star/albedo-qwen3.6-35b-talent11
Parameters
35.1B
Total size
65.4 GB
Files
22
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
- Qwen3_5MoeForConditionalGeneration
- Model type
- qwen3_5_moe
- Hidden size
- 2,048
- Layers
- 40
- Attention heads
- 16 (2 kv)
- Vocab size
- 248,320
- Context window
- 256K
- Dtype
- bfloat16
Files
22 itemsmodel-00002-of-00014.safetensors
1314e02ceb40
5.2 GB
safetensors
model-00001-of-00014.safetensors
2b5f991fad25
5.1 GB
safetensors
model-00003-of-00014.safetensors
9924b593d9d0
4.8 GB
safetensors
model-00005-of-00014.safetensors
8a9cb60aa1ec
4.8 GB
safetensors
model-00009-of-00014.safetensors
e0f1b36e873d
4.8 GB
safetensors
model-00013-of-00014.safetensors
c54dc8390d50
4.8 GB
safetensors
model-00006-of-00014.safetensors
9a855b233ef3
4.7 GB
safetensors
model-00007-of-00014.safetensors
8b8ffb9a7d46
4.7 GB
safetensors
model-00010-of-00014.safetensors
b2435d967906
4.7 GB
safetensors
model-00011-of-00014.safetensors
d66581de5271
4.7 GB
safetensors
model-00008-of-00014.safetensors
fa95e2635505
4.6 GB
safetensors
model-00012-of-00014.safetensors
612fd614546e
4.6 GB
safetensors
model-00004-of-00014.safetensors
a32b988ee644
4.6 GB
safetensors
model-00014-of-00014.safetensors
dd16b8d73afe
3.4 GB
safetensors
tokenizer.json
06b9509352d2
19.1 MB
model.safetensors.index.json
cf41a3a3920c
94.6 KB
config.json
96a9035d5bd6
3.5 KB
tokenizer_config.json
792fa3f0cb88
1.1 KB
preprocessor_config.json
27225450ac9c
390 B
video_preprocessor_config.json
7768af27c1fa
385 B
chat_template.jinja
5301c9aa584c
313 B
generation_config.json
a4cef85934ea
214 B