Views
No views yet
pipeline() function from 🤗 Transformers:1# pip install transformers
2# pip install accelerate
3
4import torch
5from transformers import pipeline
6
7pipe = pipeline("text-generation", model="open-r1/OlympicCoder-7B", torch_dtype=torch.bfloat16, device_map="auto")
8
9# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
10messages = [
11 {"role": "user", "content": "Write a python program to calculate the 10th Fibonacci number"},
12]
13prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
14outputs = pipe(prompt, max_new_tokens=8000, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
15print(outputs[0]["generated_text"])
16#<|im_start|>user
17#Write a python program to calculate the 10th fibonacci number<|im_end|>
18#<|im_start|>assistant
19#<think>Okay, I need to write a Python program that calculates the 10th Fibonacci number. Hmm, the Fibonacci sequence starts with 0 and 1. Each subsequent number is the sum of the two preceding ones. So the sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, and so on. ...[!WARNING] To ensure that the model consistently outputs a long chain-of-thought, we have edited the chat template to prefill the first assistant turn with a<think>token. As a result, the outputs from this model will not show the opening<think>token if you use the model'sgenerate()method. To apply reinforcement learning with a format reward, either prepend the<think>token to the model's completions or amend the chat template to remove the prefill.