MISHANM/Kashmiri_text_generation_Llama3_8B_instruct

This model is fine-tuned for the Kashmiri language, capable of answering queries and translating text Between English and Kashmiri . It leverages advanced natural language processing techniques to provide accurate and context-aware responses.

Model Details

1. Language: Kashmiri
2. Tasks: Question Answering, Translation (English to Kashmiri )
3. Base Model: meta-llama/Meta-Llama-3-8B-Instruct

Training Details

The model is trained on approx 49K instruction samples.

1. GPUs: 2*AMD Instinct™ MI210 Accelerators

Inference with HuggingFace

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the fine-tuned model and tokenizer
model_path = "MISHANM/Kashmiri_text_generation_Llama3_8B_instruct"

model = AutoModelForCausalLM.from_pretrained(model_path,device_map="auto")

tokenizer = AutoTokenizer.from_pretrained(model_path)

# Function to generate text
def generate_text(prompt, max_length=1000, temperature=0.9):
   # Format the prompt according to the chat template
   messages = [
       {
           "role": "system",
           "content": "You are a Kashmiri language expert and linguist, with same knowledge give response in Kashmiri language.",
       },
       {"role": "user", "content": prompt}
   ]

   # Apply the chat template
   formatted_prompt = f"<|system|>{messages[0]['content']}<|user|>{messages[1]['content']}<|assistant|>"

   # Tokenize and generate output
   inputs = tokenizer(formatted_prompt, return_tensors="pt")
   output = model.generate(  # Use model.module for DataParallel
       **inputs, max_new_tokens=max_length, temperature=temperature, do_sample=True
   )
   return tokenizer.decode(output[0], skip_special_tokens=True)

# Example usage
prompt = """Give a poem on LLM ."""
translated_text = generate_text(prompt)
print(translated_text)

Citation Information

@misc{MISHANM/Kashmiri_text_generation_Llama3_8B_instruct,
  author = {Mishan Maurya},
  title = {Introducing Fine Tuned LLM for Kashmiri Language},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  
}

• PEFT 0.12.0