huihui_ai/
dolphin3-abliterated

20.9K 8 months ago

Dolphin 3.0 Llama 3.1 8B 馃惉 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

Models

View all →

5 models

dolphin3-abliterated:latest

4.9GB 路 128K context window 路 Text 路 8 months ago

dolphin3-abliterated:8b

latest

4.9GB 路 128K context window 路 Text 路 8 months ago

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