Modelpublic

RichardErkhov/Sakalti_-_iturkaAI-large-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes50downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

iturkaAI-large - GGUF

—Model creator: https://huggingface.co/Sakalti/
—Original model: https://huggingface.co/Sakalti/iturkaAI-large/

Name	Quant method	Size
iturkaAI-large.Q2_K.gguf	Q2_K	0.39GB
iturkaAI-large.IQ3_XS.gguf	IQ3_XS	0.44GB
iturkaAI-large.IQ3_S.gguf	IQ3_S	0.45GB
iturkaAI-large.Q3_K_S.gguf	Q3KS	0.45GB
iturkaAI-large.IQ3_M.gguf	IQ3_M	0.48GB
iturkaAI-large.Q3_K.gguf	Q3_K	0.51GB
iturkaAI-large.Q3_K_M.gguf	Q3KM	0.51GB
iturkaAI-large.Q3_K_L.gguf	Q3KL	0.55GB
iturkaAI-large.IQ4_XS.gguf	IQ4_XS	0.54GB
iturkaAI-large.Q4_0.gguf	Q4_0	0.56GB
iturkaAI-large.IQ4_NL.gguf	IQ4_NL	0.56GB
iturkaAI-large.Q4_K_S.gguf	Q4KS	0.56GB
iturkaAI-large.Q4_K.gguf	Q4_K	0.61GB
iturkaAI-large.Q4_K_M.gguf	Q4KM	0.61GB
iturkaAI-large.Q4_1.gguf	Q4_1	0.61GB
iturkaAI-large.Q5_0.gguf	Q5_0	0.66GB
iturkaAI-large.Q5_K_S.gguf	Q5KS	0.66GB
iturkaAI-large.Q5_K.gguf	Q5_K	0.71GB
iturkaAI-large.Q5_K_M.gguf	Q5KM	0.71GB
iturkaAI-large.Q5_1.gguf	Q5_1	0.72GB
iturkaAI-large.Q6_K.gguf	Q6_K	0.78GB
iturkaAI-large.Q8_0.gguf	Q8_0	1.0GB

Original model description: --- language:

—en tags:
—pytorch
—causal-lm
—pythia
—iturka license: apache-2.0 datasets:
—EleutherAI/thepilededuplicated basedmodel: EleutherAI/pythia-1b-deduped libraryname: transformers ---