Full-text search
+ 1,000 results
FantasiaFoundry / GGUF-Quantization-Script
README.md
model
10 matches
tags:
gguf, quantized, text-generation-inference, text-generation, license:cc-by-nc-4.0, region:us
28
29
30
31
32
BF16 GGUF to hopefully generate lossless, or as close to that for now, Llama-3 model quantizations avoiding the recent talked about issues on that topic, it is more resource intensive and will generate more writes in the drive as there's a whole additional conversion step that isn't performed in the previous version. This should only be necessary until we have GPU support for BF16 to run directly without conversion.
Pull Requests with your own features and improvements to this script are always welcome.
gguf / Genstruct-7B-GGUF
model
2 matches
Felladrin / gguf-Llama-160M-Chat-v1
README.md
model
3 matches
Felladrin / gguf-Tinyllama-616M-Cinder
README.md
model
3 matches
Felladrin / gguf-Qwen1.5-0.5B-Chat
README.md
model
3 matches
Felladrin / gguf-sharded-gemma-2b-orpo
README.md
model
3 matches
Felladrin / gguf-gemma-2b-orpo
README.md
model
3 matches
Cebtenzzre / gguf-misc
model
2 matches
npvinHnivqn / GGUF-metamath-llemma
README.md
model
3 matches
npvinHnivqn / GGUF-openchat
README.md
model
3 matches
huodon / gguf-models
model
2 matches
Felladrin / gguf-TinyMistral-248M-SFT-v4
README.md
model
3 matches
Felladrin / gguf-llama-160m
README.md
model
3 matches
hesha / gguf-collection
model
2 matches
IndiaBuild / GGUF_Navarna_v0_1_OpenHermes_Hindi
README.md
model
3 matches
gguf / cosmo-1b-GGUF
model
2 matches
gguf / Smaug-34B-v0.1-GGUF
model
2 matches
gguf / Mistral-7B-Instruct-v0.2-GGUF
model
2 matches
gguf / Nous-Hermes-2-Mistral-7B-DPO-GGUF
model
2 matches