Instructions to use LEAP-LAB-KUS/jevkt-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use LEAP-LAB-KUS/jevkt-checkpoints with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
README: add pykt/classical, final layout
Browse files
README.md
CHANGED
|
@@ -32,8 +32,15 @@ e15/F1-cs/<ds>-s<seed>N<N>/ckpt-*/ # E15 F1-cs: one block per cold-start cell
|
|
| 32 |
e16/<arm>/train_log.jsonl
|
| 33 |
e16/<arm>/<ckpt-STEP>/... # trained by the e16 driver (jevkt.e16_rl); also holds E17/E18/E19/E20/LODO arms
|
| 34 |
meta_only/pod{A,C}/e1x/<arm>/... # configs + train logs ONLY (weights still on the stopped pods' volumes)
|
|
|
|
|
|
|
|
|
|
| 35 |
```
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
Each `ckpt-STEP/` contains everything needed to reuse the block:
|
| 38 |
- `adapter_vllm/` — vLLM LoRA export (`adapter_config.json`, `adapter_model.safetensors`, `decision_head.json`
|
| 39 |
with head bias / verbalizer ids). Same format as JEV-9B's own `adapter_vllm`.
|
|
@@ -65,6 +72,7 @@ Each `train_log.jsonl` first line records `data`, `data_manifest.train_sha256`,
|
|
| 65 |
| e16/S1-SS-{hlr,mix}-n16k-syn | data/e18/SS-… | E18 semi-synthetic: real non-KT interaction structure (Duolingo HLR / KuaiRec / Lichess), simulated outcomes |
|
| 66 |
| e16/S1-E19-{a1,a2,b}-n<N>[-variant]-syn | data/e19/E19-… | E19 LLM-student simulator (a1 GSM8K+MATH, a2 XES3G5M/KCQRL text, b E17 bank) |
|
| 67 |
| e16/S1-MIX-E18E19-n16k-syn, S1-MIX3-n16k-syn | data/e20/MIX… | mixes of E18 / E19 / SS data |
|
|
|
|
| 68 |
| Pod A/C arms (meta_only) | data/e15, e16, e17, e18, e19 | see `meta_only/` train logs |
|
| 69 |
|
| 70 |
All S1 arms use objective s-log + 5 % replay of `data/e16/replay` (JEV distill corpus subset) unless the train log says otherwise.
|
|
|
|
| 32 |
e16/<arm>/train_log.jsonl
|
| 33 |
e16/<arm>/<ckpt-STEP>/... # trained by the e16 driver (jevkt.e16_rl); also holds E17/E18/E19/E20/LODO arms
|
| 34 |
meta_only/pod{A,C}/e1x/<arm>/... # configs + train logs ONLY (weights still on the stopped pods' volumes)
|
| 35 |
+
pykt/<ds>/pykt-<model>-s<seed>/ # pyKT DLKT baselines (local machine copy): qid_model.ckpt + train_info.json;
|
| 36 |
+
pykt/<ds>/coldstart/... # full-data seeds + cold-start cells (jevkt.pykt_runner; CLAUDE.md 2026-10-03 … 10-07)
|
| 37 |
+
classical/<model>__<ds>__s<seed>.pt # leap-kt-toolkit baselines (src/jevkt/classical)
|
| 38 |
```
|
| 39 |
|
| 40 |
+
pyKT note: this is the LOCAL machine's `models/pykt` (19.8 GB). Pod B's `models/pykt` (8.5 GB: Pod-B-trained Stage-3
|
| 41 |
+
seeds, cold-start cells, tuned DLKT) and Pod A's pyKT checkpoints are not included; predictions for all of them
|
| 42 |
+
are in the JevKT repo `results/preds/`.
|
| 43 |
+
|
| 44 |
Each `ckpt-STEP/` contains everything needed to reuse the block:
|
| 45 |
- `adapter_vllm/` — vLLM LoRA export (`adapter_config.json`, `adapter_model.safetensors`, `decision_head.json`
|
| 46 |
with head bias / verbalizer ids). Same format as JEV-9B's own `adapter_vllm`.
|
|
|
|
| 72 |
| e16/S1-SS-{hlr,mix}-n16k-syn | data/e18/SS-… | E18 semi-synthetic: real non-KT interaction structure (Duolingo HLR / KuaiRec / Lichess), simulated outcomes |
|
| 73 |
| e16/S1-E19-{a1,a2,b}-n<N>[-variant]-syn | data/e19/E19-… | E19 LLM-student simulator (a1 GSM8K+MATH, a2 XES3G5M/KCQRL text, b E17 bank) |
|
| 74 |
| e16/S1-MIX-E18E19-n16k-syn, S1-MIX3-n16k-syn | data/e20/MIX… | mixes of E18 / E19 / SS data |
|
| 75 |
+
| pykt/, classical/ | public KT datasets (data/<ds>, not in jevkt-data) | DLKT baselines |
|
| 76 |
| Pod A/C arms (meta_only) | data/e15, e16, e17, e18, e19 | see `meta_only/` train logs |
|
| 77 |
|
| 78 |
All S1 arms use objective s-log + 5 % replay of `data/e16/replay` (JEV distill corpus subset) unless the train log says otherwise.
|