Commits · CrazyMonkey0/APi

test(tts): checking whether the tts model is working correctly

65952f6

CrazyMonkey0 commited on Dec 16, 2025

fix: optimize FastAPI + Qwen2.5-1.5B for CPU, reduce max_tokens, increase timeout

88284a4

CrazyMonkey0 commited on Dec 16, 2025

perf: implement lazy loading to fix startup timeouts

8f110eb

CrazyMonkey0 commited on Dec 15, 2025

build: use custom Docker base image from Docker Hub

fc8b522

CrazyMonkey0 commited on Dec 15, 2025

feat(docker): install llama-cpp-python directly with OpenBLAS

5adcb69

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): Add python alpine for llama-cpp-python

0442de3

CrazyMonkey0 commited on Dec 15, 2025

fix(requirements): adapting packages for Python 3.13

f42f941

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): switch version python to 3.12

482015f

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): switch to prebuilt llama-cpp-python image on Debian

33c584f

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): repair version dependecies

5d2827d

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): adding a permanent version of llama

06eacd3

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): replacing python:3.12-slim with python:3.12-alpine

ad141ba

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): add --prefer-binary

347b2fa

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): add --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

ef2c272

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): replacing python:3.12-alpine with python:3.12-slim

5c256f5

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): replacing apt-get with apk

38fe107

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): replacing python:3.12-slim with python:3.12-alpine

bf92c5c

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): replace llama-cpp-python extra index with pinned cp312 linux wheel

2a2937c

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): changing the option --only-binary=llama-cpp-python to --prefer-binary

8757f21

CrazyMonkey0 commited on Dec 15, 2025

fix(docker): add build dependencies for llama-cpp-python

c0cf206

CrazyMonkey0 commited on Dec 14, 2025

fix(docker): resolve llama-cpp-python module import error

fd4e818

CrazyMonkey0 commited on Dec 14, 2025

chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build

23187e2

CrazyMonkey0 commited on Dec 14, 2025

fix(docker): increase gunicorn worker timeout to 120s

101988f

CrazyMonkey0 commited on Dec 12, 2025

feat(nlp): reintroduce Qwen2.5-1.5B-Instruct model and migrate back to Transformers

94cf754

CrazyMonkey0 commited on Dec 12, 2025

fix(llama): fixed a bug with building llama

19edf1b

CrazyMonkey0 commited on Dec 12, 2025

fix(llama): clear cache after llama

ca4e6e3

CrazyMonkey0 commited on Dec 11, 2025

test(models): downloading models from transformers

fe8b413

CrazyMonkey0 commited on Dec 11, 2025

fix(lama.cpp): Add prebuilt lamma.cpp to docker

ad5570a

CrazyMonkey0 commited on Dec 11, 2025

fix(nlp): update Llama loading to use from_pretrained()

f7ec4f4

CrazyMonkey0 commited on Dec 11, 2025

feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel

f45e402

CrazyMonkey0 commited on Dec 11, 2025

Fix(nlp): NLP model download and build fix

89865a6

CrazyMonkey0 commited on Dec 11, 2025

Fix(docker): repair building llama.cpp

74de35c

CrazyMonkey0 commited on Dec 11, 2025

Fix(docker): start of the model when building the Docker image

9c29a0e

CrazyMonkey0 commited on Dec 11, 2025

Fix commad to run in dockerfile

0b8f94b

CrazyMonkey0 commited on Dec 11, 2025

Fix python version

420a9d9

CrazyMonkey0 commited on Dec 11, 2025

Fix dockerfile

385c547

CrazyMonkey0 commited on Dec 11, 2025

Initial APP

7eb3110

CrazyMonkey0 commited on Dec 11, 2025

Spaces:

CrazyMonkey0
/

APi_English

Sleeping

Commit History

test(tts): checking whether the tts model is working correctly

65952f6

fix: optimize FastAPI + Qwen2.5-1.5B for CPU, reduce max_tokens, increase timeout

88284a4

perf: implement lazy loading to fix startup timeouts

8f110eb

build: use custom Docker base image from Docker Hub

fc8b522

feat(docker): install llama-cpp-python directly with OpenBLAS

5adcb69

fix(docker): Add python alpine for llama-cpp-python

0442de3

fix(requirements): adapting packages for Python 3.13

f42f941

fix(docker): switch version python to 3.12

482015f

fix(docker): switch to prebuilt llama-cpp-python image on Debian

33c584f

fix(docker): repair version dependecies

5d2827d

fix(docker): adding a permanent version of llama

06eacd3

fix(docker): replacing python:3.12-slim with python:3.12-alpine

ad141ba

fix(docker): add --prefer-binary

347b2fa

fix(docker): add --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

ef2c272

fix(docker): replacing python:3.12-alpine with python:3.12-slim

5c256f5

fix(docker): replacing apt-get with apk

38fe107

fix(docker): replacing python:3.12-slim with python:3.12-alpine

bf92c5c

fix(docker): replace llama-cpp-python extra index with pinned cp312 linux wheel

2a2937c

fix(docker): changing the option --only-binary=llama-cpp-python to --prefer-binary

8757f21

fix(docker): add build dependencies for llama-cpp-python

c0cf206

fix(docker): resolve llama-cpp-python module import error

fd4e818

chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build

23187e2

fix(docker): increase gunicorn worker timeout to 120s

101988f

feat(nlp): reintroduce Qwen2.5-1.5B-Instruct model and migrate back to Transformers

94cf754

fix(llama): fixed a bug with building llama

19edf1b

fix(llama): clear cache after llama

ca4e6e3

test(models): downloading models from transformers

fe8b413

fix(lama.cpp): Add prebuilt lamma.cpp to docker

ad5570a

fix(nlp): update Llama loading to use from_pretrained()

f7ec4f4

feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel

f45e402

Fix(nlp): NLP model download and build fix

89865a6

Fix(docker): repair building llama.cpp

74de35c

Fix(docker): start of the model when building the Docker image

9c29a0e

Fix commad to run in dockerfile

0b8f94b

Fix python version

420a9d9

Fix dockerfile

385c547

Initial APP

7eb3110

Commit History

test(tts): checking whether the tts model is working correctly 65952f6

fix: optimize FastAPI + Qwen2.5-1.5B for CPU, reduce max_tokens, increase timeout 88284a4

perf: implement lazy loading to fix startup timeouts 8f110eb

build: use custom Docker base image from Docker Hub fc8b522

feat(docker): install llama-cpp-python directly with OpenBLAS 5adcb69

fix(docker): Add python alpine for llama-cpp-python 0442de3

fix(requirements): adapting packages for Python 3.13 f42f941

fix(docker): switch version python to 3.12 482015f

fix(docker): switch to prebuilt llama-cpp-python image on Debian 33c584f

fix(docker): repair version dependecies 5d2827d

fix(docker): adding a permanent version of llama 06eacd3

fix(docker): replacing python:3.12-slim with python:3.12-alpine ad141ba

fix(docker): add --prefer-binary 347b2fa

fix(docker): add --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu ef2c272

fix(docker): replacing python:3.12-alpine with python:3.12-slim 5c256f5

fix(docker): replacing apt-get with apk 38fe107

fix(docker): replacing python:3.12-slim with python:3.12-alpine bf92c5c

fix(docker): replace llama-cpp-python extra index with pinned cp312 linux wheel 2a2937c

fix(docker): changing the option --only-binary=llama-cpp-python to --prefer-binary 8757f21

fix(docker): add build dependencies for llama-cpp-python c0cf206

fix(docker): resolve llama-cpp-python module import error fd4e818

chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build 23187e2

fix(docker): increase gunicorn worker timeout to 120s 101988f

feat(nlp): reintroduce Qwen2.5-1.5B-Instruct model and migrate back to Transformers 94cf754

fix(llama): fixed a bug with building llama 19edf1b

fix(llama): clear cache after llama ca4e6e3

test(models): downloading models from transformers fe8b413

fix(lama.cpp): Add prebuilt lamma.cpp to docker ad5570a

fix(nlp): update Llama loading to use from_pretrained() f7ec4f4

feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel f45e402

Fix(nlp): NLP model download and build fix 89865a6

Fix(docker): repair building llama.cpp 74de35c

Fix(docker): start of the model when building the Docker image 9c29a0e

Fix commad to run in dockerfile 0b8f94b

Fix python version 420a9d9

Fix dockerfile 385c547

Initial APP 7eb3110

test(tts): checking whether the tts model is working correctly

65952f6

fix: optimize FastAPI + Qwen2.5-1.5B for CPU, reduce max_tokens, increase timeout

88284a4

perf: implement lazy loading to fix startup timeouts

8f110eb

build: use custom Docker base image from Docker Hub

fc8b522

feat(docker): install llama-cpp-python directly with OpenBLAS

5adcb69

fix(docker): Add python alpine for llama-cpp-python

0442de3

fix(requirements): adapting packages for Python 3.13

f42f941

fix(docker): switch version python to 3.12

482015f

fix(docker): switch to prebuilt llama-cpp-python image on Debian

33c584f

fix(docker): repair version dependecies

5d2827d

fix(docker): adding a permanent version of llama

06eacd3

fix(docker): replacing python:3.12-slim with python:3.12-alpine

ad141ba

fix(docker): add --prefer-binary

347b2fa

fix(docker): add --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

ef2c272

fix(docker): replacing python:3.12-alpine with python:3.12-slim

5c256f5

fix(docker): replacing apt-get with apk

38fe107

fix(docker): replacing python:3.12-slim with python:3.12-alpine

bf92c5c

fix(docker): replace llama-cpp-python extra index with pinned cp312 linux wheel

2a2937c

fix(docker): changing the option --only-binary=llama-cpp-python to --prefer-binary

8757f21

fix(docker): add build dependencies for llama-cpp-python

c0cf206

fix(docker): resolve llama-cpp-python module import error

fd4e818

chore(docker): reintroduce llama-cpp-python pre-built wheel for faster build

23187e2

fix(docker): increase gunicorn worker timeout to 120s

101988f

feat(nlp): reintroduce Qwen2.5-1.5B-Instruct model and migrate back to Transformers

94cf754

fix(llama): fixed a bug with building llama

19edf1b

fix(llama): clear cache after llama

ca4e6e3

test(models): downloading models from transformers

fe8b413

fix(lama.cpp): Add prebuilt lamma.cpp to docker

ad5570a

fix(nlp): update Llama loading to use from_pretrained()

f7ec4f4

feat(python): Change Python version to 3.11-bullseye for llama-cpp-python prebuilt wheel

f45e402

Fix(nlp): NLP model download and build fix

89865a6

Fix(docker): repair building llama.cpp

74de35c

Fix(docker): start of the model when building the Docker image

9c29a0e

Fix commad to run in dockerfile

0b8f94b

Fix python version

420a9d9

Fix dockerfile

385c547

Initial APP

7eb3110