t1-1.5B/README.md

license, language, datasets, base_model, library_name

license	language	datasets	base_model	library_name
mit	am ar bn zh cs nl en fr de el ha he hi id it ja jv km ko lo ms mr fa pl pt ro ru es sw sv tl ta te th tr uk ur vi	simplescaling/s1K lightblue/reasoning-multilingual-R1-Llama-70B-train	Qwen/Qwen2.5-1.5B-Instruct	transformers

It's a 1.5B model.

It's a distill model like s1 and deepseek-r1-distill.

It's test model. I hope I can reproduce a rl model like RL-Zero.

This model is a mini-step.

Thanks for evveryone in the open community.

how to use:

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model = LLM(
    "Amu/t1-1.5B"
)
tok = AutoTokenizer.from_pretrained("simplescaling/s1-32B")

stop_token_ids = tok("<|im_end|>")["input_ids"]

sampling_params = SamplingParams(
    max_tokens=32768,
    min_tokens=0,
    stop_token_ids=stop_token_ids,
)

prompt = "How many r in raspberry"
prompt = "<|im_start|>system\nYou are t1, created by Amu. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n" + prompt + "<|im_end|>\n<|im_start|>assistant\n"

o = model.generate(prompt, sampling_params=sampling_params)
print(o[0].outputs[0].text)