metadata
license: mit
datasets:
- Cynaptics/persona-chat
- rizalHidayat/bot-dialog
language:
- en
metrics:
- accuracy
base_model:
- distilbert/distilgpt2
pipeline_tag: text-generation
library_name: transformers
tags:
- llm
- text-generation-inference
✨DarkNeuron-AI/darkneuron-chat-v1.1
DarkNeuron-Chat v1.1 is a chatbot designed for basic, friendly conversations. It provides clear and concise responses and is suitable for general use.
👍Model Overview
- Model type: GPT-based causal language model
- Purpose: Basic conversational chatbot
- Training data: Fine-tuned on Persona-Chat and Bot-Dialog datasets
- Intended audience: General users, students, hobbyists, and researchers interested in chatbot interactions
🌟Installation
Install the latest version of Transformers:
!pip install --upgrade transformers torch
👽Example Usage
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch, gc
# Load tokenizer and model
model_name = "DarkNeuron-AI/darkneuron-chat-v1.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
# Use GPU if available
device = 0 if torch.cuda.is_available() else -1
# Create chatbot pipeline
chatbot = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
device=device,
return_full_text=False
)
# Optional: Free GPU memory
gc.collect()
torch.cuda.empty_cache()
# Interactive chat loop
print("Chatbot ready! Type 'exit' or 'quit' to stop.\n")
while True:
user_input = input("User: ")
if user_input.lower() in ["exit", "quit"]:
print("Chat ended.")
break
prompt = f"User: {user_input}\nBot:"
response = chatbot(
prompt,
max_length=100,
do_sample=True,
temperature=0.7,
top_p=0.9,
num_return_sequences=1
)
print(response[0]["generated_text"])