Adrienfndr/luna-stage1-backbone

Luna Stage 1 Backbone

This is a fine-tuned version of Llama-2-7B-chat, trained on conversational data for improved dialogue capabilities.

Model Details

• Base Model: meta-llama/Llama-2-7b-chat-hf
• Training Data: DailyDialog dataset (7,000 samples)
• Fine-tuning: Stage 1 backbone training
• Parameters: 6.7B parameters

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Adrienfndr/luna-stage1-backbone")
model = AutoModelForCausalLM.from_pretrained("Adrienfndr/luna-stage1-backbone")

# Generate text
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)