oobabooga dfdb6fee22 Set llm_int8_enable_fp32_cpu_offload=True for --load-in-4bit ...

To allow for 32-bit CPU offloading (it's very slow).

2024-04-26 09:39:27 -07:00

..

grammar

Better HF grammar implementation (#4953)

2023-12-17 02:01:23 -03:00

AutoGPTQ_loader.py

AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this)

2023-12-15 06:46:13 -08:00

block_requests.py

Improved instruct style (with syntax highlighting & LaTeX rendering) (#5936)

2024-04-26 10:13:11 -03:00

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

Prevent double <BOS_TOKEN> with Command R+

2024-04-06 13:14:32 -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

Lint

2023-09-25 20:31:11 -07:00

GPTQ_loader.py

Improve several log messages

2023-12-19 20:54:32 -08:00

gradio_hijack.py

Bump gradio to 4.23 (#5758)

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

html_generator.py

Improved instruct style (with syntax highlighting & LaTeX rendering) (#5936)

2024-04-26 10:13:11 -03:00

llama_cpp_python_hijack.py

Bump llama-cpp-python to 0.2.64, use official wheels (#5921)

2024-04-23 23:17:05 -03:00

llamacpp_hf.py

Bump llama-cpp-python to 0.2.64, use official wheels (#5921)

2024-04-23 23:17:05 -03:00

llamacpp_model.py

Bump llama-cpp-python to 0.2.64, use official wheels (#5921)

2024-04-23 23:17:05 -03:00

loaders.py

Bump llama-cpp-python to 0.2.64, use official wheels (#5921)

2024-04-23 23:17:05 -03:00

logging_colors.py

Lint

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

logits.py

Add Ascend NPU support (basic) (#5541)

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

LoRA.py

Revert "Remove non-HF ExLlamaV2 loader (#5431)"

2024-02-06 06:21:36 -08:00

metadata_gguf.py

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

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

models_settings.py

Fix the Phi-3 template when used in the UI

2024-04-24 01:34:11 -07:00

models.py

Set llm_int8_enable_fp32_cpu_offload=True for --load-in-4bit

2024-04-26 09:39:27 -07:00

monkey_patch_gptq_lora.py

fix lora training with alpaca_lora_4bit (#3853)

2023-09-11 01:22:20 -03:00

one_click_installer_check.py

Lint

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

presets.py

Organize the parameters tab (#5767)

2024-03-28 16:45:03 -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

RoPE.py

Lint

2024-01-09 16:27:50 -08:00

sampler_hijack.py

Cubic sampling w/ curve param (#5551)

2024-03-03 13:22:21 -03:00

shared.py

Add back the max_updates_second parameter (#5937)

2024-04-26 10:14:51 -03:00

text_generation.py

Add back the max_updates_second parameter (#5937)

2024-04-26 10:14:51 -03:00

training.py

Perplexity evaluation: make UI events more robust (attempt)

2024-02-22 07:13:22 -08:00

ui_chat.py

UI: Focus on the chat input after starting a new chat

2024-04-06 12:57:57 -07:00

ui_default.py

Bump gradio to 4.23 (#5758)

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

ui_file_saving.py

Improve the file saving/deletion menus

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

ui_model_menu.py

Remove obsolete --tensorcores references

2024-04-24 00:31:28 -07:00

ui_notebook.py

Bump gradio to 4.23 (#5758)

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

ui_parameters.py

Add back the max_updates_second parameter (#5937)

2024-04-26 10:14:51 -03:00

ui_session.py

Bump gradio to 4.23 (#5758)

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

ui.py

Add back the max_updates_second parameter (#5937)

2024-04-26 10:14:51 -03:00

utils.py

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

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