Commits · Tonic/Petite-LLM-3

Merge branch 'main' of https://huggingface.co/spaces/Tonic/Petite-LLM-3

53fac62

Running

Tonic commited on Aug 2

small mods on the title and description

5975026

Tonic commited on Aug 2

Update README.md

a4b7295
verified

Tonic commited on Aug 2

test commit powershell

249d9cf

Tonic commited on Jul 30

Remove test_download.py

6e00c9e

Tonic commited on Jul 30

Remove test_app.py

bcd9c36

Tonic commited on Jul 30

testing singing

0d91323

Tonic commited on Jul 30

testing signing on hf

5333df3

Tonic commited on Jul 30

adds minor changes to the README

0004ba8

Tonic commited on Jul 30

adds special tokens strip with fallback

9413e52

Tonic commited on Jul 30

adds debug

7578eea

Tonic commited on Jul 30

removes int4 subfolder

3436b88

Tonic commited on Jul 30

removes cache implementation static

3679e0b

Tonic commited on Jul 30

removes subdirectory and chat template loading

cfb5435

Tonic commited on Jul 30

removes flash attention from app

3448aad

Tonic commited on Jul 30

removes flash attention from requirements

37641fb

Tonic commited on Jul 30

makes modifications for zerogpu spaces

fbcc018

Tonic commited on Jul 30

adds flash attention 2 to attention implementation or eager to cpu

d749fc8

Tonic commited on Jul 30

adds flash attention 2 to attention implementation

435433d

Tonic commited on Jul 30

adds subdirectory back

5d56e20

Tonic commited on Jul 29

adds flash attention

109031b

Tonic commited on Jul 29

tries to improve the generation paramaters

d784738

Tonic commited on Jul 29

adds torchao

2ee7774

Tonic commited on Jul 29

add french description

1a6008e

Tonic commited on Jul 29

adds float32 defaults for quantized model tensors

55d7c97

Tonic commited on Jul 29

fix local model typo

a3113ce

Tonic commited on Jul 29

fix requests import error

f3832f5

Tonic commited on Jul 29

attempts to add chat template

9d0240c

Tonic commited on Jul 29

use the subfolder param

384c439

Tonic commited on Jul 29

last trt to download the model at build time using the scripts

5a6251e

Tonic commited on Jul 29

last try download int4 model from subfolder using hffilesystem

8dbd7e8

Tonic commited on Jul 29

tries to download the model at build time using the scripts

5b9c598

Tonic commited on Jul 29

tries to download the model at build time

19b19f0

Tonic commited on Jul 29

initial commit

6f9d970

Tonic commited on Jul 29

Spaces:

Tonic
/

Petite-LLM-3

Running on Zero

Commit History

Merge branch 'main' of https://huggingface.co/spaces/Tonic/Petite-LLM-3

53fac62

Running

small mods on the title and description

5975026

Update README.md

a4b7295
verified

test commit powershell

249d9cf

Remove test_download.py

6e00c9e

Remove test_app.py

bcd9c36

testing singing

0d91323

testing signing on hf

5333df3

adds minor changes to the README

0004ba8

adds special tokens strip with fallback

9413e52

adds debug

7578eea

removes int4 subfolder

3436b88

removes cache implementation static

3679e0b

removes subdirectory and chat template loading

cfb5435

removes flash attention from app

3448aad

removes flash attention from requirements

37641fb

makes modifications for zerogpu spaces

fbcc018

adds flash attention 2 to attention implementation or eager to cpu

d749fc8

adds flash attention 2 to attention implementation

435433d

adds subdirectory back

5d56e20

adds flash attention

109031b

tries to improve the generation paramaters

d784738

adds torchao

2ee7774

add french description

1a6008e

adds float32 defaults for quantized model tensors

55d7c97

fix local model typo

a3113ce

fix requests import error

f3832f5

attempts to add chat template

9d0240c

use the subfolder param

384c439

last trt to download the model at build time using the scripts

5a6251e

last try download int4 model from subfolder using hffilesystem

8dbd7e8

tries to download the model at build time using the scripts

5b9c598

tries to download the model at build time

19b19f0

initial commit

6f9d970

Commit History

Merge branch 'main' of https://huggingface.co/spaces/Tonic/Petite-LLM-3 53fac62 Running

small mods on the title and description 5975026

Update README.md a4b7295 verified

test commit powershell 249d9cf

Remove test_download.py 6e00c9e

Remove test_app.py bcd9c36

testing singing 0d91323

testing signing on hf 5333df3

adds minor changes to the README 0004ba8

adds special tokens strip with fallback 9413e52

adds debug 7578eea

removes int4 subfolder 3436b88

removes cache implementation static 3679e0b

removes subdirectory and chat template loading cfb5435

removes flash attention from app 3448aad

removes flash attention from requirements 37641fb

makes modifications for zerogpu spaces fbcc018

adds flash attention 2 to attention implementation or eager to cpu d749fc8

adds flash attention 2 to attention implementation 435433d

adds subdirectory back 5d56e20

adds flash attention 109031b

tries to improve the generation paramaters d784738

adds torchao 2ee7774

add french description 1a6008e

adds float32 defaults for quantized model tensors 55d7c97

fix local model typo a3113ce

fix requests import error f3832f5

attempts to add chat template 9d0240c

use the subfolder param 384c439

last trt to download the model at build time using the scripts 5a6251e

last try download int4 model from subfolder using hffilesystem 8dbd7e8

tries to download the model at build time using the scripts 5b9c598

tries to download the model at build time 19b19f0

initial commit 6f9d970

Merge branch 'main' of https://huggingface.co/spaces/Tonic/Petite-LLM-3

53fac62

Running

small mods on the title and description

5975026

Update README.md

a4b7295
verified

test commit powershell

249d9cf

Remove test_download.py

6e00c9e

Remove test_app.py

bcd9c36

testing singing

0d91323

testing signing on hf

5333df3

adds minor changes to the README

0004ba8

adds special tokens strip with fallback

9413e52

adds debug

7578eea

removes int4 subfolder

3436b88

removes cache implementation static

3679e0b

removes subdirectory and chat template loading

cfb5435

removes flash attention from app

3448aad

removes flash attention from requirements

37641fb

makes modifications for zerogpu spaces

fbcc018

adds flash attention 2 to attention implementation or eager to cpu

d749fc8

adds flash attention 2 to attention implementation

435433d

adds subdirectory back

5d56e20

adds flash attention

109031b

tries to improve the generation paramaters

d784738

adds torchao

2ee7774

add french description

1a6008e

adds float32 defaults for quantized model tensors

55d7c97

fix local model typo

a3113ce

fix requests import error

f3832f5

attempts to add chat template

9d0240c

use the subfolder param

384c439

last trt to download the model at build time using the scripts

5a6251e

last try download int4 model from subfolder using hffilesystem

8dbd7e8

tries to download the model at build time using the scripts

5b9c598

tries to download the model at build time

19b19f0

initial commit

6f9d970