bogdankostic 11440395f4

fix: Set model_max_length in the Tokenizer of DefaultPromptHandler (#5596) ...

* Set model_max_length in tokenizer in prompt handler

* Add release note

2023-09-01 11:48:41 +02:00

..

invocation_layer

feat: enable passing use_fast to the underlying transformers' pipeline (#5655)

2023-08-30 10:25:18 +02:00

__init__.py

Make promptnode test unit (#4420)

2023-03-15 22:17:23 +01:00

conftest.py

test: Rework conftest (#4614)

2023-04-11 10:33:43 +02:00

test_handlers.py

fix: Set model_max_length in the Tokenizer of DefaultPromptHandler (#5596)

2023-09-01 11:48:41 +02:00

test_prompt_model.py

feat: pass model parameters to HFLocalInvocationLayer via model_kwargs, enabling direct model usage (#4956)

2023-06-07 13:34:45 +02:00

test_prompt_node.py

feat: Remove template variables from PromptNode invocation kwargs (#5526)

2023-08-08 16:40:23 +02:00

test_prompt_template.py

feat: Remove template variables from PromptNode invocation kwargs (#5526)

2023-08-08 16:40:23 +02:00