Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-25 17:29:22 +01:00
Code Issues Packages Projects Releases Wiki Activity
3,698 Commits 2 Branches 52 Tags 67 MiB
1576227f16
Commit Graph

3698 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Forkoz
1576227f16
Fix GGUFs with no BOS token present, mainly qwen2 models. (#6119) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2024-06-14 13:51:01 -03:00
dependabot[bot]
fdd8fab9cf
Bump hqq from 0.1.7.post2 to 0.1.7.post3 (#6090) 2024-06-14 13:46:35 -03:00
oobabooga
10601850d9 Fix after previous commit 2024-06-13 19:54:12 -07:00
oobabooga
0f3a423de1 Alternative solution to "get next logits" deadlock (#6106) 2024-06-13 19:34:16 -07:00
oobabooga
9aef01551d Revert "Use reentrant generation lock (#6107)" 
This reverts commit b675151f25.
 2024-06-13 17:53:07 -07:00
oobabooga
8930bfc5f4
Bump PyTorch, ExLlamaV2, flash-attention (#6122) 2024-06-13 20:38:31 -03:00
oobabooga
386500aa37 Avoid unnecessary calls UI -> backend, to make it faster 2024-06-12 20:52:42 -07:00
Forkoz
1d79aa67cf
Fix flash-attn UI parameter to actually store true. (#6076) 2024-06-13 00:34:54 -03:00
Belladore
3abafee696
DRY sampler improvements (#6053) 2024-06-12 23:39:11 -03:00
theo77186
b675151f25
Use reentrant generation lock (#6107) 2024-06-12 23:25:05 -03:00
oobabooga
a36fa73071 Lint 2024-06-12 19:00:21 -07:00
oobabooga
2d196ed2fe Remove obsolete pre_layer parameter 2024-06-12 18:56:44 -07:00
Belladore
46174a2d33
Fix error when bos_token_id is None. (#6061) 2024-06-12 22:52:27 -03:00
Belladore
a363cdfca1
Fix missing bos token for some models (including Llama-3) (#6050) 2024-05-27 09:21:30 -03:00
oobabooga
8df68b05e9 Remove MinPLogitsWarper (it's now a transformers built-in) 2024-05-27 05:03:30 -07:00
oobabooga
4f1e96b9e3 Downloader: Add --model-dir argument, respect --model-dir in the UI 2024-05-23 20:42:46 -07:00
oobabooga
ad54d524f7 Revert "Fix stopping strings for llama-3 and phi (#6043)" 
This reverts commit 5499bc9bc8.
 2024-05-22 17:18:08 -07:00
oobabooga
5499bc9bc8
Fix stopping strings for llama-3 and phi (#6043) 2024-05-22 13:53:59 -03:00
rohitanshu
8aaa0a6f4e
Fixed minor typo in docs - Training Tab.md (#6038) 2024-05-21 14:52:22 -03:00
oobabooga
9e189947d1 Minor fix after bd7cc4234d (thanks @belladoreai) 2024-05-21 10:37:30 -07:00
oobabooga
ae86292159 Fix getting Phi-3-small-128k-instruct logits 2024-05-21 10:35:00 -07:00
oobabooga
bd7cc4234d
Backend cleanup (#6025) 2024-05-21 13:32:02 -03:00
oobabooga
6a1682aa95 README: update command-line flags with raw --help output 
This helps me keep this up-to-date more easily.
 2024-05-19 20:28:46 -07:00
Philipp Emanuel Weidmann
852c943769
DRY: A modern repetition penalty that reliably prevents looping (#5677) 2024-05-19 23:53:47 -03:00
oobabooga
9f77ed1b98
--idle-timeout flag to unload the model if unused for N minutes (#6026) 2024-05-19 23:29:39 -03:00
altoiddealer
818b4e0354
Let grammar escape backslashes (#5865) 2024-05-19 20:26:09 -03:00
Tisjwlf
907702c204
Fix gguf multipart file loading (#5857) 2024-05-19 20:22:09 -03:00
Guanghua Lu
d7bd3da35e
Add Llama 3 instruction template (#5891) 2024-05-19 20:17:26 -03:00
A0nameless0man
5cb59707f3
fix: grammar not support utf-8 (#5900) 2024-05-19 20:10:39 -03:00
Jari Van Melckebeke
8456d13349
[docs] small docker changes (#5917) 2024-05-19 20:09:37 -03:00
Samuel Wein
b63dc4e325
UI: Warn user if they are trying to load a model from no path (#6006) 2024-05-19 20:05:17 -03:00
dependabot[bot]
2de586f586
Update accelerate requirement from ==0.27.* to ==0.30.* (#5989) 2024-05-19 20:03:18 -03:00
chr
6b546a2c8b
llama.cpp: increase the max threads from 32 to 256 (#5889) 2024-05-19 20:02:19 -03:00
oobabooga
a38a37b3b3 llama.cpp: default n_gpu_layers to the maximum value for the model automatically 2024-05-19 10:57:42 -07:00
oobabooga
a4611232b7 Make --verbose output less spammy 2024-05-18 09:57:00 -07:00
oobabooga
0d90b3a25c Bump llama-cpp-python to 0.2.75 2024-05-18 05:26:26 -07:00
oobabooga
e225b0b995 downloader: fix downloading 01-ai/Yi-1.5-34B-Chat 2024-05-12 10:43:50 -07:00
oobabooga
9557f49f2f Bump llama-cpp-python to 0.2.73 2024-05-11 10:53:19 -07:00
oobabooga
7a728a38eb Update README 2024-05-07 02:59:36 -07:00
oobabooga
d5bde7babc UI: improve the performance of code syntax highlighting 2024-05-06 17:45:03 -07:00
oobabooga
0b193b8553 Downloader: handle one more retry case after 5770e06c48 2024-05-04 19:25:22 -07:00
oobabooga
cb31998605 Add a template for NVIDIA ChatQA models 2024-05-03 08:19:04 -07:00
oobabooga
e9c9483171 Improve the logging messages while loading models 2024-05-03 08:10:44 -07:00
oobabooga
e61055253c Bump llama-cpp-python to 0.2.69, add --flash-attn option 2024-05-03 04:31:22 -07:00
oobabooga
0476f9fe70 Bump ExLlamaV2 to 0.0.20 2024-05-01 16:20:50 -07:00
oobabooga
ae0f28530c Bump llama-cpp-python to 0.2.68 2024-05-01 08:40:50 -07:00
oobabooga
1eba888af6 Update FUNDING.yml 2024-05-01 05:54:21 -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
5770e06c48
Add a retry mechanism to the model downloader (#5943) 2024-04-27 12:25:28 -03:00
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