初始化项目，由ModelHub XC社区提供模型

Model: mshojaei77/gemma-3-4b-persian-v0 Source: Original Platform
2026-08-23 01:55:16 +08:00
commit b345862f26
21 changed files with 52591 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,115 @@
+---
+library_name: transformers
+language: fa
+tags:
+- persian
+- text-generation
+- qlora
+- 4-bit-quantization
+license: apache-2.0
+datasets:
+- mshojaei77/Persian_sft
+metrics:
+- bleu
+base_model:
+- google/gemma-3-4b-it
+---
+# Gemma 3-4B Persian (v0) 
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6556b1bb85d43542fa1a8f91/YY9cRRv1u_kBORuiKlr98.png)
+`mshojaei77/gemma-3-4b-persian-v0` is a Persian-specialized model built on the Gemma 3 architecture. It leverages QLoRA for 4-bit quantization to reduce computational overhead while generating and understanding Persian text. In addition to text generation, the model also retains image input capabilities inherited from its base model.
+
+## Usage
+
+This model is compatible with both the Hugging Face Transformers library and Ollama.
+
+### Running with Ollama
+
+```bash
+ollama run mshojaei77/gemma3persian
+```
+
+### Running with Hugging Face Transformers
+
+1. **Install Dependencies:**
+
+   ```bash
+   pip install git+https://github.com/huggingface/transformers@v4.49.0-Gemma-3 accelerate
+   ```
+
+2. **Load Model and Tokenizer:**
+
+   ```python
+   from transformers import AutoModelForCausalLM, AutoTokenizer
+   import torch
+
+   model_id = "mshojaei77/gemma-3-4b-persian-v0"
+
+   model = AutoModelForCausalLM.from_pretrained(
+       model_id,
+       device_map="auto",  # Use "cuda" for GPU usage if available
+       torch_dtype=torch.bfloat16,  # Alternatively, use torch.float16
+   )
+   tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+   messages = [
+       {
+           "role": "user",
+           "content": "توماس جفرسون کیست؟"
+       }
+   ]
+   inputs = tokenizer.apply_chat_template(
+       messages,
+       add_generation_prompt=True, tokenize=True, return_tensors="pt"
+   ).to(model.device)
+
+   outputs = model.generate(**inputs, max_new_tokens=200)
+   print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+   ```
+
+## Training Data and Fine-Tuning
+
+### Training Dataset
+
+This model was fine-tuned using the [mshojaei77/Persian_sft](https://huggingface.co/datasets/mshojaei77/Persian_sft) dataset, which contains approximately 681,000 rows of Persian text focused on instruction-following and conversational interactions. The dataset features:
+
+### Fine-Tuning
+
+- **Method:** Supervised Fine-Tuning (SFT) using QLoRA (4-bit quantization)  
+- **Hardware:** one T4 GPU  
+- **Software:** Utilizes Hugging Face Transformers, with supporting libraries like `peft` for QLoRA and `bitsandbytes` for quantization  
+- **Trade-offs:** Reduced memory footprint at the expense of some precision compared to full-precision models
+
+## Evaluation
+
+[SOON]
+
+## Usage Considerations and Limitations
+
+### Intended Use Cases
+
+- **Question Answering:** Responding accurately to Persian language queries
+- **Instruction Following:** Interpreting and executing text-based instructions in Persian
+- **Text Generation:** Producing fluent, context-aware Persian content
+- **Conversational AI:** Integrating into chatbots and virtual assistants
+- **Image Processing:** Retaining image input capabilities from the base model
+
+### Limitations
+
+- **Quantization Impact:** 4-bit quantization may reduce output precision and result in occasional incoherent responses.
+- **Evaluation Scope:** Absence of comprehensive evaluation metrics specific to this variant.
+- **Bias:** The model might mirror biases present in both the original Gemma 3 data and the Persian_sft dataset.
+- **Hallucination:** As with all LLMs, there is a risk of generating plausible-sounding but inaccurate information.
+- **Safety:** The model has not undergone safety tuning, so extra caution is advised when deploying in sensitive contexts.
+
+## Maintenance and Future Work
+
+This model is under active maintenance. Future updates may include:
+
+- Additional evaluation metrics and benchmarks
+- Enhanced safety tuning and bias mitigation strategies
+- Expanded documentation and usage examples
+- Incorporation of community feedback for iterative improvements
+
+For any queries, contributions, or issues, please contact me.