oobabooga 907137a13d Automatically set bf16 & use_eager_attention for Gemma-2

2024-07-01 21:46:35 -07:00

..

grammar

Let grammar escape backslashes (#5865)

2024-05-19 20:26:09 -03:00

AutoGPTQ_loader.py

Backend cleanup (#6025)

2024-05-21 13:32:02 -03:00

block_requests.py

Handle another fix after 57119c1b300d8f7b1cc87c6aea9b1bf5a294d87f

2024-06-24 15:51:12 -07:00

cache_utils.py

Fix StreamingLLM when content is removed from the beginning of the prompt

2024-03-14 09:18:54 -07:00

callbacks.py

Add Ascend NPU support (basic) (#5541)

2024-04-11 18:42:20 -03:00

chat.py

Obtain the EOT token from the jinja template (attempt)

2024-06-30 15:09:22 -07:00

deepspeed_parameters.py

Fix typo in deepspeed_parameters.py (#3222)

2023-07-24 11:17:28 -03:00

evaluate.py

Perplexity evaluation: print to terminal after calculation is finished

2024-02-28 19:58:21 -08:00

exllamav2_hf.py

Update cache_4bit documentation (#5649)

2024-03-07 13:08:21 -03:00

exllamav2.py

Add cache_4bit option for ExLlamaV2 (#5645)

2024-03-06 23:02:25 -03:00

extensions.py

Move update_wizard_windows.sh to update_wizard_windows.bat (oops)

2024-03-04 19:26:24 -08:00

github.py

Fix several typos in the codebase (#6151)

2024-06-22 21:40:25 -03:00

gradio_hijack.py

Bump gradio to 4.23 (#5758)

2024-03-26 16:32:20 -03:00

html_generator.py

UI: handle another edge case while streaming lists

2024-06-26 18:40:43 -07:00

llama_cpp_python_hijack.py

Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964)

2024-04-30 09:11:31 -03:00

llamacpp_hf.py

llama.cpp: add 4-bit/8-bit kv cache options

2024-06-29 09:10:33 -07:00

llamacpp_model.py

llama.cpp: add 4-bit/8-bit kv cache options

2024-06-29 09:10:33 -07:00

loaders.py

transformers: Add eager attention option to make Gemma-2 work properly (#6188)

2024-07-01 12:08:08 -03:00

logging_colors.py

Lint

2023-12-19 21:36:57 -08:00

logits.py

Fix after previous commit

2024-06-13 19:54:12 -07:00

LoRA.py

Fix several typos in the codebase (#6151)

2024-06-22 21:40:25 -03:00

metadata_gguf.py

llama.cpp: read instruction template from GGUF metadata (#4975)

2023-12-18 01:51:58 -03:00

models_settings.py

Automatically set bf16 & use_eager_attention for Gemma-2

2024-07-01 21:46:35 -07:00

models.py

transformers: Add eager attention option to make Gemma-2 work properly (#6188)

2024-07-01 12:08:08 -03:00

one_click_installer_check.py

Lint

2023-11-16 18:03:06 -08:00

presets.py

DRY: A modern repetition penalty that reliably prevents looping (#5677)

2024-05-19 23:53:47 -03:00

prompts.py

Fix "send instruction template to..." buttons (closes #4625)

2023-11-16 18:16:42 -08:00

relative_imports.py

Add ExLlama+LoRA support (#2756)

2023-06-19 12:31:24 -03:00

sampler_hijack.py

Small fix to make transformers 4.42 functional

2024-06-27 17:05:29 -07:00

shared.py

transformers: Add eager attention option to make Gemma-2 work properly (#6188)

2024-07-01 12:08:08 -03:00

tensorrt_llm.py

Add TensorRT-LLM support (#5715)

2024-06-24 02:30:03 -03:00

text_generation.py

Add TensorRT-LLM support (#5715)

2024-06-24 02:30:03 -03:00

training.py

Backend cleanup (#6025)

2024-05-21 13:32:02 -03:00

ui_chat.py

UI: do not show the "save character" button in the Chat tab

2024-06-28 22:11:31 -07:00

ui_default.py

UI: remove unused gr.State variable from the Default tab

2024-06-28 15:17:44 -07:00

ui_file_saving.py

Improve the file saving/deletion menus

2024-01-09 06:33:47 -08:00

ui_model_menu.py

transformers: Add eager attention option to make Gemma-2 work properly (#6188)

2024-07-01 12:08:08 -03:00

ui_notebook.py

Avoid unnecessary calls UI -> backend, to make it faster

2024-06-12 20:52:42 -07:00

ui_parameters.py

UI: remove DRY info text

2024-06-26 15:33:11 -07:00

ui_session.py

Avoid unnecessary calls UI -> backend, to make it faster

2024-06-12 20:52:42 -07:00

ui.py

transformers: Add eager attention option to make Gemma-2 work properly (#6188)

2024-07-01 12:08:08 -03:00

utils.py

Add a menu for customizing the instruction template for the model (#5521)

2024-02-16 14:21:17 -03:00