Hippius
v5safetensorsbf16Public

teutonic-5h6u2uab/teutonic-q3-4b-5h6u2uab-v5

sha256:9a6c9607e092ce0c6069b0a1d75d8dfa549f0ce60228ca22ef4d66c05f6202f3·Indexed 3d ago

Parameters

4.0B

Total size

7.5 GB

Files

6

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

6 items
  • model.safetensors

    4b6545441d8a

    7.5 GB

    safetensors

  • tokenizer.json

    be75606093db

    10.9 MB

  • chat_template.jinja

    87a2728cb8dc

    4.0 KB

  • config.json

    80ce7861835e

    1.6 KB

  • tokenizer_config.json

    5f007d04324a

    696 B

  • generation_config.json

    8ab3d28fc0d8

    138 B