Views
No views yet
pip install hsl-embedding, MIT). Trained on a single
RTX 4070. Not a benchmark-superiority claim — the release exists so every "it works" claim is
reproducible.| file | stage | golden numbers |
|---|---|---|
holo651_s1_text_30k.pt | S1 text backbone (EN+KO, 30k steps) | text 1.632 bpb / knowledge-domain 1.689 |
holo651_s2_chat_know_12k.pt | S2 chat + knowledge SFT (2KB context, 12k) | text 1.538 / chat 1.107 / grounding gap 0.120 |
holo651_s3_multimodal_10k.pt | S3 multimodal (video windows, 10k) | text 1.528 / video 4.575 / grounding gap 1.835 |
know_abl_bpb − know_bpb). It grew 0.001 → 1.835 across training: the model measurably READS its
disk memory instead of memorizing (facts live in a disk store, patterns in weights).[256B frame | SEP | 256B mu-law audio | SEP | 24B caption | WSEP]) keep their structure markers
unforced and place real English in the caption slot.1pip install "hsl-embedding>=0.5.0" torch
2git clone https://github.com/Woojiggun/holo-hsl1from holo_generate import load, gen_text # from the repo (Train/)
2m, cfg = load("holo651_s3_multimodal_10k.pt", device="cuda")
3out = gen_text(m, "The universe is ".encode(), n_new=120, temperature=0.7,
4 origin_anchor=cfg["origin_anchor"])
5print(out.decode("utf-8", "replace"))| data | role | license |
|---|---|---|
| FineWeb-Edu (EN) + Korean Wikipedia | text backbone | ODC-By / CC-BY-SA 4.0 |
| Project Gutenberg classics (philosophy etc.) | knowledge store + canon mix | Public domain (US) |
| Korean chat corpora (incl. GPT-derived sets) | S2 chat SFT | mixed, parts NC / model-derived |
| Open-movie video streams (Blender films) | S3 multimodal | CC-BY 3.0 |