Commit Graph

78 Commits

Author SHA1 Message Date
ff82173f2a Removed auto enable for QwQ 2025-04-13 09:56:01 +02:00
7e254b7f7e Fixed qwq token limit 2025-04-11 18:03:17 +02:00
Niels Geens
5b8f04be81 fix copy bug 2025-04-09 16:43:27 +02:00
Niels Geens
8fb30c8ed0 Optimized hot-loop for logits processor 2025-04-09 11:59:26 +02:00
2e08be4b75 Validator works for start 2025-04-07 14:31:56 +00:00
Niels Geens
50539f6d03 Integrate logits processor with qwq (untested) 2025-04-07 13:35:20 +02:00
Niels Geens
faf78b7948 Lock vllm version to avoid bug 2025-04-07 12:17:56 +02:00
0e2cca2e4f Fixed QwQ tokenizer 2025-04-04 08:54:06 +00:00
Niels Geens
e573b9ebe7 Removed flash-attn as dependency because it's hard to install properly 2025-04-02 14:42:35 +02:00
130afbdd92 Updates after testing 2025-04-01 11:49:21 +00:00
Niels Geens
6f3d414d17 Converted QwQ notebooks to .py files 2025-04-01 10:42:54 +02:00
Niels Geens
d5a5fd1071 Simplified bootstrapping 2025-03-14 15:53:27 +01:00
Niels Geens
2e66020f8e Replaced deepseek with qwq 2025-03-14 11:22:30 +01:00
Niels Geens
3ea3239a9b wip deepseek train 2025-03-03 16:57:04 +01:00
b64f8d7d33 wip deepseek r1 2025-03-02 22:01:24 +01:00
b7e95d7398 Added restart script and fixed dockerfile and run to match docs 2025-03-01 13:29:17 +01:00
3ab726f961 Properly close mistral response 2025-01-09 20:01:32 +01:00
Niels Geens
e730eba58c Fix error in "fixed" timestamps 2025-01-06 14:15:32 +01:00
Niels Geens
6669b7a682 Fixed timestamp timezone for entry id's 2025-01-02 16:52:43 +01:00
e0bc7a7159 Update to itb_screenshot and friends 2024-12-27 17:07:19 +01:00
da8583ab28 ITP WiP 2024-12-04 17:19:46 +01:00
e71bd7e9eb Allow stopping of inference 2024-11-30 12:44:13 +01:00
a9e70f0a22 Added iteration loading 2024-11-24 20:35:28 +01:00
b6c1a95abd Added memory editing functionality 2024-11-24 18:00:27 +01:00
2c820f6ead WIP memory editor 2024-11-23 21:36:50 +01:00
dbc0068a82 Server side implementation for interactive entry edits 2024-11-23 15:34:33 +01:00
bb74fd3621 Added output length on truncated scripts 2024-11-23 09:36:34 +01:00
Niels Geens
69f4f8a6fc Fixed auto approver 2024-11-22 17:11:06 +01:00
Niels Geens
8766a945c0 Enable multiple llms 2024-11-22 15:05:54 +01:00
Niels Geens
bbb88f39e8 Added another set of iterations 2024-11-20 16:06:33 +01:00
Niels Geens
03cf69d272 Added iteration_logger 2024-11-19 20:24:21 +01:00
ef94d0d1a0 Added mistral llm engine 2024-11-17 16:53:44 +01:00
506bc91639 Added api token for local llm 2024-11-16 22:09:04 +01:00
410e2b56f9 Fix timeout printing 2024-11-16 21:57:15 +01:00
c44d0ffbdf Fixes for runpod test 2024-11-16 21:51:18 +01:00
Niels Geens
9dfd5ddc39 Add auto_approver 2024-11-15 17:09:07 +01:00
Niels Geens
4ce421bbce Fixed context usage calculation 2024-11-14 18:23:33 +01:00
Niels Geens
ede0a642d3 Moved context generation to base agent instead of system_metrics 2024-11-14 14:51:54 +01:00
Niels Geens
325870a81a Fixed stdin buffer length in context 2024-11-14 13:36:20 +01:00
Niels Geens
834ce12e8f Added timeout and limit to script entries 2024-11-13 17:48:39 +01:00
Niels Geens
d0eed2666e Merge branch 'master' of https://git.nielsgeens.be/llm/SIA 2024-11-13 11:55:06 +01:00
Niels Geens
555fc7f764 Added check for superfluous arguments to response 2024-11-13 11:52:04 +01:00
Niels Geens
aa37182614 Added temperature argument 2024-11-13 11:51:02 +01:00
229f4f4ac7 Added openai llm engine 2024-11-13 11:46:29 +01:00
50f05b6213 Better response parsing 2024-11-13 11:44:58 +01:00
59f482bc0e Fix superfluous CDATA tokens 2024-11-11 14:23:08 +01:00
3a1d8a449c Fixed stdout 2024-11-11 13:51:27 +01:00
0e1a0407d0 Properly renamed single_shot_entry to single_entry 2024-11-11 13:26:44 +01:00
babc1c44b9 Renamed hf-api-token to api-token 2024-11-11 13:25:39 +01:00
Niels Geens
970414e56d Basic web loop works 2024-11-07 15:10:17 +01:00