ggml-org/gguf-my-repo · Discussions

[bug] asymmetric t5 models fail to quantize

#126 opened 11 days ago by

pszemraj

[Bug] Extra files with related name were uploaded to the resulting repository

#125 opened 11 days ago by

Felladrin

Issue converting PEFT LoRA fine tuned model to GGUF

#124 opened 15 days ago by

AdnanRiaz107

Issue converting nvidia/NV-Embed-v2 to GGUF

#123 opened 18 days ago by

redshiva

Issue converting FLUX.1-dev model to GGUF format

2

#122 opened 20 days ago by

cbrescia

Add Llama 3.1 license

#121 opened 22 days ago by

jxtngx

Add an option to put all quantization variants in the same repo

#120 opened 22 days ago by

A2va

Phi-3.5-MoE-instruct

4

#117 opened about 1 month ago by

goodasdgood

Fails to quntize T5 (xl and xxl) models

1

#116 opened about 1 month ago by

girishponkiya

Arm optimized quants

1

#113 opened about 1 month ago by

SaisExperiments

DeepseekForCausalLM is not supported

1

#112 opened about 2 months ago by

nanowell

Please, update converting script. Llama.cpp added support for Nemotron and Minitron architectures.

3

#111 opened about 2 months ago by

NikolayKozloff

Enable the created name repo to be without the quantization type

#110 opened about 2 months ago by

A2va

I think I broke the space quantizing 4bit modle with Q4L

#106 opened 2 months ago by

hellork

Authorship Metadata support added to converter script, you may want to add the ability to add metadata overrides

3

#104 opened 2 months ago by

mofosyne

Please support this method:

7

#96 opened 3 months ago by

ZeroWw

Support Q2 imatrix quants

#95 opened 3 months ago by

Dampfinchen

Maybe impose a max model size?

3

#33 opened 6 months ago by

pcuenq