huihui_ai/dolphin3-abliterated:8b-llama3.1-q4_K

huihui_ai/

dolphin3-abliterated:8b-llama3.1-q4_K_M

21.3K Downloads Updated 9 months 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

Updated 9 months ago

9 months ago

669007b377b4 · 4.9GB ·

archllama

parameters8.03B

quantizationQ4_K_M

4.9GB

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

12kB

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

96B

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

1.5kB

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.