huihui_ai/falcon3-abliterated:3b-instruct-q8

huihui_ai/ falcon3-abliterated:3b-instruct-q8_0

1,380 Downloads Updated 1 year ago

A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.

1b 3b 7b 10b

ollama run huihui_ai/falcon3-abliterated:3b-instruct-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/falcon3-abliterated:3b-instruct-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/falcon3-abliterated:3b-instruct-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/falcon3-abliterated:3b-instruct-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

51cb43ec5f69 · 3.4GB ·

model

archllama

parameters3.23B

quantizationQ8_0

3.4GB

license

Falcon 3 TII Falcon License December 2024 FalconLLM.tii.ae Introductory note This license is, in par

13kB

params

{ "stop": [ "<|system|>", "<|user|>", "<|end|>", "<|assistant|>"

101B

template

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

218B

Readme

This is an uncensored version of tiiuae/falcon3 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