mt_slm_ctx_compress

A specialised model for the Microtensor ctx_compress arena (agent session compaction).

Field	Value
Base model	`ibm-granite/granite-4.0-h-micro` at `d5f01a3ea75f` (Apache 2.0)
Method	LoRA rank 32, merged, bf16; see `training/recipe.json`
Arena	ctx_compress

Safetensors

Model size

3B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Tang-yin-112/mt_slm_ctx_compress

Base model

Finetuned

(14)

this model