huihui_ai/s1-abliterated:32b-fp16

huihui_ai/ s1-abliterated:32b-fp16

334 Downloads Updated 11 months ago

s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.

tools 32b

ollama run huihui_ai/s1-abliterated:32b-fp16

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/s1-abliterated:32b-fp16",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/s1-abliterated:32b-fp16',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/s1-abliterated:32b-fp16',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 11 months ago

11 months ago

2d7e32e4f86f · 66GB ·

model

archqwen2

parameters32.8B

quantizationF16

66GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

template

{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

1.5kB

system

You are Qwen, created by Alibaba Cloud. You are a helpful assistant.

68B

Readme

This is an uncensored version of simplescaling/s1-32B created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

References

HuggingFace

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge