|
model-index: |
|
- name: xmanii/llama-3-8b-instruct-bnb-4bit-persian |
|
description: | |
|
**Model Information** |
|
|
|
**Developed by:** xmanii |
|
**License:** Apache-2.0 |
|
**Finetuned from model:** unsloth/llama-3-8b-instruct-bnb-4bit |
|
|
|
**Model Description** |
|
|
|
This LLaMA model was fine-tuned on a unique Persian dataset of Alpaca chat conversations, consisting of approximately 8,000 rows. Our training process utilized two H100 GPUs, completing in just under 1 hour. We leveraged the power of Unsloth and Hugging Face's TRL library to accelerate our training process by 2x. |
|
|
|
**Open-Source Contribution** |
|
|
|
This model is open-source, and we invite the community to use and build upon our work. The fine-tuned LLaMA model is designed to improve Persian conversation capabilities, and we hope it will contribute to the advancement of natural language processing in the Persian language. |
|
|
|
**Using the Model** |
|
|
|
To use this model, you can utilize the Hugging Face Transformers library. **Note:** The default usage code provided by Hugging Face is not applicable for this model. Instead, follow the example below: |
|
|
|
```python |
|
messages = [{"from": "human", "value": prompt},] |
|
``` |
|
|
|
Finally, use the pipeline to generate responses: |
|
|
|
```python |
|
pipe = pipeline("text-generation", model="xmanii/Llama3-8b-simorgh-16bit") |
|
pipe(messages) |
|
``` |
|
|
|
**Full 16-bit Merged Model** |
|
|
|
For a full 16-bit merged model, please check out xmanii/Llama3-8b-simorgh-16bit. |
|
|
|
**Future Work** |
|
|
|
We are working on quantizing the models and bringing them to ollama. |