初始化项目，由ModelHub XC社区提供模型

Model: soynade-research/oolel-lit-gemma Source: Original Platform
2026-04-22 15:59:49 +08:00
commit 62325d65bd
17 changed files with 52930 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,96 @@
+---
+license: agpl-3.0
+datasets:
+- soynade-research/FineWeb2-HQ-50k-Wolof
+language:
+- wo
+- en
+- fr
+base_model:
+- google/gemma-3-270m-it
+pipeline_tag: text-generation
+---
+
+# Oolel-lit-gemma
+
+Oolel-lit-gemma is a fine-tuned version of [Gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it)
+for the Wolof language. It is part of our Oolel family of compact, on-device Wolof language models
+developed.
+
+The model was trained using supervised fine-tuning (SFT) on synthetic data distilled from our
+larger **Oolel-7B** models via [Oolel-translator](https://github.com/soynade-research/oolel-translator).
+
+
+## Usage
+
+### Quick start with pipeline
+
+```python
+from transformers import pipeline
+
+generator = pipeline(
+    "text-generation",
+    model="soynade-research/oolel-lit-gemma",
+    device="cuda",
+)
+
+messages = [{"role": "user", "content": "Translate to Wolof: The president is 45 years old."}]
+
+output = generator(messages, max_new_tokens=256, return_full_text=False)
+print(output["generated_text"])
+```
+### With AutoModel for more control
+
+```python
+from transformers import AutoTokenizer, Gemma3ForCausalLM
+import torch
+
+model_id = "soynade-research/oolel-lit-gemma"
+
+
+model = Gemma3ForCausalLM.from_pretrained(
+    model_id
+).eval()
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    [
+        {
+            "role": "system",
+            "content": [{"type": "text", "text": "You're a Wolof AI assistant. Please always provide detailed and useful answers to the user queries."},]
+        },
+        {
+            "role": "user",
+            "content": [{"type": "text", "text": "Translate to Wolof: The president is 45 years old."},]
+        },
+    ],
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device).to(torch.bfloat16)
+
+
+with torch.inference_mode():
+    outputs = model.generate(**inputs, max_new_tokens=256,         
+                             do_sample=True,
+                             temperature=0.7,
+                             top_p=0.9,)
+
+outputs = tokenizer.batch_decode(outputs)
+
+
+``` 
+## Training
+The training code and configuration are available at
+[soynade-research/oolel-trainer.](https://github.com/soynade-research/oolel-trainer)
+
+## Limitations
+- Primarily optimized for Wolof; performance on other languages may vary
+- As a 270M parameter model, it may struggle with complex tasks
+- Outputs should be verified by a native Wolof speaker for critical applications