Subas07/llama_finetune_16bit

llama_lora

Model Description

llama_lora is a fine-tuned Large Language Model based on a LLaMA architecture using LoRA (Low-Rank Adaptation).
The model is optimized for instruction-following and conversational text generation tasks.

Base Model

This model is built on top of a LLaMA base model (8B parameter class).

Training Method

• Fine-tuned using LoRA (Low-Rank Adaptation)
• Supervised instruction tuning
• Optimized for efficient inference

Intended Use

This model can be used for:

• Chatbots
• Question answering
• Instruction following
• General text generation
• Educational or research purposes

How to Use

Using Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "your-username/llama_lora"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

prompt = "Explain machine learning in simple words."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.7,
    top_p=0.9
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))