philipjohnbasile/glm52-idx-extract

GLM-5.2 — DSA indexer weights

The DSA (sparse-attention) indexer weights extracted from zai-org/GLM-5.2 (743B total / 39B active, MIT), split out as a standalone ~227 MB artifact.

GLM-5.2's attention uses a learned indexer to select a top-k subset of past tokens once the context exceeds index_topk, instead of attending densely over everything. Those indexer tensors are a tiny fraction of the model, but they are needed by any engine that wants to run GLM-5.2's sparse-attention path — and pulling them out of the full checkpoint otherwise means downloading ~108 GB of shards to keep ~227 MB.

Contents

• out-idx-*.safetensors — the extracted indexer tensors
• config.json / generation_config.json — GLM-5.2 config (GlmMoeDsaForCausalLM)
• _meta/ — tokenizer files

Use with iliria

iliria runs GLM-5.2 off SSD by streaming experts from disk. Its converter takes --keep-idx to produce exactly this artifact; this repo saves you that step. Point the engine at a container that includes these tensors and the DSA path activates once context passes index_topk.

Provenance

Derived from zai-org/GLM-5.2 (MIT). Extraction only — no retraining, no quantization of the indexer tensors themselves. The weights are unmodified values lifted from the source checkpoint.