rouge/daybreak-kunoichi-2dpo-7b

rouge/ daybreak-kunoichi-2dpo-7b:latest

311 Downloads Updated 2 years ago

Experimental model doing a DPO training on top of Kunoichi-DPO-v2-7b, i.e. double-DPO.

ollama run rouge/daybreak-kunoichi-2dpo-7b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rouge/daybreak-kunoichi-2dpo-7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rouge/daybreak-kunoichi-2dpo-7b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rouge/daybreak-kunoichi-2dpo-7b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

4742d588810c · 7.7GB ·

model

archllama

parameters7.24B

quantizationQ8_0

7.7GB

system

You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests t

128B

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>",

146B

template

{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

254B

Readme

Source: https://huggingface.co/crestf411/daybreak-kunoichi-2dpo-7b

Experimental model doing a DPO training on top of Kunoichi-DPO-v2-7b, i.e. double-DPO.