Update README.md

README.md

@@ -7,11 +7,11 @@ language:
 - en
 ---
 
-# Llama3-8B Adapter Fine-Tuned for Galician language
+# Llama3-8B Lora adapter for Galician language
 
-This repository contains a Lora Adapter to finetune Meta's LLaMA 3-8B Instruct LLM to Galician language.
+This repository houses a specialized LoRA (Low-Rank Adaptation) Adapter designed specifically for fine-tuning Meta's LLaMA 3-8B Instruct version for applications involving the Galician language. The purpose of this adapter is to efficiently adapt the pre-trained model, which has been initially trained on a broad range of data and languages, to better understand and generate text in Galician.
 
-## Model Adapter Description
+## Adapter Description
 
 This Lora Adapter has been specifically fine-tuned to understand and generate text in Galician. It was refined using a modified version of the [irlab-udc/alpaca_data_galician](https://huggingface.co/datasets/irlab-udc/alpaca_data_galician) dataset, enriched with synthetic data to enhance its text generation and comprehension capabilities in specific contexts.
 
@@ -19,7 +19,7 @@ This Lora Adapter has been specifically fine-tuned to understand and generate te
 
 - **Base Model**: Unsloth Meta's LLaMA 3 8B Instruct (https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit)
 - **Fine-Tuning Platform**: LLaMA Factory
-- **Infrastructure**: Finisterrae III, CESGA
+- **Infrastructure**: Finisterrae III Supercomputer, CESGA (Galicia-Spain)
 - **Dataset**: [irlab-udc/alpaca_data_galician](https://huggingface.co/datasets/irlab-udc/alpaca_data_galician) (with modifications)
 - **Fine-Tuning Objective**: To improve text comprehension and generation in Galician.
 
@@ -60,21 +60,25 @@ User: Cantos habitantes ten Galicia?
 Assistant: Segundo as últimas estimacións, Galicia ten uns 2,8 millóns de habitantes.
 ```
 
-## How to Use the Model
+## How to Use the Adapter
 
 To use this adapter, follow the example code provided below. Ensure you have the necessary libraries installed (e.g., Hugging Face's `transformers`).
 
 ### Installation
+
+Download de adapter from huggingface:
 ```bash
 git clone https://huggingface.co/abrahammg/Llama3-8B-Galician-Chat-Lora
 ```
-
+Install dependencies:
 ```bash
 pip install transformers bitsandbytes "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" llmtuner xformers
 ```
 
 ### Run the adapter
 
+Create a python script (ex. run_model.py):
+
 ```bash
 from llmtuner import ChatModel
 from llmtuner.extras.misc import torch_gc
@@ -100,17 +104,22 @@ while True:
     print("History has been removed.")
     continue
 
-  messages.append({"role": "user", "content": query})     # add query to messages
+  messages.append({"role": "user", "content": query})
   print("Assistant: ", end="", flush=True)
   response = ""
-  for new_text in chat_model.stream_chat(messages):      # stream generation
+  for new_text in chat_model.stream_chat(messages):
     print(new_text, end="", flush=True)
     response += new_text
   print()
-  messages.append({"role": "assistant", "content": response}) # add response to messages
+  messages.append({"role": "assistant", "content": response})
 
 torch_gc()
 ```
+and run it
+```bash
+python run_model.py
+```
+
 ## Citation
 
 ```markdown
@@ -127,3 +136,4 @@ torch_gc()
 
 - [meta-llama/llama3](https://github.com/meta-llama/llama3)
 - [hiyouga/LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
+- [irlab-udc/alpaca_data_galician](https://huggingface.co/datasets/irlab-udc/alpaca_data_galician)