2900 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Brian Dashore	3345da2ea4	Add flash-attention 2 for windows (#4235)	2023-10-21 03:46:23 -03:00
oobabooga	258d046218	More robust way of initializing empty .git folder	2023-10-20 23:13:09 -07:00
Johan	1d5a015ce7	Enable special token support for exllamav2 (#4314)	2023-10-21 01:54:06 -03:00
mjbogusz	8f6405d2fa	Python 3.11, 3.9, 3.8 support (#4233) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-20 21:13:33 -03:00
oobabooga	9be74fb57c	Change 2 margins	2023-10-20 14:04:14 -07:00
oobabooga	e208128d68	Lint the CSS files	2023-10-20 13:02:18 -07:00
oobabooga	dedbdb46c2	Chat CSS improvements	2023-10-20 12:49:36 -07:00
Haotian Liu	32984ea2f0	Support LLaVA v1.5 (#4305)	2023-10-20 02:28:14 -03:00
oobabooga	bb71272903	Detect WizardCoder-Python-34B & Phind-CodeLlama-34B	2023-10-19 14:35:56 -07:00
oobabooga	eda7126b25	Organize the .gitignore	2023-10-19 14:33:44 -07:00
turboderp	ae8cd449ae	ExLlamav2_HF: Convert logits to FP32 (#4310)	2023-10-18 23:16:05 -03:00
missionfloyd	c0ffb77fd8	More silero languages (#3950)	2023-10-16 17:12:32 -03:00
hronoas	db7ecdd274	openai: fix empty models list on query present in url (#4139)	2023-10-16 17:02:47 -03:00
oobabooga	f17f7a6913	Increase the evaluation table height	2023-10-16 12:55:35 -07:00
oobabooga	8ea554bc19	Check for torch.xpu.is_available()	2023-10-16 12:53:40 -07:00
oobabooga	188d20e9e5	Reduce the evaluation table height	2023-10-16 10:53:42 -07:00
oobabooga	2d44adbb76	Clear the torch cache while evaluating	2023-10-16 10:52:50 -07:00
oobabooga	388d1864a6	Merge remote-tracking branch 'refs/remotes/origin/main'	2023-10-15 21:58:16 -07:00
oobabooga	71cac7a1b2	Increase the height of the evaluation table	2023-10-15 21:56:40 -07:00
oobabooga	e14bde4946	Minor improvements to evaluation logs	2023-10-15 20:51:43 -07:00
oobabooga	b88b2b74a6	Experimental Intel Arc transformers support (untested)	2023-10-15 20:51:11 -07:00
Sam	d331501ebc	Fix for using Torch with CUDA 11.8 (#4298)	2023-10-15 19:27:19 -03:00
oobabooga	3bb4046fad	Update auto-release.yml	2023-10-15 17:27:16 -03:00
oobabooga	45fa803943	Create auto-release.yml	2023-10-15 17:25:29 -03:00
Johan	2706394bfe	Relax numpy version requirements (#4291)	2023-10-15 12:05:06 -03:00
Forkoz	8cce1f1126	Exllamav2 lora support (#4229) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-14 16:12:41 -03:00
jllllll	1f5a2c5597	Use Pytorch 2.1 exllama wheels (#4285)	2023-10-14 15:27:59 -03:00
oobabooga	cd1cad1b47	Bump exllamav2	2023-10-14 11:23:07 -07:00
Eve	6e2dec82f1	add chatml support + mistral-openorca (#4275)	2023-10-13 11:49:17 -03:00
Jesus Alvarez	ed66ca3cdf	Add HTTPS support to APIs (openai and default) (#4270) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-13 01:31:13 -03:00
oobabooga	43be1be598	Manually install CUDA runtime libraries	2023-10-12 21:02:44 -07:00
oobabooga	faf5c4dd58	Fix code blocks in instruct mode	2023-10-11 12:18:46 -07:00
oobabooga	773c17faec	Fix a warning	2023-10-10 20:53:38 -07:00
oobabooga	f63361568c	Fix safetensors kwarg usage in AutoAWQ	2023-10-10 19:03:09 -07:00
oobabooga	39f16ff83d	Fix default/notebook tabs css	2023-10-10 18:45:12 -07:00
oobabooga	fae8062d39	Bump to latest gradio (3.47) (#4258)	2023-10-10 22:20:49 -03:00
Haotian Liu	2b75d725e6	Initial support for LLaVA-LLaMA-2. (#3377)	2023-10-10 18:40:52 -03:00
oobabooga	9fab9a1ca6	Minor fix	2023-10-10 14:08:11 -07:00
oobabooga	a49cc69a4a	Ignore rope_freq_base if value is 10000	2023-10-10 13:57:40 -07:00
oobabooga	3a9d90c3a1	Download models with 4 threads by default	2023-10-10 13:52:10 -07:00
dependabot[bot]	520cbb2ab1	Bump safetensors from 0.3.2 to 0.4.0 (#4249)	2023-10-10 17:41:09 -03:00
Forkoz	35695e18c7	Remove import. (#4247) ... For real this time.	2023-10-09 18:06:11 -03:00
Forkoz	2e471071af	Update llama_attn_hijack.py (#4231)	2023-10-08 15:16:48 -03:00
oobabooga	2e8b5f7c80	Update ROCm command	2023-10-08 10:12:13 -03:00
oobabooga	00187d641a	Note about pytorch 2.1 breaking change	2023-10-08 10:10:38 -03:00
oobabooga	1c6e57dd68	Note about pytorch 2.1 breaking change	2023-10-08 10:09:22 -03:00
oobabooga	cf4d89ee65	Lint the javascript code	2023-10-07 19:07:57 -07:00
James Braza	8614c9d085	README for superboogav2 (#4212) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-07 19:50:39 -03:00
Brian Dashore	98fa73a974	Text Generation: stop if EOS token is reached (#4213)	2023-10-07 19:46:42 -03:00
Brian Dashore	7743b5e9de	Llamacpp_HF: Fix CFG cache init (#4219) ... Documentation says that model.context_params should be sent when a new context is created. The current code uses model.params which doesn't exist. Signed-off-by: kingbri <bdashore3@proton.me>	2023-10-07 19:38:29 -03:00