2953 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
oobabooga	77abd9b69b	Add no_flash_attn option	2023-11-02 11:08:53 -07:00
Mehran Ziadloo	aaf726dbfb	Updating the shared settings object when loading a model (#4425)	2023-11-01 01:29:57 -03:00
oobabooga	9bd0724d85	Change frequency/presence penalty ranges	2023-10-31 20:57:56 -07:00
Orang	6b7fa45cc3	Update exllamav2 version (#4417)	2023-10-31 19:12:14 -03:00
Casper	41e159e88f	Bump AutoAWQ to v0.1.5 (#4410)	2023-10-31 19:11:22 -03:00
Meheret	0707ed7677	updated wiki link (#4415)	2023-10-31 19:09:05 -03:00
oobabooga	262f8ae5bb	Use default gr.Dataframe for evaluation table	2023-10-27 06:49:14 -07:00
James Braza	f481ce3dd8	Adding platform_system to autoawq (#4390)	2023-10-27 01:02:28 -03:00
dependabot[bot]	af98587580	Update accelerate requirement from ==0.23.* to ==0.24.* (#4400)	2023-10-27 00:46:16 -03:00
oobabooga	839a87bac8	Fix is_ccl_available & is_xpu_available imports	2023-10-26 20:27:04 -07:00
Abhilash Majumder	778a010df8	Intel Gpu support initialization (#4340)	2023-10-26 23:39:51 -03:00
GuizzyQC	317e2c857e	sd_api_pictures: fix Gradio warning message regarding custom value (#4391)	2023-10-26 23:03:21 -03:00
oobabooga	92b2f57095	Minor metadata bug fix (second attempt)	2023-10-26 18:57:32 -07:00
oobabooga	2d97897a25	Don't install flash-attention on windows + cuda 11	2023-10-25 11:21:18 -07:00
LightningDragon	0ced78fdfa	Replace hashlib.sha256 with hashlib.file_digest so we don't need to load entire files into ram before hashing them. (#4383)	2023-10-25 12:15:34 -03:00
tdrussell	72f6fc6923	Rename additive_repetition_penalty to presence_penalty, add frequency_penalty (#4376)	2023-10-25 12:10:28 -03:00
oobabooga	ef1489cd4d	Remove unused parameter in AutoAWQ	2023-10-23 20:45:43 -07:00
oobabooga	1edf321362	Lint	2023-10-23 13:09:03 -07:00
oobabooga	280ae720d7	Organize	2023-10-23 13:07:17 -07:00
oobabooga	49e5eecce4	Merge remote-tracking branch 'refs/remotes/origin/main'	2023-10-23 12:54:05 -07:00
oobabooga	82c11be067	Update 04 - Model Tab.md	2023-10-23 12:49:07 -07:00
oobabooga	306d764ff6	Minor metadata bug fix	2023-10-23 12:46:24 -07:00
adrianfiedler	4bc411332f	Fix broken links (#4367) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-23 14:09:57 -03:00
oobabooga	92691ee626	Disable trust_remote_code by default	2023-10-23 09:57:44 -07:00
tdrussell	4440f87722	Add additive_repetition_penalty sampler setting. (#3627)	2023-10-23 02:28:07 -03:00
oobabooga	6086768309	Bump gradio to 3.50.*	2023-10-22 21:21:26 -07:00
oobabooga	b8183148cf	Update 04 ‐ Model Tab.md	2023-10-22 17:15:55 -03:00
oobabooga	cea7fc2435	Update html_instruct_style.css	2023-10-22 12:28:23 -07:00
oobabooga	df90d03e0b	Replace --mul_mat_q with --no_mul_mat_q	2023-10-22 12:23:03 -07:00
Googulator	d0c3b407b3	transformers loader: multi-LoRAs support (#3120)	2023-10-22 16:06:22 -03:00
omo	4405513ca5	Option to select/target additional linear modules/layers in LORA training (#4178)	2023-10-22 15:57:19 -03:00
oobabooga	7a3f885ea8	Update 03 ‐ Parameters Tab.md	2023-10-22 14:52:23 -03:00
oobabooga	63688004dc	Add default cmd flags to colab	2023-10-22 09:56:43 -07:00
oobabooga	613feca23b	Make colab functional for llama.cpp ... - Download only Q4_K_M for GGUF repositories by default - Use maximum n-gpu-layers by default	2023-10-22 09:08:25 -07:00
oobabooga	994502d41b	Colab fixes	2023-10-22 08:57:16 -07:00
Jiashu Xu	c544f5cc51	Support LLaVA v1.5 7B (#4348)	2023-10-22 12:49:04 -03:00
oobabooga	05741821a5	Minor colab changes	2023-10-22 08:44:35 -07:00
FartyPants (FP HAM)	6a61158adf	Training PRO a month worth of updates (#4345)	2023-10-22 12:38:09 -03:00
mongolu	c18504f369	USE_CUDA118 from ENV remains null one_click.py + cuda-toolkit (#4352)	2023-10-22 12:37:24 -03:00
oobabooga	cd45635f53	tqdm improvement for colab	2023-10-21 22:00:29 -07:00
oobabooga	ae79c510cc	Merge remote-tracking branch 'refs/remotes/origin/main'	2023-10-21 21:46:15 -07:00
oobabooga	2d1b3332e4	Ignore warnings on Colab	2023-10-21 21:45:25 -07:00
oobabooga	caf6db07ad	Update README.md	2023-10-22 01:22:17 -03:00
oobabooga	1a34927314	Make API URLs more visible	2023-10-21 21:11:07 -07:00
oobabooga	09f807af83	Use ExLlama_HF for GPTQ models by default	2023-10-21 20:45:38 -07:00
oobabooga	619093483e	Add Colab notebook	2023-10-21 20:27:52 -07:00
oobabooga	506d05aede	Organize command-line arguments	2023-10-21 18:52:59 -07:00
oobabooga	b1f33b55fd	Update 01 ‐ Chat Tab.md	2023-10-21 20:17:56 -03:00
oobabooga	ac6d5d50b7	Update README.md	2023-10-21 20:03:43 -03:00
oobabooga	6efb990b60	Add a proper documentation (#3885)	2023-10-21 19:15:54 -03:00