huihui_ai/command-r7b-abliterated:7b-12-2024-q8

huihui_ai/ command-r7b-abliterated:7b-12-2024-q8_0

917 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:7b-12-2024-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/command-r7b-abliterated:7b-12-2024-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/command-r7b-abliterated:7b-12-2024-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/command-r7b-abliterated:7b-12-2024-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

98df22ff8d9f · 8.5GB ·

model

archcohere2

parameters8.03B

quantizationQ8_0

8.5GB

license

Creative Commons Attribution-NonCommercial 4.0 International Public License with Acceptable Use Adde

14kB

params

{ "stop": [ "<|START_OF_TURN_TOKEN|>", "<|END_OF_TURN_TOKEN|>", "<|END_R

110B

template

{{- if or .Tools .System }}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|> {{- if .Tools }}# Safety Preamble

3.0kB

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