github/home-llm
1
1
Fork 0
mirror of https://github.com/acon96/home-llm.git synced 2026-01-08 21:28:05 -05:00
Code Issues Packages Projects Releases Wiki Activity
638 Commits 9 Branches 39 Tags
b3df3d5346a8b8ce951e30d806fb732b4316e762
Commit Graph

638 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Evian Schlenz
b3df3d5346 correctly type example generation functions 2025-12-31 00:58:22 +01:00
Evian Schlenz
44b296e6df correctly type get_random_state 2025-12-31 00:57:12 +01:00
Evian Schlenz
80669b6522 Rename pile types to not confuse with other type classes 2025-12-30 23:51:27 +01:00
Evian Schlenz
c26ef953c6 Do not use mutable objects as default 2025-12-30 23:47:54 +01:00
Evian Schlenz
b955897c18 make TypedDict types for piles 2025-12-30 18:31:47 +01:00
Alex O'Connell
831ef9bfca clean up training guide 2025-12-23 21:03:07 -05:00
Alex O'Connell
1a8c2e6152 Merge pull request #328 from acon96/feature/dataset-new-apis 
Rewrite Dataset Generation & Training Pipeline
 2025-12-23 21:01:06 -05:00
Alex O'Connell
12ba6d649d clean up readme and add new model 2025-12-21 23:03:44 -05:00
Alex O'Connell
1811a907f7 manually set roles to train on 2025-12-21 22:09:18 -05:00
Alex O'Connell
cf01fd29ae synthesize new data, update training job/configs 2025-12-21 14:14:31 -05:00
Alex O'Connell
4407aefdf5 more synthesizing scenarios + clean up example formatting 2025-12-21 13:31:43 -05:00
copilot-swe-agent[bot]
ecf9586b5a chore: localize new dataset piles 
Co-authored-by: acon96 <35843486+acon96@users.noreply.github.com>
 2025-12-21 04:32:25 +00:00
copilot-swe-agent[bot]
6e667b17cc fix: address dataset generation review feedback 
Co-authored-by: acon96 <35843486+acon96@users.noreply.github.com>
 2025-12-21 04:28:33 +00:00
copilot-swe-agent[bot]
eee2a6ed11 feat: add failure and refusal dataset examples 
Co-authored-by: acon96 <35843486+acon96@users.noreply.github.com>
 2025-12-21 04:26:09 +00:00
copilot-swe-agent[bot]
3846057bb2 Initial plan 2025-12-21 04:13:16 +00:00
Alex O'Connell
ee5d8c4a67 clean up training folder + update TODO 2025-12-20 23:10:00 -05:00
Alex O'Connell
0b776c0a23 add defaults for functiongemma 2025-12-20 22:41:26 -05:00
Alex O'Connell
0e4031ef43 wire up options to support functiongemma properly 2025-12-20 22:25:03 -05:00
Alex O'Connell
29d839eea8 mostly working gemma implementation 2025-12-20 20:29:09 -05:00
Alex O'Connell
672a9de65c extract tool calls from multiple keys 2025-12-20 18:07:27 -05:00
Alex O'Connell
ee2d2e7640 lets try functiongemma instead 2025-12-20 10:24:08 -05:00
Alex O'Connell
04e9bc1ee6 Merge branch 'develop' into feature/dataset-new-apis 2025-12-14 20:43:52 -05:00
Alex O'Connell
c8e0945264 Merge branch 'main' into develop 2025-12-14 20:23:47 -05:00
Alex O'Connell
8e68227971 Merge pull request #326 from acon96/release/v0.4.5 
Release v0.4.5
v0.4.5 		2025-12-14 20:23:27 -05:00
Alex O'Connell
3b159178fb review code 2025-12-14 20:22:17 -05:00
Alex O'Connell
f87800a200 Release v0.4.5 2025-12-14 18:29:43 -05:00
Alex O'Connell
a351c103ff refine error retry loop 2025-12-14 18:24:26 -05:00
Alex O'Connell
f5fe6b36e3 make ai tasks more usable 2025-12-14 12:35:41 -05:00
Alex O'Connell
1f078d0a41 working ai task entities 2025-12-14 10:34:21 -05:00
Alex O'Connell
b547da286f support structured ouput for AI tasks 2025-12-14 02:30:58 -05:00
Alex O'Connell
6010bdf26c rewrite tests from scratch 2025-12-14 01:07:23 -05:00
Alex O'Connell
c8a5b30e5b clean up tool response extraction 2025-12-14 00:32:18 -05:00
Alex O'Connell
b89a0b44b6 support multiple LLM APIs at once 2025-12-13 19:03:58 -05:00
Alex O'Connell
5f48b403d4 Use the ollama python client to better handle compatability 2025-12-13 18:26:04 -05:00
Alex O'Connell
edc09c40e7 add imatrix quants and k8s training job 2025-12-13 18:25:17 -05:00
Alex O'Connell
dac9973cb5 reformat response piles to include confirmation and conclusion 2025-12-07 17:28:38 -05:00
Alex O'Connell
55f254149a start re-working training to use axlotl instead of the custom script 2025-11-30 22:29:08 -05:00
Alex O'Connell
04a5909214 organize training notebook 2025-11-30 16:24:39 -05:00
Alex O'Connell
0833fe6f0b enable flash attention 2025-11-30 16:06:53 -05:00
Alex O'Connell
d352d88fd2 allow setting prompt more generically 2025-11-30 15:59:20 -05:00
Alex O'Connell
9f51dd0e94 more training updates 2025-11-30 15:31:58 -05:00
Alex O'Connell
1a5445e68a tweak notebook 2025-11-30 14:52:29 -05:00
Alex O'Connell
d6c943e020 add gemma 270 to training notebook 2025-11-30 14:13:30 -05:00
Alex O'Connell
25b6ddfd0c fix dev requirements 2025-11-30 14:10:55 -05:00
Alex O'Connell
f12b016b51 gate startup to prevent loading of broken config entries 2025-11-30 14:09:25 -05:00
Alex O'Connell
61140713d7 refactor dataset generation code + add new synthesis script 2025-11-27 22:19:38 -05:00
Alex O'Connell
753a990a98 add new names 2025-11-26 22:08:33 -05:00
Alex O'Connell
14640bd14b finish implementing alternate dataset generation mode 2025-11-26 22:01:08 -05:00
Alex O'Connell
07507ee5f5 more fixes 2025-11-26 19:09:09 -05:00
Alex O'Connell
a16523f9e5 start re-writing dataset generation to use the new HA Assist API 2025-11-26 19:08:46 -05:00