110 Commits

Author	SHA1	Message	Date
GralchemOz	8a39f579d8	transformers: Add eager attention option to make Gemma-2 work properly (#6188)	2024-07-01 12:08:08 -03:00
oobabooga	4ea260098f	llama.cpp: add 4-bit/8-bit kv cache options	2024-06-29 09:10:33 -07:00
oobabooga	577a8cd3ee	Add TensorRT-LLM support (#5715)	2024-06-24 02:30:03 -03:00
oobabooga	536f8d58d4	Do not expose alpha_value to llama.cpp & rope_freq_base to transformers ... To avoid confusion	2024-06-23 22:09:24 -07:00
Forkoz	1d79aa67cf	Fix flash-attn UI parameter to actually store true. (#6076)	2024-06-13 00:34:54 -03:00
oobabooga	bd7cc4234d	Backend cleanup (#6025)	2024-05-21 13:32:02 -03:00
Philipp Emanuel Weidmann	852c943769	DRY: A modern repetition penalty that reliably prevents looping (#5677)	2024-05-19 23:53:47 -03:00
oobabooga	e61055253c	Bump llama-cpp-python to 0.2.69, add --flash-attn option	2024-05-03 04:31:22 -07:00
oobabooga	51fb766bea	Add back my llama-cpp-python wheels, bump to 0.2.65 (#5964)	2024-04-30 09:11:31 -03:00
oobabooga	9b623b8a78	Bump llama-cpp-python to 0.2.64, use official wheels (#5921)	2024-04-23 23:17:05 -03:00
oobabooga	d423021a48	Remove CTransformers support (#5807)	2024-04-04 20:23:58 -03:00
oobabooga	35da6b989d	Organize the parameters tab (#5767)	2024-03-28 16:45:03 -03:00
oobabooga	afb51bd5d6	Add StreamingLLM for llamacpp & llamacpp_HF (2nd attempt) (#5669)	2024-03-09 00:25:33 -03:00
oobabooga	2ec1d96c91	Add cache_4bit option for ExLlamaV2 (#5645)	2024-03-06 23:02:25 -03:00
kalomaze	cfb25c9b3f	Cubic sampling w/ curve param (#5551) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2024-03-03 13:22:21 -03:00
oobabooga	a6730f88f7	Add --autosplit flag for ExLlamaV2 (#5524)	2024-02-16 15:26:10 -03:00
oobabooga	2a1063eff5	Revert "Remove non-HF ExLlamaV2 loader (#5431)" ... This reverts commit cde000d478.	2024-02-06 06:21:36 -08:00
oobabooga	8c35fefb3b	Add custom sampler order support (#5443)	2024-02-06 11:20:10 -03:00
oobabooga	9033fa5eee	Organize the Model tab	2024-02-04 19:30:22 -08:00
Forkoz	2a45620c85	Split by rows instead of layers for llama.cpp multi-gpu (#5435)	2024-02-04 23:36:40 -03:00
oobabooga	cde000d478	Remove non-HF ExLlamaV2 loader (#5431)	2024-02-04 01:15:51 -03:00
kalomaze	b6077b02e4	Quadratic sampling (#5403) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2024-02-04 00:20:02 -03:00
oobabooga	87dc421ee8	Bump exllamav2 to 0.0.12 (#5352)	2024-01-22 22:40:12 -03:00
oobabooga	e055967974	Add prompt_lookup_num_tokens parameter (#5296)	2024-01-17 17:09:36 -03:00
oobabooga	372ef5e2d8	Fix dynatemp parameters always visible	2024-01-08 19:42:31 -08:00
oobabooga	29c2693ea0	dynatemp_low, dynatemp_high, dynatemp_exponent parameters (#5209)	2024-01-08 23:28:35 -03:00
oobabooga	0d07b3a6a1	Add dynamic_temperature_low parameter (#5198)	2024-01-07 17:03:47 -03:00
kalomaze	48327cc5c4	Dynamic Temperature HF loader support (#5174) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2024-01-07 10:36:26 -03:00
oobabooga	0e54a09bcb	Remove exllamav1 loaders (#5128)	2023-12-31 01:57:06 -03:00
oobabooga	c727a70572	Remove redundancy from modules/loaders.py	2023-12-20 19:18:07 -08:00
oobabooga	de138b8ba6	Add llama-cpp-python wheels with tensor cores support (#5003)	2023-12-19 17:30:53 -03:00
oobabooga	0a299d5959	Bump llama-cpp-python to 0.2.24 (#5001)	2023-12-19 15:22:21 -03:00
oobabooga	f6d701624c	UI: mention that QuIP# does not work on Windows	2023-12-18 18:05:02 -08:00
Water	674be9a09a	Add HQQ quant loader (#4888) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-12-18 21:23:16 -03:00
oobabooga	f1f2c4c3f4	Add --num_experts_per_token parameter (ExLlamav2) (#4955)	2023-12-17 12:08:33 -03:00
oobabooga	3bbf6c601d	AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this)	2023-12-15 06:46:13 -08:00
oobabooga	62d59a516f	Add trust_remote_code to all HF loaders	2023-12-08 06:29:26 -08:00
oobabooga	98361af4d5	Add QuIP# support (#4803) ... It has to be installed manually for now.	2023-12-06 00:01:01 -03:00
oobabooga	7fc9033b2e	Recommend ExLlama_HF and ExLlamav2_HF	2023-12-04 15:28:46 -08:00
oobabooga	9940ed9c77	Sort the loaders	2023-11-29 15:13:03 -08:00
oobabooga	a7670c31ca	Sort	2023-11-28 18:43:33 -08:00
oobabooga	6e51bae2e0	Sort the loaders menu	2023-11-28 18:41:11 -08:00
oobabooga	0589ff5b12	Bump llama-cpp-python to 0.2.19 & add min_p and typical_p parameters to llama.cpp loader (#4701)	2023-11-21 20:59:39 -03:00
oobabooga	e0ca49ed9c	Bump llama-cpp-python to 0.2.18 (2nd attempt) (#4637) ... * Update requirements*.txt * Add back seed	2023-11-18 00:31:27 -03:00
oobabooga	9d6f79db74	Revert "Bump llama-cpp-python to 0.2.18 (#4611)" ... This reverts commit 923c8e25fb.	2023-11-17 05:14:25 -08:00
oobabooga	8b66d83aa9	Set use_fast=True by default, create --no_use_fast flag ... This increases tokens/second for HF loaders.	2023-11-16 19:55:28 -08:00
oobabooga	923c8e25fb	Bump llama-cpp-python to 0.2.18 (#4611)	2023-11-16 22:55:14 -03:00
oobabooga	58c6001be9	Add missing exllamav2 samplers	2023-11-16 07:09:40 -08:00
oobabooga	af3d25a503	Disable logits_all in llamacpp_HF (makes processing 3x faster)	2023-11-07 14:35:48 -08:00
feng lui	4766a57352	transformers: add use_flash_attention_2 option (#4373)	2023-11-04 13:59:33 -03:00