mainsafetensorsfp32Public
happyconst/albedo-qwen3-4b-trainer-333
sha256:12187e5a0143379a6b778a170deea1b6b64eb999a2813e6f480706d8463d7886·Indexed 25d ago
Parameters
4.0B
Total size
15.0 GB
Files
6
Quantization
FP32
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
6 itemsmodel.safetensors
d229640a16fd
15.0 GB
safetensors
tokenizer.json
be75606093db
10.9 MB
chat_template.jinja
87a2728cb8dc
4.0 KB
config.json
8ba006f74fec
726 B
tokenizer_config.json
c5798e4cd1d5
403 B
generation_config.json
c5ad180df43f
188 B