Commits · Pyboxs/hf-llm-api

:hammer: [WIP] Try to enable conversation api

1e3a144

Hansimov commited on Apr 6, 2024

:zap: [Enhance] Handle if http_proxy is None, and prettify logs

f3e7da4

Hansimov commited on Apr 6, 2024

:gem: [Feature] New api for chat_requiements, and moduralize logs

1ee4f76

Hansimov commited on Apr 6, 2024

:recycle: [Refactor] Prettify initializaiton of OpenaiAPI requests params

96d1023

Hansimov commited on Apr 6, 2024

:gem: [Feature] Enable get models of chat.openai.com

51e07f2

Hansimov commited on Apr 6, 2024

:boom: [Fix] Revert chat templates with mannual version as nous-mixtral-8x7b behaves weirdly

dc3b7a9

Hansimov commited on Mar 1, 2024

:recycle: [Refactor] Use official chat_template to replace mannual parses for several models, and remove unused message split functions

4a9e46f

Hansimov commited on Mar 1, 2024

:boom: [Fix] [Errno 13] Permission denied: '/.cache'

e491840

Hansimov commited on Mar 1, 2024

:recycle: [Refactor] Move AVAILABLE_MODELS(_DICTS) to constants

40ba0ea

Hansimov commited on Mar 1, 2024

:recycle: [Refactor] Move STOP_SEQUENCES_MAP and TOKEN_LIMIT_MAP to constants

bf8c5bd

Hansimov commited on Mar 1, 2024

:recycle: [Refactor] Move MODELS_MAP to constants

3f608c6

Hansimov commited on Mar 1, 2024

:gem: [Feature] Support new model: openchat-3.5-0106

9f5d69c

Hansimov commited on Mar 1, 2024

:gem: [Feature] New model enabled: gemma-7b

77b5a47

Hansimov commited on Feb 22, 2024

:hammer: [Test] Enable deployment in vercel

fdc9940

Hansimov commited on Feb 11, 2024

:zap: [Enhance] Set min and max for top_p

64645f0

Hansimov commited on Jan 28, 2024

:gem: [Feature] Add top_p and set 0.95 as default

403b8cf

Hansimov commited on Jan 28, 2024

:gem: [Feature] Add use_cache parameter, and set default temperature to 0.5

e2b245b

Hansimov commited on Jan 28, 2024

:boom: [Fix] Missing system message for original mistral models

395e196

Hansimov commited on Jan 22, 2024

:zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility

a2d3414

Hansimov commited on Jan 22, 2024

:gem: [Feature] ChatAPIApp: New /readme route

6e2fad5

Hansimov commited on Jan 22, 2024

:pencil: [Doc] New model, and prettify formats

37be019

Hansimov commited on Jan 22, 2024

:zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route

06a233d

Hansimov commited on Jan 22, 2024

:gem: [Feature] New model enabled: nous-mixtral-8-7b

4a28ca5

Hansimov commited on Jan 22, 2024

:zap: [Enhance] Align /models response with openai format

245d9fd

Hansimov commited on Jan 16, 2024

:pencil: [Doc] Update available models

acbd8bf

Hansimov commited on Jan 15, 2024

:zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability

6d3fdc0

Hansimov commited on Jan 15, 2024

:zap: [Enhance] Remove openchat-3.5 from available models

06c8d58

Hansimov commited on Jan 15, 2024

:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768

fa3bfb0

Hansimov commited on Jan 11, 2024

:boom: [Fix] temperature must be strictly positive

eb00725

Hansimov commited on Jan 11, 2024

:boom: [Fix] Error 500 when temperature is null

8ba223c

Hansimov commited on Jan 8, 2024

:boom: [Fix] Error 422 when max_tokens is null

a54e7a6

Hansimov commited on Jan 8, 2024

:zap: [Enhance] Auto calculate max_tokens if not set

1b9f698

Hansimov commited on Jan 8, 2024

:zap: [Enhance] Remove leading whitespaces of first response

c95d47e

Hansimov commited on Jan 5, 2024

:boom: [Fix] Ignore invalid HF Token

8ab8ca6

Hansimov commited on Jan 5, 2024

:pencil: [Doc] Available models: More comments on dropped models

85354a9

Hansimov commited on Jan 5, 2024

:pencil: [Doc] Readme: New models, api key and no-stream mode, and models to support

cec776f

Hansimov commited on Dec 28, 2023

:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages

30421b7

Hansimov commited on Dec 28, 2023

:gem: [Feature] MessageStreamer: Support stop sequence and auto removal

4ba2ca6

Hansimov commited on Dec 28, 2023

:zap: [Enhance] Update available models description

c769be6

Hansimov commited on Dec 28, 2023

:zap: [Enhance] Support provide api_key with os env HF_TOKEN

bc384a3

Hansimov commited on Dec 28, 2023

:gem: [Feature] Support call hf api with api_key via HTTP Bearer

2da6968

Hansimov commited on Dec 28, 2023

:gem: [Feature] Support no-stream mode with dict response

d2b20f2

Hansimov commited on Dec 27, 2023

:boom: [Fix] Suppress ping message by increasing ping interval

489b65b

Hansimov commited on Dec 26, 2023

:pencil: [Doc] Readme for features, and comments for references

e820e51

Hansimov commited on Dec 20, 2023

:zap: [Enhance] Cleaner logger output

b96cef7

Hansimov commited on Dec 20, 2023

:zap: [Enhance] New models: mistral-7b and openchat-3.5

e916990

Hansimov commited on Dec 20, 2023

:zap: [Enhance] OSLogger: Re-wrap for better syntax check, and move stream log to debug

047008b

Hansimov commited on Dec 20, 2023

:pencil: [Comment] References of requests params

395ee29

Hansimov commited on Dec 20, 2023

:zap: [Enhance] Default models and max_new_tokens

6aa8b86

Hansimov commited on Dec 20, 2023

:zap: [Enhance] API: Ensure temperature to be positive

3dfcb72

Hansimov commited on Dec 19, 2023

Commit History

:hammer: [WIP] Try to enable conversation api 1e3a144

:zap: [Enhance] Handle if http_proxy is None, and prettify logs f3e7da4

:gem: [Feature] New api for chat_requiements, and moduralize logs 1ee4f76

:recycle: [Refactor] Prettify initializaiton of OpenaiAPI requests params 96d1023

:gem: [Feature] Enable get models of chat.openai.com 51e07f2

:boom: [Fix] Revert chat templates with mannual version as nous-mixtral-8x7b behaves weirdly dc3b7a9

:recycle: [Refactor] Use official chat_template to replace mannual parses for several models, and remove unused message split functions 4a9e46f

:boom: [Fix] [Errno 13] Permission denied: '/.cache' e491840

:recycle: [Refactor] Move AVAILABLE_MODELS(_DICTS) to constants 40ba0ea

:recycle: [Refactor] Move STOP_SEQUENCES_MAP and TOKEN_LIMIT_MAP to constants bf8c5bd

:recycle: [Refactor] Move MODELS_MAP to constants 3f608c6

:gem: [Feature] Support new model: openchat-3.5-0106 9f5d69c

:gem: [Feature] New model enabled: gemma-7b 77b5a47

:hammer: [Test] Enable deployment in vercel fdc9940

:zap: [Enhance] Set min and max for top_p 64645f0

:gem: [Feature] Add top_p and set 0.95 as default 403b8cf

:gem: [Feature] Add use_cache parameter, and set default temperature to 0.5 e2b245b

:boom: [Fix] Missing system message for original mistral models 395e196

:zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility a2d3414

:gem: [Feature] ChatAPIApp: New /readme route 6e2fad5

:pencil: [Doc] New model, and prettify formats 37be019

:zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route 06a233d

:gem: [Feature] New model enabled: nous-mixtral-8-7b 4a28ca5

:zap: [Enhance] Align /models response with openai format 245d9fd

:pencil: [Doc] Update available models acbd8bf

:zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability 6d3fdc0

:zap: [Enhance] Remove openchat-3.5 from available models 06c8d58

:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768 fa3bfb0

:boom: [Fix] temperature must be strictly positive eb00725

:boom: [Fix] Error 500 when temperature is null 8ba223c

:boom: [Fix] Error 422 when max_tokens is null a54e7a6

:zap: [Enhance] Auto calculate max_tokens if not set 1b9f698

:zap: [Enhance] Remove leading whitespaces of first response c95d47e

:boom: [Fix] Ignore invalid HF Token 8ab8ca6

:pencil: [Doc] Available models: More comments on dropped models 85354a9

:pencil: [Doc] Readme: New models, api key and no-stream mode, and models to support cec776f

:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages 30421b7

:gem: [Feature] MessageStreamer: Support stop sequence and auto removal 4ba2ca6

:zap: [Enhance] Update available models description c769be6

:zap: [Enhance] Support provide api_key with os env HF_TOKEN bc384a3

:gem: [Feature] Support call hf api with api_key via HTTP Bearer 2da6968

:gem: [Feature] Support no-stream mode with dict response d2b20f2

:boom: [Fix] Suppress ping message by increasing ping interval 489b65b

:pencil: [Doc] Readme for features, and comments for references e820e51

:zap: [Enhance] Cleaner logger output b96cef7

:zap: [Enhance] New models: mistral-7b and openchat-3.5 e916990

:zap: [Enhance] OSLogger: Re-wrap for better syntax check, and move stream log to debug 047008b

:pencil: [Comment] References of requests params 395ee29

:zap: [Enhance] Default models and max_new_tokens 6aa8b86

:zap: [Enhance] API: Ensure temperature to be positive 3dfcb72

:hammer: [WIP] Try to enable conversation api

1e3a144

:zap: [Enhance] Handle if http_proxy is None, and prettify logs

f3e7da4

:gem: [Feature] New api for chat_requiements, and moduralize logs

1ee4f76

:recycle: [Refactor] Prettify initializaiton of OpenaiAPI requests params

96d1023

:gem: [Feature] Enable get models of chat.openai.com

51e07f2

:boom: [Fix] Revert chat templates with mannual version as nous-mixtral-8x7b behaves weirdly

dc3b7a9

:recycle: [Refactor] Use official chat_template to replace mannual parses for several models, and remove unused message split functions

4a9e46f

:boom: [Fix] [Errno 13] Permission denied: '/.cache'

e491840

:recycle: [Refactor] Move AVAILABLE_MODELS(_DICTS) to constants

40ba0ea

:recycle: [Refactor] Move STOP_SEQUENCES_MAP and TOKEN_LIMIT_MAP to constants

bf8c5bd

:recycle: [Refactor] Move MODELS_MAP to constants

3f608c6

:gem: [Feature] Support new model: openchat-3.5-0106

9f5d69c

:gem: [Feature] New model enabled: gemma-7b

77b5a47

:hammer: [Test] Enable deployment in vercel

fdc9940

:zap: [Enhance] Set min and max for top_p

64645f0

:gem: [Feature] Add top_p and set 0.95 as default

403b8cf

:gem: [Feature] Add use_cache parameter, and set default temperature to 0.5

e2b245b

:boom: [Fix] Missing system message for original mistral models

395e196

:zap: [Enhance] Display schema of /api/v1 for user-friendly compatibility

a2d3414

:gem: [Feature] ChatAPIApp: New /readme route

6e2fad5

:pencil: [Doc] New model, and prettify formats

37be019

:zap: [Enhance] ChatAPIApp: Only include schema for non-prefix route

06a233d

:gem: [Feature] New model enabled: nous-mixtral-8-7b

4a28ca5

:zap: [Enhance] Align /models response with openai format

245d9fd

:pencil: [Doc] Update available models

acbd8bf

:zap: [Enhance] add /api/v1 prefix for hf banning and ui compatability

6d3fdc0

:zap: [Enhance] Remove openchat-3.5 from available models

06c8d58

:boom: [Fix] inputs_tokens + max_new_tokens must <= 32768

fa3bfb0

:boom: [Fix] temperature must be strictly positive

eb00725

:boom: [Fix] Error 500 when temperature is null

8ba223c

:boom: [Fix] Error 422 when max_tokens is null

a54e7a6

:zap: [Enhance] Auto calculate max_tokens if not set

1b9f698

:zap: [Enhance] Remove leading whitespaces of first response

c95d47e

:boom: [Fix] Ignore invalid HF Token

8ab8ca6

:pencil: [Doc] Available models: More comments on dropped models

85354a9

:pencil: [Doc] Readme: New models, api key and no-stream mode, and models to support

cec776f

:gem: [Feature] MessageComposer: Support openchat-3.5, and generalize preprocessing stages

30421b7

:gem: [Feature] MessageStreamer: Support stop sequence and auto removal

4ba2ca6

:zap: [Enhance] Update available models description

c769be6

:zap: [Enhance] Support provide api_key with os env HF_TOKEN

bc384a3

:gem: [Feature] Support call hf api with api_key via HTTP Bearer

2da6968

:gem: [Feature] Support no-stream mode with dict response

d2b20f2

:boom: [Fix] Suppress ping message by increasing ping interval

489b65b

:pencil: [Doc] Readme for features, and comments for references

e820e51

:zap: [Enhance] Cleaner logger output

b96cef7

:zap: [Enhance] New models: mistral-7b and openchat-3.5

e916990

:zap: [Enhance] OSLogger: Re-wrap for better syntax check, and move stream log to debug

047008b

:pencil: [Comment] References of requests params

395ee29

:zap: [Enhance] Default models and max_new_tokens

6aa8b86

:zap: [Enhance] API: Ensure temperature to be positive

3dfcb72