Spaces:
Running
Running
Download models/qwen.json from alphabell/Model-Observatory: direct link, hf CLI and curl.
- Browser
- Download file 2.47 kB
-
https://huggingface.co/spaces/alphabell/Model-Observatory/resolve/main/models/qwen.json
- Command line
-
hf download hf://spaces/alphabell/Model-Observatory/models/qwen.json
-
curl -L -o qwen.json https://huggingface.co/spaces/alphabell/Model-Observatory/resolve/main/models/qwen.json
2.47 kB
| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "model_type": "qwen3_5_text", | |
| "num_hidden_layers": 64, | |
| "hidden_size": 5120, | |
| "intermediate_size": 17408, | |
| "num_attention_heads": 24, | |
| "num_key_value_heads": 4, | |
| "head_dim": 256, | |
| "attn_output_gate": true, | |
| "full_attention_interval": 4, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_value_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 48, | |
| "mamba_ssm_dtype": "float32", | |
| "rms_norm_eps": 0.000001, | |
| "max_position_embeddings": 262144, | |
| "vocab_size": 248320, | |
| "partial_rotary_factor": 0.25, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "hidden_act": "silu", | |
| "num_experts": 0, | |
| "first_k_dense_replace": 64 | |
| } | |