cosmo-3b-test-v0.2 / README.md
gmonsoon's picture
Update README.md
544e8b5 verified
|
raw
history blame
1.17 kB
metadata
library_name: transformers
inference:
  parameters:
    temperature: 1.1
    top_p: 0.95
    top_k: 30
    repetition_penalty: 1
widget:
  - text: Photosynthesis is
    example_title: Textbook
    group: Completion
  - text: '<s> [INST]  How to take care of exotic cars? [/INST] '
    example_title: Wikihow
    group: Completion
  - text: '<s> [INST] Generate a story about Dark Knight [/INST] '
    example_title: Story
    group: Completion
license: apache-2.0
language:
  - en

Updated to v0.2

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "frankenmerger/cosmo-3b-test-v0.2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])