huihui_ai/
qwen2.5-1m-abliterated:14b-instruct-q8_0

21.5K 3 months ago

Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens.

tools 7b 14b

3 months ago

39e0c2d17b4d · 16GB

model
qwen2
·
14.8B
·
Q8_0
system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
template
{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{
license
Apache License Version 2.0, January 200

Readme

This is an uncensored version of Qwen/qwen25-1m 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