README.md

---
license: apache-2.0
---



For Inference:

- Download dependencies:
```bash
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps trl peft accelerate bitsandbytes triton xformers
```


- Infer part:

```python

from operator import index
from unsloth import FastLanguageModel
import torch

max_seq_length = 2048 # Choose any! Llama 3 is up to 8k
dtype = None
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

alpaca_prompt = """ حلل العاطفة متاع النص الموجود بين الأقواس المربعة، وقرّر إذا كان إيجابي ولا سلبي، ورجع الجواب كعلامة عاطفية متطابقة "إيجابي" ولا "سلبي".

### Instruction:
{}

### Response:
{}"""

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "hedhoud12/Llama-3.2-1B-Instruct_Tunisian_sentiment_analysis", # your trained model
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model)


inputs = tokenizer(
[
    alpaca_prompt.format(
        "برا وليدي رابي يناجحك", # instruction
        "", # output - leave this blank for generation!
    )
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
tokenizer.batch_decode(outputs)[0].split("### Response:")[1].strip()
```

- The result will be like :
```bash
==((====))==  Unsloth 2024.9.post4: Fast Llama patching. Transformers = 4.44.2.
   \\   /|    GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.
O^O/ \_/ \    Pytorch: 2.4.1+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.
\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.28.post1. FA2 = False]
 "-____-"     Free Apache license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
كلام إيجابي<|eot_id|>
```