huihui_ai/tulu3-abliterate:70b-q4_K

huihui_ai/ tulu3-abliterate:70b-q4_K_M

779 Downloads Updated 1 year ago

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.

8b 70b

ollama run huihui_ai/tulu3-abliterate:70b-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/tulu3-abliterate:70b-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/tulu3-abliterate:70b-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/tulu3-abliterate:70b-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

7f75cc11a1d4 · 43GB ·

model

archllama

parameters70.6B

quantizationQ4_K_M

43GB

system

You are Tulu 3, a helpful and harmless AI Assistant built by the Allen Institute for AI.

88B

license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”

7.6kB

template

{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -}} <|{{ .Role }}|> {

218B

Readme

This is an uncensored version of llama-31-tulu-3 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