dolphin-mixtral:8x22b

945.8K Downloads Updated 1 year ago

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

8x7b 8x22b

ollama run dolphin-mixtral:8x22b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "dolphin-mixtral:8x22b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='dolphin-mixtral:8x22b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'dolphin-mixtral:8x22b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

0772a1b884bf · 80GB ·

model

archllama

parameters141B

quantizationQ4_0

80GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

system

You are Dolphin, a helpful AI assistant.

41B

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

182B

Readme

The Dolphin model by Eric Hartford based on Mixtral that is trained with additional datasets:

Synthia, OpenHermes and PureDove
New Dolphin-Coder
MagiCoder

Sizes

dolphin-mixtral:8x22b
dolphin-mixtral:8x7b

References

HuggingFace