huihui_ai/deephermes3-abliterated:8b-preview-q4_K

huihui_ai/

deephermes3-abliterated:8b-preview-q4_K_M

1,746 Downloads Updated 7 months ago

DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one mod

Updated 7 months ago

7 months ago

5e0dd34c75ce · 4.9GB ·

archllama

parameters8.03B

quantizationQ4_K_M

4.9GB

{{- if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|> {{- end }} {{- r

249B

You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the prob

367B

{ "stop": [ "<|end_of_text|>", "<|eot_id|>" ] }

62B

This is an uncensored version of NousResearch/DeepHermes-3-Llama-3-8B-Preview 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