Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-28 18:48:04 +01:00
Code Issues Packages Projects Releases Wiki Activity
3,468 Commits 3 Branches 52 Tags 67 MiB
33c4ce0720
Commit Graph

1230 Commits

Author SHA1 Message Date
oobabooga
f1f2c4c3f4
Add --num_experts_per_token parameter (ExLlamav2) (#4955) 2023-12-17 12:08:33 -03:00
oobabooga
12690d3ffc
Better HF grammar implementation (#4953) 2023-12-17 02:01:23 -03:00
oobabooga
f8079d067d UI: save the sent chat message on "no model is loaded" error 2023-12-16 10:52:41 -08:00
oobabooga
3bbf6c601d AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this) 2023-12-15 06:46:13 -08:00
oobabooga
2cb5b68ad9
Bug fix: when generation fails, save the sent message (#4915) 2023-12-15 01:01:45 -03:00
Kim Jaewon
e53f99faa0
[OpenAI Extension] Add 'max_logits' parameter in logits endpoint (#4916) 2023-12-15 00:22:43 -03:00
Lounger
5754f0c357
Fix deleting chat logs (#4914) 2023-12-13 21:54:43 -03:00
Bartowski
f51156705d
Allow symlinked folder within root directory (#4863) 2023-12-13 18:08:21 -03:00
Ixion
3f3960dbfb
Fixed invalid Jinja2 syntax in instruction templates (#4911) 2023-12-13 15:46:23 -03:00
oobabooga
fcf5512364 Jinja templates: fix a potential small bug 2023-12-13 10:19:39 -08:00
oobabooga
7f1a6a70e3 Update the llamacpp_HF comment 2023-12-12 21:04:20 -08:00
oobabooga
1c531a3713 Minor cleanup 2023-12-12 13:25:21 -08:00
oobabooga
8513028968 Fix lag in the chat tab during streaming 2023-12-12 13:01:25 -08:00
oobabooga
39d2fe1ed9
Jinja templates for Instruct and Chat (#4874) 2023-12-12 17:23:14 -03:00
oobabooga
aab0dd962d Revert "Update callbacks.py to show tracebacks on ValueError (#4892)" 
This reverts commit 993ca51a65.
 2023-12-12 11:47:11 -08:00
Nehereus
993ca51a65
Update callbacks.py to show tracebacks on ValueError (#4892) 2023-12-12 02:29:27 -03:00
Morgan Schweers
602b8c6210
Make new browser reloads recognize current model. (#4865) 2023-12-11 02:51:01 -03:00
oobabooga
8c8825b777 Add QuIP# to README 2023-12-08 08:40:42 -08:00
oobabooga
2a335b8aa7 Cleanup: set shared.model_name only once 2023-12-08 06:35:23 -08:00
oobabooga
62d59a516f Add trust_remote_code to all HF loaders 2023-12-08 06:29:26 -08:00
oobabooga
181743fd97 Fix missing spaces tokenizer issue (closes #4834) 2023-12-08 05:16:46 -08:00
Yiximail
1c74b3ab45
Fix partial unicode characters issue (#4837) 2023-12-08 09:50:53 -03:00
oobabooga
2c5a1e67f9
Parameters: change max_new_tokens & repetition_penalty_range defaults (#4842) 2023-12-07 20:04:52 -03:00
oobabooga
98361af4d5
Add QuIP# support (#4803) 
It has to be installed manually for now.
 2023-12-06 00:01:01 -03:00
oobabooga
6430acadde Minor bug fix after https://github.com/oobabooga/text-generation-webui/pull/4814 2023-12-05 10:08:11 -08:00
oobabooga
0f828ea441 Do not limit API updates/second 2023-12-04 20:45:43 -08:00
oobabooga
9edb193def
Optimize HF text generation (#4814) 2023-12-05 00:00:40 -03:00
俞航
ac9f154bcc
Bump exllamav2 from 0.0.8 to 0.0.10 & Fix code change (#4782) 2023-12-04 21:15:05 -03:00
oobabooga
131a5212ce UI: update context upper limit to 200000 2023-12-04 15:48:34 -08:00
oobabooga
be88b072e9 Update --loader flag description 2023-12-04 15:41:25 -08:00
oobabooga
7fc9033b2e Recommend ExLlama_HF and ExLlamav2_HF 2023-12-04 15:28:46 -08:00
Lounger
7c0a17962d
Gallery improvements (#4789) 2023-12-03 22:45:50 -03:00
oobabooga
77d6ccf12b Add a LOADER debug message while loading models 2023-11-30 12:00:32 -08:00
oobabooga
092a2c3516 Fix a bug in llama.cpp get_logits() function 2023-11-30 11:21:40 -08:00
oobabooga
2698d7c9fd Fix llama.cpp model unloading 2023-11-29 15:19:48 -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
68059d7c23 llama.cpp: minor log change & lint 2023-11-27 10:44:55 -08:00
tsukanov-as
9f7ae6bb2e
fix detection of stopping strings when HTML escaping is used (#4728) 2023-11-27 15:42:08 -03:00
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
2769a1fa25 Hide deprecated args from Session tab 2023-11-21 15:15:16 -08:00
oobabooga
a2e6d00128 Use convert_ids_to_tokens instead of decode in logits endpoint 
This preserves the llama tokenizer spaces.
 2023-11-19 09:22:08 -08:00
oobabooga
9da7bb203d Minor LoRA bug fix 2023-11-19 07:59:29 -08:00
oobabooga
a6f1e1bcc5 Fix PEFT LoRA unloading 2023-11-19 07:55:25 -08:00
oobabooga
ab94f0d9bf Minor style change 2023-11-18 21:11:04 -08:00
oobabooga
5fcee696ea
New feature: enlarge character pictures on click (#4654) 2023-11-19 02:05:17 -03:00
oobabooga
ef6feedeb2
Add --nowebui flag for pure API mode (#4651) 2023-11-18 23:38:39 -03:00
oobabooga
0fa1af296c
Add /v1/internal/logits endpoint (#4650) 2023-11-18 23:19:31 -03:00
oobabooga
8f4f4daf8b
Add --admin-key flag for API (#4649) 2023-11-18 22:33:27 -03:00
Jordan Tucker
baab894759
fix: use system message in chat-instruct mode (#4648) 2023-11-18 20:20:13 -03:00
oobabooga
47d9e2618b Refresh the Preset menu after saving a preset 2023-11-18 14:03:42 -08:00
oobabooga
83b64e7fc1
New feature: "random preset" button (#4647) 2023-11-18 18:31:41 -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
13dc3b61da Update README 2023-11-16 19:57:55 -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
6525707a7f Fix "send instruction template to..." buttons (closes #4625) 2023-11-16 18:16:42 -08:00
oobabooga
510a01ef46 Lint 2023-11-16 18:03:06 -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
cd41f8912b Warn users about n_ctx / max_seq_len 2023-11-15 18:56:42 -08:00
oobabooga
9be48e83a9 Start API when "api" checkbox is checked 2023-11-15 16:35:47 -08:00
oobabooga
a85ce5f055 Add more info messages for truncation / instruction template 2023-11-15 16:20:31 -08:00
oobabooga
883701bc40 Alternative solution to 025da386a0 
Fixes an error.
 2023-11-15 16:04:02 -08:00
oobabooga
8ac942813c Revert "Fix CPU memory limit error (issue #3763) (#4597)" 
This reverts commit 025da386a0.
 2023-11-15 16:01:54 -08:00
oobabooga
e6f44d6d19 Print context length / instruction template to terminal when loading models 2023-11-15 16:00:51 -08:00
oobabooga
e05d8fd441 Style changes 2023-11-15 15:51:37 -08:00
Andy Bao
025da386a0
Fix CPU memory limit error (issue #3763) (#4597) 
get_max_memory_dict() was not properly formatting shared.args.cpu_memory

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-11-15 20:27:20 -03:00
oobabooga
4aabff3728 Remove old API, launch OpenAI API with --api 2023-11-10 06:39:08 -08:00
oobabooga
2af7e382b1 Revert "Bump llama-cpp-python to 0.2.14" 
This reverts commit 5c3eb22ce6.

The new version has issues:

https://github.com/oobabooga/text-generation-webui/issues/4540
https://github.com/abetlen/llama-cpp-python/issues/893
 2023-11-09 10:02:13 -08:00
oobabooga
21ed9a260e Document the new "Custom system message" field 2023-11-08 17:54:10 -08:00
oobabooga
2358706453 Add /v1/internal/model/load endpoint (tentative) 2023-11-07 20:58:06 -08:00
oobabooga
43c53a7820 Refactor the /v1/models endpoint 2023-11-07 19:59:27 -08:00
oobabooga
1b69694fe9 Add types to the encode/decode/token-count endpoints 2023-11-07 19:32:14 -08:00
oobabooga
6e2e0317af
Separate context and system message in instruction formats (#4499) 2023-11-07 20:02:58 -03:00
oobabooga
5c0559da69 Training: fix .txt files now showing in dropdowns 2023-11-07 14:41:11 -08:00
oobabooga
af3d25a503 Disable logits_all in llamacpp_HF (makes processing 3x faster) 2023-11-07 14:35:48 -08:00
oobabooga
5c3eb22ce6 Bump llama-cpp-python to 0.2.14 2023-11-07 14:20:43 -08:00
oobabooga
ec17a5d2b7
Make OpenAI API the default API (#4430) 2023-11-06 02:38:29 -03:00
feng lui
4766a57352
transformers: add use_flash_attention_2 option (#4373) 2023-11-04 13:59:33 -03:00
wouter van der plas
add359379e
fixed two links in the ui (#4452) 2023-11-04 13:41:42 -03:00
oobabooga
aa5d671579
Add temperature_last parameter (#4472) 2023-11-04 13:09:07 -03:00
oobabooga
1ab8700d94 Change frequency/presence penalty ranges 2023-11-03 17:38:19 -07:00
oobabooga
45fcb60e7a Make truncation_length_max apply to max_seq_len/n_ctx 2023-11-03 11:29:31 -07:00
oobabooga
7f9c1cbb30 Change min_p default to 0.0 2023-11-03 08:25:22 -07:00
oobabooga
4537853e2c Change min_p default to 1.0 2023-11-03 08:13:50 -07:00
kalomaze
367e5e6e43
Implement Min P as a sampler option in HF loaders (#4449) 2023-11-02 16:32:51 -03:00
oobabooga
fcb7017b7a Remove a checkbox 2023-11-02 12:24:09 -07:00
Julien Chaumond
fdcaa955e3
transformers: Add a flag to force load from safetensors (#4450) 2023-11-02 16:20:54 -03:00
oobabooga
c0655475ae Add cache_8bit option 2023-11-02 11:23:04 -07:00
oobabooga
42f816312d Merge remote-tracking branch 'refs/remotes/origin/dev' into dev 2023-11-02 11:09:26 -07:00
oobabooga
77abd9b69b Add no_flash_attn option 2023-11-02 11:08:53 -07:00
Julien Chaumond
a56ef2a942
make torch.load a bit safer (#4448) 2023-11-02 14:07:08 -03:00
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
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
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
oobabooga
92b2f57095 Minor metadata bug fix (second attempt) 2023-10-26 18:57:32 -07:00
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
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
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
2d1b3332e4 Ignore warnings on Colab 2023-10-21 21:45:25 -07:00
oobabooga
09f807af83 Use ExLlama_HF for GPTQ models by default 2023-10-21 20:45:38 -07:00
oobabooga
506d05aede Organize command-line arguments 2023-10-21 18:52:59 -07:00
oobabooga
fbac6d21ca Add missing exception 2023-10-20 23:53:24 -07:00
Brian Dashore
3345da2ea4
Add flash-attention 2 for windows (#4235) 2023-10-21 03:46:23 -03:00
Johan
1d5a015ce7
Enable special token support for exllamav2 (#4314) 2023-10-21 01:54:06 -03:00
turboderp
ae8cd449ae
ExLlamav2_HF: Convert logits to FP32 (#4310) 2023-10-18 23:16:05 -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
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
Forkoz
8cce1f1126
Exllamav2 lora support (#4229) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-10-14 16:12:41 -03:00
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
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
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
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
turboderp
8a98646a21
Bump ExLlamaV2 to 0.0.5 (#4186) 2023-10-05 19:12:22 -03:00
oobabooga
7ffb424c7b Add AutoAWQ to README 2023-10-05 09:22:37 -07:00
cal066
cc632c3f33
AutoAWQ: initial support (#3999) 2023-10-05 13:19:18 -03:00
tdrussell
cb26163a20
Fix off-by-one error in exllama_hf caching logic (#4145) 2023-10-05 12:20:56 -03:00
oobabooga
ae4ba3007f
Add grammar to transformers and _HF loaders (#4091) 2023-10-05 10:01:36 -03:00
oobabooga
b6fe6acf88 Add threads_batch parameter 2023-10-01 21:28:00 -07:00
jllllll
41a2de96e5
Bump llama-cpp-python to 0.2.11 2023-10-01 18:08:10 -05:00
oobabooga
f2d82f731a Add recommended NTKv1 alpha values 2023-09-29 13:48:38 -07:00
oobabooga
abe99cddeb Extend evaluation slider bounds 2023-09-29 13:06:26 -07:00
oobabooga
96da2e1c0d Read more metadata (config.json & quantize_config.json) 2023-09-29 06:14:16 -07:00
oobabooga
56b5a4af74 exllamav2 typical_p 2023-09-28 20:10:12 -07:00