huihui_ai/dolphin3-r1-abliterated:24b-mistral-q6

huihui_ai/

dolphin3-r1-abliterated:24b-mistral-q6_K

1,596 Downloads Updated 8 months ago

Dolphin's first generation reasoning models.

24b

Updated 8 months ago

8 months ago

2f24671451f5 · 19GB ·

archllama

parameters23.6B

quantizationQ6_K

19GB

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

59B

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

182B

This is an uncensored version of cognitivecomputations/Dolphin3.0-R1-Mistral-24B 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.

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge