huihui_ai/command-r7b-abliterated

huihui_ai/ command-r7b-abliterated

916 Downloads Updated 1 year ago

he smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

tools 7b

ollama run huihui_ai/command-r7b-abliterated

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/command-r7b-abliterated",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/command-r7b-abliterated',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/command-r7b-abliterated',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model huihui_ai/command-r7b-abliterated

Codex ollama launch codex --model huihui_ai/command-r7b-abliterated

OpenCode ollama launch opencode --model huihui_ai/command-r7b-abliterated

OpenClaw ollama launch openclaw --model huihui_ai/command-r7b-abliterated

Models

View all →

Name

5 models

Size

Context

Input

command-r7b-abliterated:latest

5.1GB · 8K context window · Text · 1 year ago

command-r7b-abliterated:latest

5.1GB

Text

command-r7b-abliterated:7b

latest

5.1GB · 8K context window · Text · 1 year ago

command-r7b-abliterated:7b latest

5.1GB

Text

Readme

This is an uncensored version of CohereForAI/c4ai-command-r7b-12-2024 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.

Note: this model requires Ollama 0.5.5

References

HuggingFace