Hippius
Get the CLI
trainer01safetensorsbf16Public

star/albedo-qwen3-4b-trainer01

sha256:1389dc66a9007d8e328fa3d3d4f1a46d6314dc1acdd0db04800e03ab30cf493a·Indexed Jun 6, 2026

Parameters

4.0B

Total size

7.5 GB

Files

8

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

8 items

  • model.safetensors

    00e8da332110

    7.5 GB

    safetensors

  • tokenizer.json

    aeb13307a71a

    10.9 MB

  • vocab.json

    ca10d7e9fb3e

    2.6 MB

  • merges.txt

    8831e4f1a044

    1.6 MB

  • tokenizer_config.json

    d5d09f07b48c

    9.5 KB

  • chat_template.jinja

    87a2728cb8dc

    4.0 KB

  • config.json

    8ba006f74fec

    726 B

  • generation_config.json

    2325da0f15bb

    239 B