IFM/LoopedLM-P2-huginn-m-parcae

text-generationxllmUpstream checksumsxllmsafetensorslooped-language-modelpaper-part2huginntext-generation

License: apache-2.0
Size: not mirrored yet
Downloads in the last 30 days: 0 / 30 days

No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.

Cataloged from IFM/LoopedLM-P2-huginn-m-parcae

huginn-m-parcae

Table 3, M, Parcae-Decay of Towards Looped Models Done Right. Part II: Rethinking at Fixed Points.

[!IMPORTANT] Loading this checkpoint requires the xLLM code. The weights are stored in xLLM's native format (BF16 Safetensors with an xLLM config.json and artifact_manifest.json). This is not a Hugging Face transformers checkpoint: AutoModel.from_pretrained cannot load it. Get the code at https://github.com/ifm-ai/xllm-loop and load the directory with xllm.paper_part2.artifacts.load_artifact.

Model details


Model	looped Transformer: 1 prelude, 2 recurrent and 1 coda block; width 3,072, 48 heads (12 KV heads), SwiGLU FFN 8,704
Parameters	819,499,008, including the embedding and output layers
Input injection	Parcae-Decay: diagonal injection of the RMS-normalized prelude output
Recurrent depth in training	PLN-5: capped Poisson-lognormal depths with mean 5, backpropagating the last 10 recurrences
Evaluation	R = 5 with terminal KV; the recurrent state is seeded by example identity (seed 42)
Training	recipe `m_parcae`: 20,480 updates of 512 x 8,192 tokens (85.90B), AdamW, warmup-stable-decay
Weights	BF16 Safetensors: the training checkpoint's FP32 weights rounded to BF16
Tokenizer	`tokenizer/`, the Jais64k tokenizer of training

Download

The xLLM loader checks the directory against artifact_manifest.json: it rejects symbolic links and files the manifest does not list, apart from the .gitattributes file and the .cache/huggingface/ folder that hf download --local-dir adds. Download into a directory as above, not into the Hub cache (~/.cache/huggingface/hub), whose files are symbolic links.

Use

Evaluate with eval_paper_part2.py from the xLLM repository:

data.json and the evaluation inputs come from release/paper-part2/prepare-eval-data.py --output /path/to/eval-data.

xllm.paper_part2.artifacts.load_artifact("huginn-m-parcae") verifies the directory and returns the model config fields and the BF16 state dict on CPU.

artifact_manifest.json records the size and SHA-256 of every file in this repository.

Paper and citation

Towards Looped Models Done Right. Part II: Rethinking at Fixed Points: https://arxiv.org/abs/2610.06833

bibtex

@article{huang2026fixedpoints,  title   = {Towards Looped Models Done Right, Part II: Rethinking at Fixed Points},  author  = {Benhao Huang and Chufan Shi and Junlin Chen and Shicheng Wen and Zhengzhong Liu and Eric Xing and Xuezhe Ma},  journal = {arXiv preprint arXiv:2610.06833},  year    = {2026}}

License

The weights are released under the Apache License 2.0 (LICENSE); NOTICE records the tokenizer's attribution and how the artifact was prepared. The xLLM code is distributed under its own license.