unsloth/GLM-4.7-Flash

unsloth/GLM-4.7-Flash is listed on Hugging Face as a text-generation model. This page records the public repository snapshot 070169aa5fd9cf953f8a4e9e30b8dad73ec02604; 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 unsloth/GLM-4.7-Flash. Its current public snapshot is 070169aa5fd9cf953f8a4e9e30b8dad73ec02604. Access is public repository; review the applicable licence and publisher terms; the recorded licence label is mit. A public repository or gated download does not establish permission for every use.

Configuration facts

The pinned configuration reports model type glm4_moe_lite and architecture Glm4MoeLiteForCausalLM. The model hub tags it for text-generation; these labels describe repository metadata and do not establish benchmark performance.

  • torch_dtype: bfloat16
  • head_dim: 64
  • hidden_size: 2048
  • intermediate_size: 10240
  • max_position_embeddings: 202752
  • n_routed_experts: 64
  • num_attention_heads: 20
  • num_experts_per_tok: 4
  • num_hidden_layers: 47
  • num_key_value_heads: 20
  • rms_norm_eps: 1e-05
  • rope_parameters.rope_theta: 1000000
  • vocab_size: 154880

Model-specific qualification

This configuration or publisher metadata marks the model as a mixture of experts. Confirm whether the serving runtime supports its routing layers, and distinguish total parameters from parameters active per token; no active count is inferred here unless the publisher explicitly states one.

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 070169aa5fd9cf953f8a4e9e30b8dad73ec02604. 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: glm4_moe_lite
  • Architecture: Glm4MoeLiteForCausalLM
  • Licence label: mit
  • Access: public repository; review the applicable licence and publisher terms
  • Revision: 070169aa5fd9cf953f8a4e9e30b8dad73ec02604

Sources and verification