sjo/deepseek-r1-8b-llama-distill-abliterated-q8

sjo/ deepseek-r1-8b-llama-distill-abliterated-q8_0

2,700 Downloads Updated 1 year ago

The mradermacher model of DeepSeek-r1 llama distilled with abliteration applied

ollama run sjo/deepseek-r1-8b-llama-distill-abliterated-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sjo/deepseek-r1-8b-llama-distill-abliterated-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sjo/deepseek-r1-8b-llama-distill-abliterated-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sjo/deepseek-r1-8b-llama-distill-abliterated-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size

Context

Input

deepseek-r1-8b-llama-distill-abliterated-q8_0:latest

8.5GB · 128K context window · Text · 1 year ago

deepseek-r1-8b-llama-distill-abliterated-q8_0:latest

8.5GB

128K

Text

Readme

Model adapted from the Modelfile in original non-abliterated llama distill version of r1 and this model downloaded from huggingface - https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Abliterated-GGUF

hope others find it useful