 Tobi Lutke
|
533f0eed37
docs: add finetune CLAUDE.md and update training workflow
|
hai 3 meses |
|
Tobi Lutke
|
7de18ee066
Merge main into finetune
|
hai 3 meses |
|
Tobi Lutke
|
785620467a
refactor: reorder output format to put hyde line first
|
hai 3 meses |
|
Tobi Lütke
|
8cc7d8c138
Add sampled /only: variants (399) for training balance
|
hai 3 meses |
|
Tobi Lütke
|
20aef8a3e9
Change format to /only:lex (slash prefix)
|
hai 3 meses |
|
Tobi Lütke
|
46ff098361
Change only: format to only:lex (no space after colon)
|
hai 3 meses |
|
Tobi Lütke
|
806a0cfc14
Add 'only:' mode support for single-type expansions
|
hai 3 meses |
|
Tobi Lütke
|
32d313ad6b
Add LLM session management for lifecycle safety
|
hai 3 meses |
|
Christopher Jones
|
6d9871d2f5
Fix DisposedError during slow batch embedding (#41)
|
hai 3 meses |
|
Algimantas Krasauskas
|
f6a987a642
Add skills.sh integration for AI agent discovery (#64)
|
hai 3 meses |
|
Tobi Lutke
|
7b98d4d308
Link fine-tuned model to HuggingFace in README
|
hai 3 meses |
|
Tobi Lutke
|
5cf4958bfa
Add HuggingFace model card YAML metadata to finetune README
|
hai 3 meses |
|
Tobias Lütke
|
eb1b77c8cb
Deploy fine-tuned GRPO model as default query expansion (#67)
|
hai 3 meses |
|
Tobi Lutke
|
8572c2fd94
Deploy fine-tuned GRPO model as default for query expansion
|
hai 3 meses |
|
Tobi Lutke
|
5ab78d00a2
Add HF Jobs scripts, temporal query examples, and training results
|
hai 3 meses |
|
Tobi Lutke
|
354744af53
Finetune 2.0: consolidate and simplify the entire training pipeline
|
hai 3 meses |
|
jdvmi00
|
64c6e6c2e3
fix: rename collectionId to collectionName in searchVec for proper filtering (#61)
|
hai 3 meses |
|
Freeman Jiang
|
bfb0eebc3e
fix: use sequential embedding on CPU-only systems to avoid race condition (#54)
|
hai 3 meses |
|
Copilot
|
053252ca24
Add Windows path utilities with cross-platform test coverage (#51)
|
hai 3 meses |
|
sh54
|
ba7391832d
Add org-mode title extraction support (#50)
|
hai 3 meses |
|
sh54
|
65c0f89560
Enable SQLite extension loading in devshell (#48)
|
hai 3 meses |
|
Tobi Lutke
|
9b3a209a97
Fix GRPO training: apply chat template to prompts
|
hai 3 meses |
|
Tobi Lutke
|
3ea85eff50
Make TUI model list dynamic from HuggingFace Hub
|
hai 3 meses |
|
Tobi Lutke
|
891f3262cf
Fix GRPO reward function to handle think blocks and end tokens
|
hai 4 meses |
|
Tobi Lutke
|
66bb8ed963
Remove beads reference from CLAUDE.md
|
hai 4 meses |
|
Tobi Lutke
|
2267986302
Remove beads issue tracking
|
hai 4 meses |
|
Tobi Lutke
|
8a1c4cdab0
Add 1.7B and 4B GRPO training and GGUF conversion scripts
|
hai 4 meses |
|
Tobi Lutke
|
b9b1b39a76
Update README with separate model repos
|
hai 4 meses |
|
Tobi Lutke
|
312c281109
Update README for unified model repository structure
|
hai 4 meses |
|
Tobi Lutke
|
2648512b7c
Fix TUI to load GRPO models with SFT base first
|
hai 4 meses |
