Hippius
Get the CLI
5fcms2sh-HeavyBall-PSGDProsafetensorsbf16Public

teutonic-lucas/teutonic-q3-4b-5fcms2sh-heavyball-psgdpro

sha256:fe57b68861d5e6605b42d69cf5e5e71e0394f2447a3e2e3a7b0d3f6a82f8da09·Indexed 1d ago

Parameters

4.4B

Total size

8.2 GB

Files

7

Quantization

BF16

No README on this version

Push a README.md with the model files to see it rendered here.

Model architecture

config.json
Architecture
Qwen3ForCausalLM
Model type
qwen3
Hidden size
2,560
Layers
36
Attention heads
32 (8 kv)
FFN size
9,728
Vocab size
151,936
Context window
40K

Files

7 items

  • model.safetensors

    4c8b95acaf76

    8.2 GB

    safetensors

  • tokenizer.json

    be75606093db

    10.9 MB

  • config.json

    9430f79acea2

    1.6 KB

  • tokenizer_config.json

    5f007d04324a

    696 B

  • q3_train_state.json

    f30d69d2d0eb

    595 B

  • teutonic_model_store.json

    c60072b60da5

    527 B

  • generation_config.json

    0af44c629f5c

    213 B