v15bestsafetensorsbf16Public
mattts/teutonic-q3-4b-5fbywvfq-v15best
sha256:0e9f527e5f487d62bf76052650e00eeda87e32dd14a1e91a6c2c96632c9cef88·Indexed 1h ago
Parameters
4.0B
Total size
7.5 GB
Files
5
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
5 itemsmodel.safetensors
1fab6a769d56
7.5 GB
safetensors
tokenizer.json
be75606093db
10.9 MB
config.json
80ce7861835e
1.6 KB
tokenizer_config.json
2e3bd3cb5055
693 B
generation_config.json
b77461537176
213 B