52 lines
1.3 KiB
Markdown
52 lines
1.3 KiB
Markdown
---
|
|
library_name: transformers
|
|
tags:
|
|
- arabic
|
|
- sft
|
|
- qwen
|
|
---
|
|
|
|
# Qwen3-8B-SFT
|
|
|
|
## Model Details
|
|
|
|
- **Developed by:** Mushari Alothman
|
|
- **Model type:** Causal Language Model
|
|
- **Language(s):** Arabic, English
|
|
- **License:** Apache 2.0
|
|
- **Finetuned from:** Qwen3-8B-Base
|
|
|
|
This is a supervised fine-tuned (SFT) Qwen3-8B model optimized for accurate, clean supervision across Arabic and English tasks.
|
|
|
|
## Intended Uses
|
|
|
|
### Direct Use
|
|
- Arabic & English MCQ answering
|
|
- Context-based QA / RAG
|
|
- General instruction following
|
|
|
|
### Out-of-Scope Use
|
|
- Safety-critical or real-time decision making
|
|
- Generating factual guarantees without verification
|
|
|
|
## Training Summary
|
|
|
|
- **Training type:** Supervised Fine-Tuning (SFT)
|
|
- **Precision:** bf16 mixed precision
|
|
- **Data:** Curated Arabic & English datasets including:
|
|
- MCQ
|
|
- QA / RAG / context understanding
|
|
- General instruction data
|
|
|
|
## How to Use
|
|
|
|
```python
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("Mushari440/Qwen3-8B-SFT-chatml")
|
|
model = AutoModelForCausalLM.from_pretrained("Mushari440/Qwen3-8B-SFT-chatml")
|
|
|
|
inputs = tokenizer("سؤال: ما عاصمة السعودية؟", return_tensors="pt")
|
|
outputs = model.generate(**inputs, max_new_tokens=50)
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|