huihui_ai/dolphin3-abliterated:8b-llama3.1-q8

huihui_ai/ dolphin3-abliterated:8b-llama3.1-q8_0

35.4K Downloads Updated 1 year ago

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

tools 8b

ollama run huihui_ai/dolphin3-abliterated:8b-llama3.1-q8_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/dolphin3-abliterated:8b-llama3.1-q8_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/dolphin3-abliterated:8b-llama3.1-q8_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/dolphin3-abliterated:8b-llama3.1-q8_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

ce280c8c6a71 · 8.5GB ·

model

archllama

parameters8.03B

quantizationQ8_0

8.5GB

template

{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }

1.5kB

license

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”

12kB

params

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

96B

Readme

This is an uncensored version of cognitivecomputations/Dolphin3.0-Llama3.1-8B 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.

References

HuggingFace