state-spaces/mamba-130m-hf

state-spaces/mamba-130m-hf is listed on Hugging Face as a text-generation model. This page records the public repository snapshot 1e76775f628fbf1350fbe4dbb3d971ba64af25a1; verify the listed revision, licence, and runtime support before using it.

Updated

Computraq is preparing for launch. These guides explain readiness and the proposed framework; they do not establish a live service, integration or partnership.

Identity and access

The publisher record identifies this repository as state-spaces/mamba-130m-hf. Its current public snapshot is 1e76775f628fbf1350fbe4dbb3d971ba64af25a1. Access is public repository; review the applicable licence and publisher terms; the recorded licence label is not stated in the public record. A public repository or gated download does not establish permission for every use.

Configuration facts

The pinned configuration reports model type mamba and architecture MambaForCausalLM. The model hub tags it for text-generation; these labels describe repository metadata and do not establish benchmark performance.

  • hidden_size: 768
  • intermediate_size: 1536
  • num_hidden_layers: 24
  • torch_dtype: float32
  • vocab_size: 50280

Model-specific qualification

The configuration or tags identify recurrent, hybrid, or state-space components. Confirm state handling, sequence limits, batching behavior, and runtime implementation; transformer-only assumptions may not apply.

Weight-memory planning

This guide does not retain an independently verified logical parameter count, so it omits a numeric weight-memory estimate. If a count is verified for this exact repository revision, use parameter count × bytes per parameter for a weights-only floor; then account separately for KV cache, context, activations, runtime, and concurrency.

Revision and reproducibility

The metadata and configuration are pinned to revision 1e76775f628fbf1350fbe4dbb3d971ba64af25a1. Pin this commit when reproducing an evaluation. Repository branches can change, and this source check does not validate the model weights themselves.

Published record

  • Task: text-generation
  • Model type: mamba
  • Architecture: MambaForCausalLM
  • Licence label: not stated in the public record
  • Access: public repository; review the applicable licence and publisher terms
  • Revision: 1e76775f628fbf1350fbe4dbb3d971ba64af25a1

Sources and verification