---
base_model: ALLaM-AI/ALLaM-7B-Instruct-preview
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---

# Uploaded  model

- **Developed by:** maanaar
- **License:** apache-2.0
- **Finetuned from model :** ALLaM-AI/ALLaM-7B-Instruct-preview

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)


# maanaar/allam7b-sft-arabic-grammar-eerab

Fine-tuned ALLaM-7B model for Arabic Q&A and grammar tasks.

## Usage

```python
from unsloth import FastLanguageModel
import torch

model_name = "maanaar/allam7b-sft-arabic-grammar-eerab"

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=model_name,
    max_seq_length=2048,
    dtype=None,         # auto-detect
    load_in_4bit=True,  # saves GPU memory
)

messages = [
    {"role": "user", "content": "ما اعراب جملة لا اله الا الله"}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

outputs = model.generate(
    **tokenizer(text, return_tensors="pt").to(model.device),
    max_new_tokens=256,
    temperature=0.7,
    top_p=0.8,
    top_k=20
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))