ebolam
f027d8b6e5
Better working valid detection and named model backends for UI
2023-05-17 21:15:31 -04:00
ebolam
c6b17889d0
Updated to latest united
2023-05-12 07:53:27 -04:00
Henk
67df9b917f
Reintroduce 4.29 Transformers
2023-05-12 09:08:07 +02:00
henk717
db32aba74d
Merge pull request #359 from one-some/gptj-fix
...
GPT-J fix
2023-05-12 08:40:00 +02:00
ebolam
aaa9133899
Disk Cache working
...
UI valid marker broken for disk cache
2023-05-11 21:22:33 -04:00
ebolam
a6f0e97ba0
Working(?) breakmodel
2023-05-11 20:40:05 -04:00
ebolam
69d942c00c
Kind of working breakmodel
2023-05-11 20:22:30 -04:00
somebody
3065c1b40e
Ignore missing keys in get_original_key
2023-05-11 17:10:43 -05:00
somebody
c16336f646
Add traceback to debug log on fallback
2023-05-11 17:10:19 -05:00
somebody
6838563ea9
Merge branch 'united' of https://github.com/henk717/KoboldAI into united
2023-05-11 16:32:25 -05:00
ebolam
a9c785d0f0
Fix for Horde
2023-05-11 14:20:14 -04:00
ebolam
e9c845dc2a
Fix for badwordIDs
2023-05-11 14:14:52 -04:00
Henk
20b54eb9ff
Revert 4.29 due to unforseen consequences
2023-05-11 19:06:39 +02:00
ebolam
4605d10c37
Next iteration. Model Loading is broken completely now :)
2023-05-11 12:08:35 -04:00
Henk
edd9c7d782
Warning polish
2023-05-11 15:13:59 +02:00
ebolam
77dd5aa725
Minor update
2023-05-11 09:09:09 -04:00
Henk
e932364a1e
RWKV support
2023-05-11 14:56:12 +02:00
Henk
84e4cb0f4a
Update Transformers
2023-05-11 13:44:53 +02:00
somebody
546ba84723
Fix memory->genre bug in context viewer bar tooltip
...
Crazy change I know
2023-05-10 19:10:23 -05:00
ebolam
71aee4dbd8
First concept of model plugins with a conceptual UI.
...
Completely breaks UI2 model loading.
2023-05-10 16:30:46 -04:00
Henk
702f59b2db
Downgrade ROCM properly
2023-05-09 22:10:01 +02:00
Henk
9fdc2f73a6
ROCM Downgrade for stability
2023-05-09 20:59:10 +02:00
henk717
a649bd8d3c
Merge pull request #357 from one-some/tpu-api-fix
...
Fix TPU API errors
2023-05-09 01:05:20 +02:00
somebody
a9e342ca64
Fix TPU API errors
2023-05-08 17:34:59 -05:00
henk717
0f9129859f
Merge pull request #353 from Zurnaz/llama_tpu_tokenizer_fix
...
fix: tpu tokenizers errors
2023-05-08 19:41:33 +02:00
Bogdan Drema
d53726bed6
fix: tpu tokenizers errors
2023-05-08 18:24:34 +01:00
henk717
cb4af7e56e
Update requirements_mtj.txt
2023-05-08 17:23:49 +02:00
Henk
bb206f598e
Don't load peft when unused
2023-05-06 18:55:26 +02:00
henk717
19092827aa
Merge pull request #351 from one-some/peft
...
Change PEFT directory structure to be inside model
2023-05-06 18:43:57 +02:00
somebody
b7db709c47
PEFT: Change directory structure to be inside model
2023-05-06 11:16:09 -05:00
henk717
472c2c8cbc
Merge pull request #348 from one-some/peft
...
Basic PEFT support
2023-05-06 17:53:51 +02:00
somebody
f02ddab7c7
Merge branch 'united' of https://github.com/henk717/KoboldAI into peft
2023-05-06 10:47:14 -05:00
henk717
04592e5086
Merge pull request #349 from Zurnaz/llama_config
...
feat: llama config and updated mtj requirement
2023-05-06 16:52:22 +02:00
Henk
2730879c61
Better warning until something more robust is in
2023-05-05 21:28:06 +02:00
Henk
d508b4a319
More max_context_length flexibility
2023-05-05 19:50:56 +02:00
Henk
33969b5845
Basic HF code execution support
2023-05-05 17:23:01 +02:00
Henk
b1722081a5
AMD Pytorch 2.0
2023-05-05 15:12:59 +02:00
Henk
33745669dd
Pytorch 2.0
2023-05-05 13:14:58 +02:00
Bogdan Drema
91463a4d97
feat: llama config and updated mtj requirement
2023-05-04 01:47:41 +01:00
somebody
35b56117e6
Basic PEFT support
2023-05-03 18:51:01 -05:00
somebody
a9ef475142
Lock safetensors in version jail
...
Let's have breaking changes when we expect them
2023-05-03 17:57:38 -05:00
Henk
a87d5d6f23
Remove HF's llama workaround
2023-05-03 20:18:40 +02:00
henk717
7f5242db17
Merge pull request #344 from pi6am/fix/llama-tokens
...
Fix/llama tokens
2023-05-03 19:07:47 +02:00
Llama
35d344b951
Remove torch dependency and more generic dim0 workaround
...
Remove torch dependency from hf.py
Make workaround for dimension zero values of token_ids
more generic to handle every token, not just newlines.
2023-05-03 09:48:16 -07:00
henk717
11a9f562a2
Merge pull request #346 from ebolam/united
...
More UI2 paste error fixes
2023-05-03 18:33:58 +02:00
ebolam
0c9537e910
Potential fix for putting pasted text in wrong action
2023-05-03 12:04:05 -04:00
ebolam
fa3611b994
Update to United
...
Update to United
2023-05-03 10:54:17 -04:00
henk717
f958f086f1
Merge pull request #343 from LostRuins/united
...
Added v27 of Embedded Kobold Lite, which will now be usable locally.
2023-05-03 12:30:39 +02:00
Llama
3768848548
Fix tokenization and whitespace issues with llama-derived models
...
Work around the 'soft' prefix space behavior of sentencepiece.
Override encode to restore the deleted HF support for decode_with_prefix_space.
Override decode to skip the soft space and return true decoded tokens.
Allow submitting chat messages with embedded newlines.
Split sentences between punctuation and whitespace, rather than after whitespace.
Also include trailing quotes and brackets after sentence stoppers.
This avoids splitting ." and .) into two tokens, for instance.
Insert whitespace at the beginning of the author's note, since sentences are
split with leading whitespace.
Remove spurious newlines at the end of chat responses.
2023-05-03 01:27:11 -07:00
Concedo
063131a2e6
Added v27 of Embedded Kobold Lite, which will now be usable locally.
...
Avoid modifying this file directly since it will be overwritten in future versions - submit changes to the Lite repo instead.
2023-05-03 14:53:06 +08:00
