Gemma2_Farsi / README.md
alibidaran's picture
Update README.md
297b0f1 verified
---
library_name: transformers
license: apache-2.0
language:
- fa
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is Persian Q&A fine-tuned on Google's Gemma open-source model. Users can ask general question from it. It can be used for chatbot applications and fine-tuning for
other datasets.
- **Developed by:** Ali Bidaran
- **Language(s) (NLP):** Farsi
- **Finetuned from model [optional]:** Gemma2b
## Uses
This model can be used for developing chatbot applications, Q&A, instruction engineering and fine-tuning with other persian datasets.
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
``` python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, GemmaTokenizer
model_id = "alibidaran/Gemma2_Farsi"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(model_id, token=os.environ['HF_TOKEN'])
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0}, token=os.environ['HF_TOKEN'])
prompt = "چند روش برای کاهش چربی بدن ارائه نمایید؟"
text = f"<s> ###Human: {prompt} ###Asistant: "
inputs=tokenizer(text,return_tensors='pt').to('cuda')
with torch.no_grad():
outputs=model.generate(**inputs,max_new_tokens=400,do_sample=True,top_p=0.99,top_k=10,temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->