github/home-llm
1
1
Fork 0
mirror of https://github.com/acon96/home-llm.git synced 2026-01-09 13:48:05 -05:00
Code Issues Packages Projects Releases Wiki Activity
166 Commits 9 Branches 39 Tags
7b01251f5d568eee32057de40fcd15484cc42f81
Commit Graph

166 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alex O'Connell
7b01251f5d fixes for training zephyr base 2024-02-04 11:40:03 -05:00
Alex O'Connell
cecf9bc53e move to jsonl, finish sharegpt dataset format, and add flag to add chatml prompt template 2024-01-31 23:00:32 -05:00
Alex O'Connell
d901eaffdf start working on other base models 2024-01-30 22:12:46 -05:00
Alex O'Connell
371ac513b2 typo in pile 2024-01-30 22:12:12 -05:00
Alex O'Connell
d023cfee28 add another test prompt 2024-01-30 22:12:12 -05:00
Alex O'Connell
8b1cc5a587 add random sampler with largest first to optimize pytorch memory usage 2024-01-30 22:12:12 -05:00
Alex O'Connell
2bdfb79f89 clear cuda cache after evaluation to clear out the irregularly sized blocks from the allocation cache 2024-01-30 22:12:12 -05:00
Alex O'Connell
da7b7b4d95 try to checkpoint saved lora modules 2024-01-30 22:12:12 -05:00
Alex O'Connell
18f9b7cdc0 Merge branch 'main' into develop 2024-01-28 19:21:24 -05:00
Alex O'Connell
92617f8484 Merge pull request #44 from acon96/release/v0.2.5 
Release v0.2.5
v0.2.5 		2024-01-28 19:20:52 -05:00
Alex O'Connell
235df081b8 fix release notes 2024-01-28 19:19:35 -05:00
Alex O'Connell
7f94c6d4bb update todo 2024-01-28 18:50:41 -05:00
Alex O'Connell
24f8ba10c3 update manually installed llama-cpp-python 2024-01-28 11:46:35 -05:00
Alex O'Connell
95a90618f6 fix link 2024-01-28 10:28:34 -05:00
Alex O'Connell
038d869ded random readme fixes + format notes 2024-01-28 10:17:50 -05:00
Alex O'Connell
c2d4d95212 fix gguf download 2024-01-27 16:33:48 -05:00
Alex O'Connell
c6cc99e59f Release v0.2.5 2024-01-27 15:44:20 -05:00
Alex O'Connell
8e4c602685 Merge branch 'feature/proper-functioncalling-args' into develop 2024-01-27 15:22:07 -05:00
Alex O'Connell
d5c8f7221d gitignore 2024-01-27 15:20:03 -05:00
Alex O'Connell
3134c4f954 update info about model in readme 2024-01-27 15:19:10 -05:00
Alex O'Connell
30361809ae count tokens faster 2024-01-27 14:54:46 -05:00
Alex O'Connell
9723a98139 more dataset + model experiments using the evaluation script 2024-01-27 14:54:14 -05:00
Alex O'Connell
be99ac2d12 fix missing setup config for text-generation-webui + pass arguments to service calls 2024-01-27 14:50:57 -05:00
Alex O'Connell
946623713f add "extra exposed attributes" to dataset as function call arguments + fix pile template inconsistencies 2024-01-26 22:36:34 -05:00
Alex O'Connell
5860028990 fix chatml prompt for multi-turn conversations 2024-01-26 21:18:12 -05:00
Fixt
107f8cd740 fix: Max tokens setting for Ollama API (#40) 2024-01-26 22:59:54 +00:00
Alex O'Connell
e6fae06133 wizardlm merge + fix eval 2024-01-25 20:46:59 -05:00
Alex O'Connell
57634519ca move to eval script instead of during training 2024-01-25 20:46:59 -05:00
Alex O'Connell
c3cb5c5354 try writing an accuracy metric 2024-01-25 20:46:59 -05:00
Alex O'Connell
9cdedb021a expose arguments to function calls via HA integration 2024-01-25 20:46:59 -05:00
Alex O'Connell
69e7302704 Merge branch 'develop' v0.2.4 2024-01-25 20:28:21 -05:00
Alex O'Connell
552e084b47 Update readme + version number 2024-01-25 20:28:10 -05:00
Alex O'Connell
a9b042de1d Fix api key on load model for text-generation-webui 2024-01-25 20:23:57 -05:00
Fixt
a43c6ed27e feat: Ollama API Support (#34) 2024-01-23 02:10:50 +00:00
Anto79-ops
3010aa6719 Update README.md to LocalAI and Home-LLM model install (#31) 2024-01-23 02:07:58 +00:00
Alex O'Connell
b7e850618e readme typo 2024-01-21 22:03:44 -05:00
Alex O'Connell
2be8e857f1 Merge branch 'main' into develop 2024-01-21 21:50:29 -05:00
Alex O'Connell
221cceb762 Merge branch 'release/v0.2.3' v0.2.3 2024-01-21 21:46:42 -05:00
Alex O'Connell
4f96c01367 update changelog 2024-01-21 21:46:35 -05:00
Alex O'Connell
83dd9744ae Merge branch 'feature/chat-completions' into develop 2024-01-21 21:40:29 -05:00
Alex O'Connell
1594844962 fix auth, add llama-cpp-python server backend, better in-app docs 2024-01-21 21:38:23 -05:00
Alex O'Connell
7c30bb57cf split up even more + add llama-cpp-python server 2024-01-21 16:25:50 -05:00
Alex O'Connell
cc3dd4884a rewrite using class inheritance to cut down on repeated code 2024-01-21 14:38:06 -05:00
Alex O'Connell
18dfd70c86 Bump text-generation-webui snapshot date 2024-01-21 13:07:47 -05:00
Alex O'Connell
9290d9b388 properly pass chat mode + docs 2024-01-21 13:07:19 -05:00
Alex O'Connell
27963d06f9 completions endpoint works but it doesn't apply prompt formatting 2024-01-19 00:00:29 -05:00
Alex O'Connell
cae4aa3908 format TODO.md 2024-01-18 20:16:29 -05:00
Alex O'Connell
96d095f8c5 start working on chat completions API 2024-01-18 20:14:56 -05:00
Alex O'Connell
bf792d443c Merge branch 'master' into develop 2024-01-18 20:14:52 -05:00
Alex O'Connell
5a61728a38 update changelog v0.2.2 2024-01-17 18:29:23 -05:00