Laurent Mazare

#1 opened 6 months ago by

Steve0010

New activity in lmz/candle-whisper 6 months ago

fix model reference

#6 opened 6 months ago by

New activity in lmz/candle-quantized-phi 7 months ago

Update phi-2_0.json

#8 opened 7 months ago by

Upload phi-2_0.json

#7 opened 7 months ago by

phi2-quantized-files

#6 opened 7 months ago by

New activity in lmz/candle-quantized-t5 7 months ago

Add xl variant

#3 opened 7 months ago by

bayang

Flan-t5-xl.gguf missing

#2 opened 7 months ago by

bayang

New activity in openai/whisper-large-v3 8 months ago

TokenizerFast with tokenizer.json

#7 opened 8 months ago by

vubiqus

New activity in moka-ai/m3e-large 8 months ago

Adding `safetensors` variant of this model

#5 opened 8 months ago by

lmz

New activity in lmz/candle-whisper 8 months ago

Add distill link

#5 opened 8 months ago by

New activity in lmz/candle-quantized-phi 8 months ago

Can you quantize this model?

4

#5 opened 8 months ago by

KatyTheCutie

New activity in lmz/candle-quantized-t5 8 months ago

Is `model.gguf` t5-small or flan-t5-small?

#1 opened 8 months ago by

Felladrin

New activity in lmz/candle-blip 8 months ago

Add blip large config here

#1 opened 8 months ago by

New activity in lmz/candle-quantized-phi 8 months ago

add configs to repo

#4 opened 8 months ago by

New activity in microsoft/phi-1_5 8 months ago

Any plan/ideas to convert this to gguf?

6

#40 opened 9 months ago by

has-c

New activity in lmz/candle-quantized-phi 8 months ago

easy execution

15

#3 opened 8 months ago by

KatyKunXD

New activity in lmz/candle-quantized-phi 9 months ago

Is this Phi-1 or Phi-1_5?

3

#1 opened 9 months ago by

whatever1983

Can you please share the code to convert phi 1.5 to the GGUF format?

6

#2 opened 9 months ago by

diablo98

New activity in lmz/candle-whisper 9 months ago

add quantized models support

#4 opened 9 months ago by

New activity in lmz/candle-llama2 9 months ago

fix

#5 opened 9 months ago by

minor ui changes

#4 opened 9 months ago by

set min for repeat_penalty

#3 opened 9 months ago by

New activity in lmz/candle-yolo-v8 10 months ago

Can you provide scripts that convert to safetensors format?

3

#1 opened 10 months ago by

rkingzhong

New activity in lmz/candle-yolo 10 months ago

force cache using cache api

#6 opened 10 months ago by

New activity in lmz/candle-whisper 10 months ago

force caching using cache api

#3 opened 10 months ago by

New activity in lmz/candle-llama2 10 months ago

force cache with cache API and fix max seq

#2 opened 10 months ago by

New activity in lmz/candle-whisper 10 months ago

minor ui change

#2 opened 10 months ago by

New activity in lmz/candle-yolo 10 months ago

minor UI change

#5 opened 10 months ago by

New activity in lmz/candle-llama2 10 months ago

new UI

#1 opened 10 months ago by

New activity in lmz/candle-yolo 10 months ago

UI: Put "Predict" button above the fold

#4 opened 10 months ago by

victor

pose-update

#2 opened 10 months ago by

New activity in lmz/candle-whisper 10 months ago

new-ui

#1 opened 10 months ago by

New activity in lmz/candle-yolo 10 months ago

new-ui

#1 opened 10 months ago by

New activity in TheBloke/CodeLlama-7B-GGUF 10 months ago

Another library supporting GGUF