huihui_ai/dolphin3-r1-abliterated

huihui_ai/

dolphin3-r1-abliterated

Dolphin's first generation reasoning models.

24b

845 Pulls Updated 6 weeks ago

Updated 6 weeks ago

6 weeks ago

05a0492884c8 · 14GB

parameters23.6B

quantizationQ4_K_M

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

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

Readme

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.

References

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge