EINSOF-II GLM-4 9B Stiefel (GGUF Quantizations)

  • Base Model: THUDM/glm-4-9b-chat (fast tokenizer aligned with zai-org/glm-4-9b-chat-hf, 151,552 vocab)
  • Adapter: Polydim-Einsof/einsof2-glm4-9b-stiefel-adapter
  • Quantizations: Q4_K_M (5.83 GB) and Q8_0 (9.31 GB)
  • Manifold: Stiefel S^(D-1) via polar retraction order 4
  • Framework: llama.cpp + POLYDIM PMTP
Downloads last month
101
GGUF
Model size
9B params
Architecture
chatglm
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

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

Model tree for Polydim-Einsof/einsof2-glm4-9b-stiefel-gguf

Quantized
(13)
this model