AiCloser_-_Qwen2.5-32B-AGI-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
AiCloser_-_Qwen2.5-32B-AGI-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Qwen2.5-32B-AGI - GGUF

Model creator: https://huggingface.co/AiCloser/
Original model: https://huggingface.co/AiCloser/Qwen2.5-32B-AGI/

Name	Quant method	Size
Qwen2.5-32B-AGI.Q2_K.gguf	Q2_K	11.47GB
Qwen2.5-32B-AGI.IQ3_XS.gguf	IQ3_XS	12.76GB
Qwen2.5-32B-AGI.IQ3_S.gguf	IQ3_S	13.45GB
Qwen2.5-32B-AGI.Q3_K_S.gguf	Q3_K_S	13.4GB
Qwen2.5-32B-AGI.IQ3_M.gguf	IQ3_M	13.79GB
Qwen2.5-32B-AGI.Q3_K.gguf	Q3_K	14.84GB
Qwen2.5-32B-AGI.Q3_K_M.gguf	Q3_K_M	14.84GB
Qwen2.5-32B-AGI.Q3_K_L.gguf	Q3_K_L	16.06GB
Qwen2.5-32B-AGI.IQ4_XS.gguf	IQ4_XS	16.64GB
Qwen2.5-32B-AGI.Q4_0.gguf	Q4_0	17.36GB
Qwen2.5-32B-AGI.IQ4_NL.gguf	IQ4_NL	17.53GB
Qwen2.5-32B-AGI.Q4_K_S.gguf	Q4_K_S	17.49GB
Qwen2.5-32B-AGI.Q4_K.gguf	Q4_K	18.49GB
Qwen2.5-32B-AGI.Q4_K_M.gguf	Q4_K_M	18.49GB
Qwen2.5-32B-AGI.Q4_1.gguf	Q4_1	19.22GB
Qwen2.5-32B-AGI.Q5_0.gguf	Q5_0	21.08GB
Qwen2.5-32B-AGI.Q5_K_S.gguf	Q5_K_S	21.08GB
Qwen2.5-32B-AGI.Q5_K.gguf	Q5_K	21.66GB
Qwen2.5-32B-AGI.Q5_K_M.gguf	Q5_K_M	21.66GB
Qwen2.5-32B-AGI.Q5_1.gguf	Q5_1	22.95GB
Qwen2.5-32B-AGI.Q6_K.gguf	Q6_K	25.04GB
Qwen2.5-32B-AGI.Q8_0.gguf	Q8_0	32.43GB

Original model description:

license: apache-2.0 language:

zh
en base_model:
Qwen/Qwen2.5-32B-Instruct datasets:
anthracite-org/kalo-opus-instruct-22k-no-refusal
unalignment/toxic-dpo-v0.2
Orion-zhen/dpo-toxic-zh library_name: transformers

AGI means Aspirational Grand Illusion

First Qwen2.5 32B Finetune, to fix its Hypercensuritis

Hyper means high, and censura means censor, the suffix "-itis" is used to denote inflammation of a particular part or organ of the body.