base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
datasets : miniguanaco
To use the model in the colab, use the below steps
!pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="epsil/Tinyllama-1.1B-miniguanaco", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "Are llm better than rule based chat?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])