Commits · featherless-ai/try-this-model

:wrench: apply reflection system prompt only to Reflection 70B

bd9ae66

Running

wxgeorge commited on 11 days ago

Fix html output

1ce20f1
verified

m8than commited on 11 days ago

:fire: revert manual chat templating for reflection now that it's working in featherless backend.

6f983da

wxgeorge commited on 12 days ago

Update app.py

2433428
verified

m8than commited on 12 days ago

Update app.py

7719c51
verified

m8than commited on 12 days ago

Update app.py

8c568be
verified

m8than commited on 12 days ago

Changed the concurrency limit.

b4b16a1
verified

m8than commited on 12 days ago

:pencil2: lead copy tuning

8abfddb

wxgeorge commited on 12 days ago

:sparkles: add Reflection-Llama to the annotations.

43df791

wxgeorge commited on 12 days ago

:heavy_plus_sign: I really only want transformers but just adding it seems to break HF?

ae83cd8

wxgeorge commited on 12 days ago

:poop: cheesy "de"chatformatization of response.

4c36b18

wxgeorge commited on 12 days ago

:sparkles: support mattshumer's Reflection

30bad6e

wxgeorge commited on 12 days ago

:sparkels: add button to facilitate returning to model card.

68492c3

wxgeorge commited on 14 days ago

:lipstick: keep chat interface filling the screen

34e11d5

wxgeorge commited on 14 days ago

:chart_with_upwards_trend: associate app attribution with inference request.

77ee232

wxgeorge commited on 14 days ago

:sparkles: update model cache constructor to include all models

988b5a0

wxgeorge commited on 15 days ago

:rocket: update model list

0810fbd

wxgeorge commited on 15 days ago

:wrench: update README to annotate only smaller models.

f3dd871

wxgeorge commited on Aug 12

:wrench: update model listing to avoid unintentionally listing larger models.

2018dd8

wxgeorge commited on Aug 12

:sparkles: make initial model choice change day over day.

a1c24d9

wxgeorge commited on Aug 12

:sparkles: model list update.

7302e17

wxgeorge commited on Aug 12

:sparkles: updating model list.

cc133a4

wxgeorge commited on Aug 6

:wrench: include unhealthy models in model cache as we expect this state to be transient.

8f28494

wxgeorge commited on Jul 30

:heavy_plus_sign: revving model list.

ae4c273

wxgeorge commited on Jul 30

:heavy_plus_sign: update list of supported models.

2c5c7ab

wxgeorge commited on Jul 18

:wrench: ensure model-cache is in sorted order for easier git inspection.

ccf3a62

wxgeorge commited on Jul 18

:truck: move model-cache.json back to root ... needed for space.

77d9d41

wxgeorge commited on Jul 18

:sparkles: add annotations for missing llama2-solar-10b7 models

2d50157

wxgeorge commited on Jul 18

:sparkles: script to auto-generate model annotations.

caba5f3

wxgeorge commited on Jul 18

:pencil: more instruction to the app.

e00ab88

wxgeorge commited on Jul 17

:pencil2: update card title.

a01b3a8

wxgeorge commited on Jul 17

:lipstick: adding featherless logo.

b0902ae

wxgeorge commited on Jul 17

:lock: restrict models to 15B or less.

5ae724e

wxgeorge commited on Jul 17

:wrench: annotating supported models in the space!

fc7d8b9

wxgeorge commited on Jul 17

:sparkles: initial commit!

e0ccd06

wxgeorge commited on Jul 17

Spaces:

featherless-ai
/

try-this-model

Running

Commit History

:wrench: apply reflection system prompt only to Reflection 70B

bd9ae66

Running

Fix html output

1ce20f1
verified

:fire: revert manual chat templating for reflection now that it's working in featherless backend.

6f983da

Update app.py

2433428
verified

Update app.py

7719c51
verified

Update app.py

8c568be
verified

Changed the concurrency limit.

b4b16a1
verified

:pencil2: lead copy tuning

8abfddb

:sparkles: add Reflection-Llama to the annotations.

43df791

:heavy_plus_sign: I really only want transformers but just adding it seems to break HF?

ae83cd8

:poop: cheesy "de"chatformatization of response.

4c36b18

:sparkles: support mattshumer's Reflection

30bad6e

:sparkels: add button to facilitate returning to model card.

68492c3

:lipstick: keep chat interface filling the screen

34e11d5

:chart_with_upwards_trend: associate app attribution with inference request.

77ee232

:sparkles: update model cache constructor to include all models

988b5a0

:rocket: update model list

0810fbd

:wrench: update README to annotate only smaller models.

f3dd871

:wrench: update model listing to avoid unintentionally listing larger models.

2018dd8

:sparkles: make initial model choice change day over day.

a1c24d9

:sparkles: model list update.

7302e17

:sparkles: updating model list.

cc133a4

:wrench: include unhealthy models in model cache as we expect this state to be transient.

8f28494

:heavy_plus_sign: revving model list.

ae4c273

:heavy_plus_sign: update list of supported models.

2c5c7ab

:wrench: ensure model-cache is in sorted order for easier git inspection.

ccf3a62

:truck: move model-cache.json back to root ... needed for space.

77d9d41

:sparkles: add annotations for missing llama2-solar-10b7 models

2d50157

:sparkles: script to auto-generate model annotations.

caba5f3

:pencil: more instruction to the app.

e00ab88

:pencil2: update card title.

a01b3a8

:lipstick: adding featherless logo.

b0902ae

:lock: restrict models to 15B or less.

5ae724e

:wrench: annotating supported models in the space!

fc7d8b9

:sparkles: initial commit!

e0ccd06

Commit History

:wrench: apply reflection system prompt only to Reflection 70B bd9ae66 Running

Fix html output 1ce20f1 verified

:fire: revert manual chat templating for reflection now that it's working in featherless backend. 6f983da

Update app.py 2433428 verified

Update app.py 7719c51 verified

Update app.py 8c568be verified

Changed the concurrency limit. b4b16a1 verified

:pencil2: lead copy tuning 8abfddb

:sparkles: add Reflection-Llama to the annotations. 43df791

:heavy_plus_sign: I really only want transformers but just adding it seems to break HF? ae83cd8

:poop: cheesy "de"chatformatization of response. 4c36b18

:sparkles: support mattshumer's Reflection 30bad6e

:sparkels: add button to facilitate returning to model card. 68492c3

:lipstick: keep chat interface filling the screen 34e11d5

:chart_with_upwards_trend: associate app attribution with inference request. 77ee232

:sparkles: update model cache constructor to include all models 988b5a0

:rocket: update model list 0810fbd

:wrench: update README to annotate only smaller models. f3dd871

:wrench: update model listing to avoid unintentionally listing larger models. 2018dd8

:sparkles: make initial model choice change day over day. a1c24d9

:sparkles: model list update. 7302e17

:sparkles: updating model list. cc133a4

:wrench: include unhealthy models in model cache as we expect this state to be transient. 8f28494

:heavy_plus_sign: revving model list. ae4c273

:heavy_plus_sign: update list of supported models. 2c5c7ab

:wrench: ensure model-cache is in sorted order for easier git inspection. ccf3a62

:truck: move model-cache.json back to root ... needed for space. 77d9d41

:sparkles: add annotations for missing llama2-solar-10b7 models 2d50157

:sparkles: script to auto-generate model annotations. caba5f3

:pencil: more instruction to the app. e00ab88

:pencil2: update card title. a01b3a8

:lipstick: adding featherless logo. b0902ae

:lock: restrict models to 15B or less. 5ae724e

:wrench: annotating supported models in the space! fc7d8b9

:sparkles: initial commit! e0ccd06

:wrench: apply reflection system prompt only to Reflection 70B

bd9ae66

Running

Fix html output

1ce20f1
verified

:fire: revert manual chat templating for reflection now that it's working in featherless backend.

6f983da

Update app.py

2433428
verified

Update app.py

7719c51
verified

Update app.py

8c568be
verified

Changed the concurrency limit.

b4b16a1
verified

:pencil2: lead copy tuning

8abfddb

:sparkles: add Reflection-Llama to the annotations.

43df791

:heavy_plus_sign: I really only want transformers but just adding it seems to break HF?

ae83cd8

:poop: cheesy "de"chatformatization of response.

4c36b18

:sparkles: support mattshumer's Reflection

30bad6e

:sparkels: add button to facilitate returning to model card.

68492c3

:lipstick: keep chat interface filling the screen

34e11d5

:chart_with_upwards_trend: associate app attribution with inference request.

77ee232

:sparkles: update model cache constructor to include all models

988b5a0

:rocket: update model list

0810fbd

:wrench: update README to annotate only smaller models.

f3dd871

:wrench: update model listing to avoid unintentionally listing larger models.

2018dd8

:sparkles: make initial model choice change day over day.

a1c24d9

:sparkles: model list update.

7302e17

:sparkles: updating model list.

cc133a4

:wrench: include unhealthy models in model cache as we expect this state to be transient.

8f28494

:heavy_plus_sign: revving model list.

ae4c273

:heavy_plus_sign: update list of supported models.

2c5c7ab

:wrench: ensure model-cache is in sorted order for easier git inspection.

ccf3a62

:truck: move model-cache.json back to root ... needed for space.

77d9d41

:sparkles: add annotations for missing llama2-solar-10b7 models

2d50157

:sparkles: script to auto-generate model annotations.

caba5f3

:pencil: more instruction to the app.

e00ab88

:pencil2: update card title.

a01b3a8

:lipstick: adding featherless logo.

b0902ae

:lock: restrict models to 15B or less.

5ae724e

:wrench: annotating supported models in the space!

fc7d8b9

:sparkles: initial commit!

e0ccd06