fine-tuned-llama-distilled-deepseek-bs8-1

LoRA Adapter for deepseek-ai/DeepSeek-R1-Distill-Llama-8B

This repository contains a LoRA adapter for fine-tuning the deepseek-ai/DeepSeek-R1-Distill-Llama-8B model.

Base Model

The adapter is designed to be used with deepseek-ai/DeepSeek-R1-Distill-Llama-8B.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig

# Load the LoRA configuration
config = PeftConfig.from_pretrained("jakebentley2001/fine-tuned-llama-distilled-deepseek-bs8-1")

# Load the base model
model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

# Load the LoRA adapter
model = PeftModel.from_pretrained(model, "jakebentley2001/fine-tuned-llama-distilled-deepseek-bs8-1")

# Generate text
inputs = tokenizer("Your prompt here", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))