Fine-Tuning-Gemma-2b-it-for-Arabic

This model is a fine-tuned version of google/gemma-2b-it on arbml/CIDAR Arabic dataset.

It achieves the following results on the evaluation set:

  • training_loss=2.281057505607605

Direct Use

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic"
messages = [{"role": "user", "content": "ما هو الذكاء الاصطناعي؟"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Downloads last month
64
Safetensors
Model size
2.51B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic

Base model

google/gemma-2b-it
Finetuned
(49)
this model
Finetunes
1 model

Dataset used to train Ruqiya/Fine-Tuning-Gemma-2b-it-for-Arabic