DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.
7b
8b
14b
32b
70b
380.4K Pulls Updated 3 weeks ago
Updated 3 weeks ago
3 weeks ago
50f8d0fe980f · 43GB
model
archllama
·
parameters70.6B
·
quantizationQ4_K_M
43GB
params
{
"stop": [
"<|begin▁of▁sentence|>",
"<|end▁of▁sentence|>",
148B
template
{{- if .System }}{{ .System }}{{ end }}
{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice
387B
license
MIT License
Copyright (c) 2023 DeepSeek
Permission is hereby granted, free of charge, to any perso
1.1kB
Readme
This is an uncensored version of deepseek-ai/deepseek-r1 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.
If “<think>” does not appear or refuses to respond, you can first provide an example to guide, and then ask your question.
For instance:
How many 'r' characters are there in the word "strawberry"?
References
Donation
Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge