--- base_model: meta-llama/Meta-Llama-3-8B-Instruct library_name: peft datasets: - Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered --- # MISHANM/Konkani_text_generation_Llama3_8B_instruct This model is fine-tuned for the Konkani language, capable of answering queries and translating text Between English and Konkani . It leverages advanced natural language processing techniques to provide accurate and context-aware responses. ## Model Details 1. Language: Konkani 2. Tasks: Question Answering, Translation (English to Konkani ) 3. Base Model: meta-llama/Meta-Llama-3-8B-Instruct # Training Details The model is trained on approx 29K instruction samples. 1. GPUs: 2*AMD Instinctâ„¢ MI210 Accelerators ## Inference with HuggingFace ```python3 import torch from transformers import AutoModelForCausalLM, AutoTokenizer # Load the fine-tuned model and tokenizer model_path = "MISHANM/Konkani_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 Konkani language expert and linguist, with same knowledge give response in Konkani 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 = """What is LLM .""" translated_text = generate_text(prompt) print(translated_text) ``` ## Citation Information ``` @misc{MISHANM/Konkani_text_generation_Llama3_8B_instruct, author = {Mishan Maurya}, title = {Introducing Fine Tuned LLM for Konkani Language}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, } ``` - PEFT 0.12.0