ChiTako/unofficial-photon-repro-ja-250m-v2

Unofficial. This is an independent, hobby reimplementation of the PHOTON architecture described in arXiv:2512.20687, trained from scratch by a private individual. It is not released by, affiliated with, or endorsed by the paper's authors or any organisation, and no weights, data or code from any official PHOTON release were used. Treat it as a research artefact, not a product.

### Correction to the perplexity numbers (2026-07-28) Earlier revisions of this card reported Wikipedia perplexity measured by streaming wikimedia/wikipedia from record 0 — which is where prepare_data.py also starts building the training shards. Those numbers were measured on training data and are withdrawn. The table below uses articles past the ones training consumed (--ppl-skip-ja 700000 --ppl-skip-en 400000). Held-out Wikipedia, 409,600 tokens each, identical protocol for all runs: | model | data | ja-wiki | en-wiki | |---|---|---|---| | unofficial-photon-repro-ja-250m-v1 | Wikipedia only, 200M tok | 60.32 | 65.91 | | unofficial-photon-repro-ja-250m-v3 | Wikipedia only, 200M tok | 57.12 | 62.17 | | unofficial-photon-repro-ja-250m-v4 | Wikipedia only, 200M tok | 52.11 | 59.52 | | unofficial-photon-repro-ja-250m-v3-900m | full mixture, 900M tok | 67.60 | 69.37 | Do not rank these models by the Wikipedia column. v1-v4 trained on Wikipedia; v3-900m did not (5% of its mixture). On 青空文庫, which none of them trained on, v3-900m scores 237.10 against v4's 365.49 — the ranking reverses. See docs/findings.md sections 1b-1d in the repository.

PHOTON-JP small v2 (247M-A101M)

A Japanese language model on the PHOTON hierarchical autoregressive architecture (arXiv:2512.20687), with every transformer stack replaced by a fine-grained Mixture-of-Experts using auxiliary-loss-free load balancing.

Tokens are folded into multi-resolution latent units instead of being scanned one at a time:

tokens   t1 t2 t3 t4 | t5 t6 t7 t8 | ...      <- level-1 decoder, every token
           \  \  /  /
level-1      u1      |     u2      | ...      <- once per 4 tokens
              \_____/____________/
level-2            m1                          <- once per 16 tokens

A level-l encoder runs once per C<=l tokens, so its cost is amortised. That is the whole point: capacity sits at the top of the hierarchy where it is cheapest per token.

Size

Training

Evaluation

Data

Japanese-majority mixture: fineweb-2-edu-japanese, FineWeb-2 ja, Japanese Wikipedia, Zyda-2, FinePDFs-Edu, FineWeb-Edu and SwallowMath-v2, tokenised with llm-jp-tokenizer v3. The last 15% of training switches to a high-quality math / code / Japanese-edu blend (Nemotron-3, OLMo 3 and llm-jp-4 all do this).

Honest limitations

This model is under-trained by design of the budget, not by accident. At 0.79 tokens per parameter it is far below the ~20 that Chinchilla-optimal training implies, and further still below what an inference-efficient model would normally get. It produces fluent Japanese surface form -- correct particles, natural kana/kanji mixing, sentence-final forms -- while being largely incoherent semantically. Treat it as a demonstration that the architecture trains, not as a usable assistant.

Samples

Generation protocols

• —HierGen keeps encoder state at every level. Exact: it reproduces the training-time distribution (verified to 2e-4 in the test suite).
• —RecGen keeps only the top-level KV cache and feeds the decoder cascade its own reconstructions, cutting cache by 4.8x. Exact when recursive consistency holds, which is what L_token + alpha * L_rec optimises for.

Usage

from photon_jp.model.config import PhotonConfig
from photon_jp.model.photon import PhotonForCausalLM
from photon_jp.model.loading import load_state_dict_compat
from photon_jp.infer.generate import PhotonGenerator, GenerationConfig
from safetensors.torch import load_file

cfg = PhotonConfig.load("model_config.json")
model = PhotonForCausalLM(cfg)
load_state_dict_compat(model, load_file("model.safetensors"))

gen = PhotonGenerator(model.cuda().eval(), "cuda")
out = gen.generate(input_ids, GenerationConfig(mode="recgen", max_new_tokens=256))

Accounting

==============================================================================
PHOTON-JP parameter report
==============================================================================
vocab=99,584  D0=512  L=2  C_<=L=16  ctx=1024

stack                    total        active   amort     amort.act
------------------------------------------------------------------------------
L1.encoder              39.6M        12.1M       4         3.0M
L1.decoder              15.5M         7.8M       1         7.8M
L2.encoder             127.3M        21.2M      16         1.3M
L2.decoder               7.0M         4.5M       4         1.1M
------------------------------------------------------------------------------
embedding               51.0M
lm_head                  0.0M
chunk/convert            4.2M
mtp                      2.7M
==============================================================================
TOTAL          : 0.247 B   (0.196 B non-emb)
ACTIVE / token : 0.101 B   (0.050 B non-emb)
AMORTISED      : 0.068 B  (FLOP-equivalent dense size)
sparsity       : 2.46x

fwd FLOPs/token @ ctx=1024: 0.13 GFLOP (matmul 0.13, attn 0.001)
KV cache mode    : MLA latent (weight-absorbed)
KV cache  HierGen: 0.945 KiB/token   (other mode: 2.312)
KV cache  RecGen : 0.195 KiB/token   (other mode: 1.562)
  -> 0.9 MiB for a full 1024-token context (HierGen, per sequence)
==============================================================================

Citation

@article{ichikawa2025photon,
  title  = {PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and
            Memory-Efficient Language Generation},
  author = {Ichikawa, Yuma and Takagi, Naoya and Nakagawa, Takumi and
            Kanazawa, Yuzi and Sakai, Akira},
  journal= {arXiv preprint arXiv:2512.20687},
  year   = {2025}
}