                   | 34.33               |
+
+### English Benchmark Scores
+
+| Model                 | IFEval<br>English | GPQA-Diamond<br>English | MMLU<br>English | Math500<br>English | Arc-Challenge<br>English | Hellaswag<br>English |
+| --------------------- | ----------------- | ----------------------- | --------------- | ------------------ | ------------------------ | -------------------- |
+| **Luth-LFM2-1.2B**    | <u>70.55</u>      | 30.30                   | 54.58           | 50.60              | <u>43.26</u>             | 58.42                |
+| LFM2-1.2B             | 68.52             | 24.24                   | 55.22           | 45.80              | 42.58                    | 57.61                |
+| Qwen3-1.7B            |  68.88            | <u>31.82<u>             | 52.82           | <u>71.20</u>       | 36.18                    | 46.98                |
+| SmolLM2-1.7B-Instruct | 49.04             | 25.08                   | 50.27           | 22.67              | 42.32                    | <u>66.94</u>            |
+| Qwen2.5-1.5B-Instruct | 39.99             | 25.76                   | <u>59.81</u>    | 57.20              | 41.04                    |  64.48          |
+
+
+## Code Example
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("kurakurai/Luth-LFM2-1.2B")
+model = AutoModelForCausalLM.from_pretrained("kurakurai/Luth-LFM2-1.2B")
+messages = [
+    {"role": "user", "content": "Quelle est la capitale de la France?"},
+]
+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=100)
+print(
+    tokenizer.decode(
+        outputs[0][inputs["input_ids"].shape[-1] :], skip_special_tokens=True
+    )
+)
+```
+
+## Citation
+
+```bibtex
+@misc{luth2025kurakurai,
+  title        = {Luth: Efficient French Specialization for Small Language Models and Cross-Lingual Transfer},
+  author       = {Lasbordes, Maxence and Gad, Sinoué},
+  year         = {2025},
+  howpublished = {\url{https://arxiv.org/abs/2510.05846}},
+  note         = {arXiv:2510.05846}
+}
+```