6 contributors

History: 15 commits

ggerganov

Add quantized model sizes and hashes

fb5ed93 verified 3 months ago

.gitattributes

1.48 kB

initial commit almost 2 years ago
README.md

3.15 kB

Add quantized model sizes and hashes 3 months ago
ggml-base-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
37.9 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-base-q5_1.bin

59.7 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-base-q8_0.bin

81.8 MB
LFS

Add Q8_0 models 3 months ago
ggml-base.bin

148 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-base.en-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
38 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-base.en-q5_1.bin

59.7 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-base.en-q8_0.bin

81.8 MB
LFS

Add Q8_0 models 3 months ago
ggml-base.en.bin

148 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-large-v1-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
1.18 GB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-large-v1.bin

3.09 GB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-large-v2-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
1.17 GB
LFS

Add Whisper Large v3 about 1 year ago
ggml-large-v2-q5_0.bin

1.08 GB
LFS

Add Whisper Large v3 about 1 year ago
ggml-large-v2-q8_0.bin

1.66 GB
LFS

Add Q8_0 models 3 months ago
ggml-large-v2.bin

3.09 GB
LFS

Add Whisper Large v3 about 1 year ago
ggml-large-v3-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
1.18 GB
LFS

Include compressed version of the CoreML version of large-v3 model. (#14) about 1 year ago
ggml-large-v3-q5_0.bin

1.08 GB
LFS

Be explicit about large model versions about 1 year ago
ggml-large-v3-turbo-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
1.17 GB
LFS

Include compressed version of the CoreML version of large-v3-turbo model. (#19) 4 months ago
ggml-large-v3-turbo-q5_0.bin

574 MB
LFS

Add Whisper Large v3 Turbo 4 months ago
ggml-large-v3-turbo-q8_0.bin

874 MB
LFS

Add Q8_0 models 3 months ago
ggml-large-v3-turbo.bin

1.62 GB
LFS

Add Whisper Large v3 Turbo 4 months ago
ggml-large-v3.bin

3.1 GB
LFS

Be explicit about large model versions about 1 year ago
ggml-medium-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
568 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-medium-q5_0.bin

539 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-medium-q8_0.bin

823 MB
LFS

Add Q8_0 models 3 months ago
ggml-medium.bin

1.53 GB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-medium.en-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
567 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-medium.en-q5_0.bin

539 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-medium.en-q8_0.bin

823 MB
LFS

Add Q8_0 models 3 months ago
ggml-medium.en.bin

1.53 GB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-small-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
163 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-small-q5_1.bin

190 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-small-q8_0.bin

264 MB
LFS

Add Q8_0 models 3 months ago
ggml-small.bin

488 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-small.en-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
163 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-small.en-q5_1.bin

190 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-small.en-q8_0.bin

264 MB
LFS

Add Q8_0 models 3 months ago
ggml-small.en.bin

488 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-tiny-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
15 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-tiny-q5_1.bin

32.2 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-tiny-q8_0.bin

43.5 MB
LFS

Add Q8_0 models 3 months ago
ggml-tiny.bin

77.7 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago
ggml-tiny.en-encoder.mlmodelc.zip
Pickle imports
- No problematic imports detected
What is a pickle import?
15 MB
LFS

Include compressed versions of the CoreML versions of each model. (#4) over 1 year ago
ggml-tiny.en-q5_1.bin

32.2 MB
LFS

Add back properly named models (#9) over 1 year ago
ggml-tiny.en-q8_0.bin

43.6 MB
LFS

Upload ggml-tiny.en-q8_0.bin about 1 year ago
ggml-tiny.en.bin

77.7 MB
LFS

Migrate from HG dataset into HG model almost 2 years ago

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports

Pickle imports