UltraInteract-Llama-FT

This model is a fine-tuned version of Llama-2 using the UltraInteract dataset. It has been trained to handle interactive conversational tasks with improved accuracy and contextual understanding.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("kritsadaK/UltraInteract-Llama-FT")
model = AutoModelForCausalLM.from_pretrained("kritsadaK/UltraInteract-Llama-FT")

input_text = "typing your prompt here"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Dataset: UltraInteract

Training Parameters: 4-bit quantization with LoRA