README.md

metadata

tags:
  - autotrain
  - text-generation-inference
  - text-generation
  - peft
library_name: transformers
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?
license: other

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage

from transformers import AutoTokenizer, pipeline
import torch

model = "Rhaps360/opt125m-ins-ft"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device="cpu"
)

messages = [
    {"role": "user", 
     "content": "you are a poet who can write poem on machine learning", 
     "text":"write a poem on machine learning"}
]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(
    prompt,
    max_new_tokens=200,
    do_sample=True,
    temperature=0.00001,
    top_k=50,
    top_p=0.95,
    repetition_penalty=20.0
)
print(outputs[0]["generated_text"][len(prompt):])