v1safetensorsbf16Public
teutonic-q3-4b-default/5gxmpyzq-teutonic-q3-4b
sha256:4118ef351cb10712513bc235a4e8e00f1468d3493ab5fb7ae170c1b0dbb9b899·Indexed 2d ago
Parameters
903.7M
Total size
1.7 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
- Gemma3ForCausalLM
- Model type
- gemma3_text
- Hidden size
- 1,152
- Layers
- 24
- Attention heads
- 4 (1 kv)
- FFN size
- 6,400
- Vocab size
- 262,144
- Context window
- 32K
Files
6 itemsmodel.safetensors
3efc44d91fd9
1.7 GB
safetensors
tokenizer.json
77d6eba10db5
31.8 MB
tokenizer_config.json
4a2188480a3c
1.1 MB
config.json
966ccdca5e77
1.7 KB
special_tokens_map.json
e3ad09a4a83c
597 B
generation_config.json
8775c0b9fd32
134 B