Hippius
topsafetensorsbf16Public

superstar/albedo-qwen3-4b-top

sha256:c702e6dbc59b2f44e9422a57e6dfcc3a1df11da88857fc10ccef80b4dfc9e904·Indexed Jun 8, 2026

Parameters

4.0B

Total size

7.5 GB

Files

11

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
Dtype
bfloat16

Files

11 items
  • model-00001-of-00002.safetensors

    9b4c10d3298f

    4.6 GB

    safetensors

  • model-00002-of-00002.safetensors

    0e16b1226f7e

    2.8 GB

    safetensors

  • tokenizer.json

    7c58a2ddb530

    10.9 MB

  • vocab.json

    ca10d7e9fb3e

    2.6 MB

  • merges.txt

    8831e4f1a044

    1.6 MB

  • model.safetensors.index.json

    c842ea735f04

    32.0 KB

  • tokenizer_config.json

    e50f6e0b1e23

    9.3 KB

  • config.json

    829b9758aedb

    809 B

  • added_tokens.json

    c0284b582e14

    707 B

  • generation_config.json

    3b101cd89b14

    188 B

  • special_tokens_map.json

    b15f1f34e32d

    175 B