Hugging Face's logo
Georgi Gerganov's picture
21 9 23

Georgi Gerganov

ggerganov
hakase's profile picture r1cc4rd0m4zz4's profile picture prabakarviji's profile picture
·
https://ggerganov.com

AI & ML interests

ggml

Recent Activity

liked a Space 8 days ago
xet-team/quantization-dedup
upvoted an article 8 days ago
From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub
updated a collection 22 days ago
llama.vim
View all activity

Organizations

PlayAI's profile picture ggml.ai's profile picture Social Post Explorers's profile picture private beta for deeplinks's profile picture

ggerganov's activity

New activity in ggml-org/WavTokenizer about 1 month ago

Added q5_1 quant
#1 opened about 1 month ago by
concedo
New activity in Qwen/Qwen2.5-Coder-7B-Instruct 4 months ago

FIM prompt temlate

3
#2 opened 5 months ago by
ijwfly
New activity in ggerganov/whisper.cpp 4 months ago

Add automatic-speech-recognition tag
#15 opened 9 months ago by
BaptisteCS
New activity in ggerganov/whisper.cpp 5 months ago

Include compressed version of the CoreML version of large-v3-turbo model.

1
#19 opened 5 months ago by
solaoi

Add large-v3-turbo model

6
#17 opened 5 months ago by
kth8

Upload ggml-large-v3-turbo.bin

1
#18 opened 5 months ago by
baristikir
New activity in reach-vb/gguf-stats 5 months ago

Interesting SQL Queries

3
#1 opened 5 months ago by
cfahlgren1
New activity in ggml-org/gguf-my-repo 9 months ago

imatrix support

18
#80 opened 9 months ago by
SixOpen
New activity in ggml-org/gguf-my-repo 11 months ago

Minor improvement suggestions

1
#28 opened 11 months ago by
ggerganov
New activity in ggml-org/models 11 months ago

How to add new files without cloning the entire repo?

3
#1 opened 11 months ago by
ggerganov
New activity in ggml-org/README 11 months ago

Update README.md
#1 opened 11 months ago by
reach-vb
New activity in google/gemma-7b-it 12 months ago

Buggy GGUF Output

15
#38 opened 12 months ago by
mattjcly
New activity in ggerganov/whisper.cpp about 1 year ago

Include compressed version of the CoreML version of large-v3 model.
#14 opened about 1 year ago by
solaoi
New activity in ggerganov/whisper.cpp over 1 year ago

Add back properly named models

1
#9 opened over 1 year ago by
nchudleigh

Normalize quantized model names

1
#8 opened over 1 year ago by
nchudleigh
New activity in TinyLlama/TinyLlama-1.1B-step-50K-105b over 1 year ago

tokenizer.model seems to be empty?

5
#1 opened over 1 year ago by
ggerganov
New activity in ggerganov/whisper.cpp over 1 year ago

COEP/COOP Headers on Static Spaces Hugging Face

2
#6 opened over 1 year ago by
radames

Add quantized versions of the models

1
#5 opened over 1 year ago by
gabrielgrant

Include compressed versions of the CoreML versions of each model.

1
#4 opened over 1 year ago by
intheblueyonder

Can You upload large v2 model

1
#3 opened almost 2 years ago by
Tsogtpurev