| { | |
| "architectures": [ | |
| "DFlash2DraftModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": null, | |
| "is_causal": false, | |
| "dflash_config": { | |
| "block_size": 8, | |
| "conv_group_size": 16, | |
| "conv_kernel_size": 2, | |
| "mask_token_id": 248070, | |
| "selector_rank": 256, | |
| "selector_top_k": 16, | |
| "target_layer_ids": [ | |
| 5, | |
| 19, | |
| 33, | |
| 47, | |
| 61 | |
| ] | |
| }, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 17408, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 262144, | |
| "max_window_layers": 5, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 5, | |
| "num_key_value_heads": 8, | |
| "num_target_layers": 64, | |
| "pad_token_id": 248044, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": 2048, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.15.0", | |
| "use_cache": true, | |
| "use_sliding_window": true, | |
| "vocab_size": 248320, | |
| "quantization_config": { | |
| "activation_scheme": "dynamic", | |
| "dequantize": false, | |
| "fmt": "e4m3", | |
| "quant_method": "fp8", | |
| "scale_fmt": "float", | |
| "weight_block_size": [ | |
| 128, | |
| 128 | |
| ], | |
| "modules_to_not_convert": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "qkv_proj", | |
| "fc", | |
| "lm_head", | |
| "layers.0.self_attn.q_proj", | |
| "layers.0.self_attn.k_proj", | |
| "layers.0.self_attn.v_proj", | |
| "layers.0.attention_conv.kernel_projection", | |
| "layers.0.mlp_conv.kernel_projection", | |
| "layers.1.self_attn.q_proj", | |
| "layers.1.self_attn.k_proj", | |
| "layers.1.self_attn.v_proj", | |
| "layers.1.attention_conv.kernel_projection", | |
| "layers.1.mlp_conv.kernel_projection", | |
| "layers.2.self_attn.q_proj", | |
| "layers.2.self_attn.k_proj", | |
| "layers.2.self_attn.v_proj", | |
| "layers.2.attention_conv.kernel_projection", | |
| "layers.2.mlp_conv.kernel_projection", | |
| "layers.3.self_attn.q_proj", | |
| "layers.3.self_attn.k_proj", | |
| "layers.3.self_attn.v_proj", | |
| "layers.3.attention_conv.kernel_projection", | |
| "layers.3.mlp_conv.kernel_projection", | |
| "layers.4.self_attn.q_proj", | |
| "layers.4.self_attn.k_proj", | |
| "layers.4.self_attn.v_proj", | |
| "layers.4.attention_conv.kernel_projection", | |
| "layers.4.mlp_conv.kernel_projection", | |
| "candidate_selector.hidden_projection" | |
| ] | |
| } | |
| } | |
Xet Storage Details
- Size:
- 2.64 kB
- Xet hash:
- d901f4863d0a0ac1f496d91428458d1475782f636b1a6653b21ac8accbb53cd6
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.