---
license: apache-2.0
library_name: pytorch
tags: [dynamic-chunking, tokenization, hnet, byte-level, beetle-hnet]
---

# ali_ali_s2

A byte-level H-Net run from [beetle-hnet](https://github.com/suchirsalhan/beetle-hnet)
(`architecture=ali`, `objective=ratio`
`schedule=None`, `dechunk=ema`, seed 2,
6000 steps x 32 x 1024 bytes, langs ['en', 'tr', 'fi']).

## Layout (Beetle-style)

- **`step-N` branches**, one per kept checkpoint on a phase-aware log2 schedule (0, 1, 2, 4, 6,
  8, 16, ..., 2^k from every objective-phase start, plus the final step). Each holds
  `model.safetensors`, `config.json`, `training_config.yaml` and the full resumable trainer
  state `training_state/checkpoint.pt` (for inventory arms this includes the inventory).
- **`main`**: the latest step's weights and config, plus `log.jsonl`, `final.json` and the
  FLORES+ boundary probes `probe/` once the run has finished.

```python
from huggingface_hub import hf_hub_download
import torch
p = hf_hub_download("AdaptiveChunking/ali_ali_s2", "training_state/checkpoint.pt", revision="step-1024")
state = torch.load(p, map_location="cpu", weights_only=False)
```

`model.safetensors` stores each tied tensor once; `config.json["tied_weights"]` maps the
dropped names to the stored ones.