huihui_ai/skyt1-abliterated:32b-preview-q4_K

huihui_ai/ skyt1-abliterated:32b-preview-q4_K_M

204 Downloads Updated 1 year ago

Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities

tools 32b

ollama run huihui_ai/skyt1-abliterated:32b-preview-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/skyt1-abliterated:32b-preview-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/skyt1-abliterated:32b-preview-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/skyt1-abliterated:32b-preview-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

cef16596dd74 · 20GB ·

model

archqwen2

parameters32.8B

quantizationQ4_K_M

20GB

template

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

1.2kB

system

You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-b

107B

license

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

11kB

Readme

This is an uncensored version of NovaSky-AI/Sky-T1-32B-Preview 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