| { |
| "architectures": [ |
| "DeepseekOCRForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "modeling_deepseekocr.DeepseekOCRConfig", |
| "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM" |
| }, |
| "aux_loss_alpha": 0.001, |
| "bos_token_id": 0, |
| "candidate_resolutions": [ |
| [ |
| 1024, |
| 1024 |
| ] |
| ], |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "first_k_dense_replace": 1, |
| "global_view_pos": "head", |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 1280, |
| "initializer_range": 0.02, |
| "intermediate_size": 6848, |
| "kv_lora_rank": null, |
| "language_config": { |
| "architectures": [ |
| "DeepseekV2ForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_deepseekv2.DeepseekV2Config", |
| "AutoModel": "modeling_deepseek.DeepseekV2Model", |
| "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM" |
| }, |
| "bos_token_id": 0, |
| "eos_token_id": 1, |
| "first_k_dense_replace": 1, |
| "hidden_size": 1280, |
| "intermediate_size": 6848, |
| "kv_lora_rank": null, |
| "lm_head": true, |
| "max_position_embeddings": 8192, |
| "moe_intermediate_size": 896, |
| "n_group": 1, |
| "n_routed_experts": 64, |
| "n_shared_experts": 2, |
| "num_attention_heads": 10, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 10, |
| "q_lora_rank": null, |
| "qk_nope_head_dim": 0, |
| "qk_rope_head_dim": 0, |
| "rm_head": false, |
| "topk_group": 1, |
| "topk_method": "greedy", |
| "torch_dtype": "bfloat16", |
| "use_mla": false, |
| "v_head_dim": 0, |
| "vocab_size": 129280 |
| }, |
| "lm_head": true, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "deepseek_vl_v2", |
| "moe_intermediate_size": 896, |
| "n_group": 1, |
| "n_routed_experts": 64, |
| "n_shared_experts": 2, |
| "norm_topk_prob": false, |
| "num_attention_heads": 10, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 10, |
| "projector_config": { |
| "input_dim": 2048, |
| "model_type": "mlp_projector", |
| "n_embed": 1280, |
| "projector_type": "linear" |
| }, |
| "q_lora_rank": null, |
| "qk_nope_head_dim": 0, |
| "qk_rope_head_dim": 0, |
| "quantization_config": { |
| "algo_config": null, |
| "exclude": [ |
| "model.layers.0.self_attn.q_proj", |
| "model.layers.0.self_attn.k_proj", |
| "model.layers.0.self_attn.v_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.1.self_attn.q_proj", |
| "model.layers.1.self_attn.k_proj", |
| "model.layers.1.self_attn.v_proj", |
| "model.layers.1.self_attn.o_proj", |
| "model.layers.1.mlp.shared_experts.gate_proj", |
| "model.layers.1.mlp.shared_experts.up_proj", |
| "model.layers.1.mlp.shared_experts.down_proj", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.2.self_attn.o_proj", |
| "model.layers.2.mlp.shared_experts.gate_proj", |
| "model.layers.2.mlp.shared_experts.up_proj", |
| "model.layers.2.mlp.shared_experts.down_proj", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.mlp.shared_experts.gate_proj", |
| "model.layers.3.mlp.shared_experts.up_proj", |
| "model.layers.3.mlp.shared_experts.down_proj", |
| "model.layers.4.self_attn.q_proj", |
| "model.layers.4.self_attn.k_proj", |
| "model.layers.4.self_attn.v_proj", |
| "model.layers.4.self_attn.o_proj", |
| "model.layers.4.mlp.shared_experts.gate_proj", |
| "model.layers.4.mlp.shared_experts.up_proj", |
| "model.layers.4.mlp.shared_experts.down_proj", |
| "model.layers.5.self_attn.q_proj", |
| "model.layers.5.self_attn.k_proj", |
| "model.layers.5.self_attn.v_proj", |
| "model.layers.5.self_attn.o_proj", |
| "model.layers.5.mlp.shared_experts.gate_proj", |
| "model.layers.5.mlp.shared_experts.up_proj", |
| "model.layers.5.mlp.shared_experts.down_proj", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.6.self_attn.o_proj", |
| "model.layers.6.mlp.shared_experts.gate_proj", |
| "model.layers.6.mlp.shared_experts.up_proj", |
| "model.layers.6.mlp.shared_experts.down_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.mlp.shared_experts.gate_proj", |
| "model.layers.7.mlp.shared_experts.up_proj", |
| "model.layers.7.mlp.shared_experts.down_proj", |
| "model.layers.8.self_attn.q_proj", |
| "model.layers.8.self_attn.k_proj", |
| "model.layers.8.self_attn.v_proj", |
| "model.layers.8.self_attn.o_proj", |
| "model.layers.8.mlp.shared_experts.gate_proj", |
| "model.layers.8.mlp.shared_experts.up_proj", |
| "model.layers.8.mlp.shared_experts.down_proj", |
| "model.layers.9.self_attn.q_proj", |
| "model.layers.9.self_attn.k_proj", |
| "model.layers.9.self_attn.v_proj", |
| "model.layers.9.self_attn.o_proj", |
| "model.layers.9.mlp.shared_experts.gate_proj", |
| "model.layers.9.mlp.shared_experts.up_proj", |
| "model.layers.9.mlp.shared_experts.down_proj", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.10.self_attn.o_proj", |
| "model.layers.10.mlp.shared_experts.gate_proj", |
| "model.layers.10.mlp.shared_experts.up_proj", |
| "model.layers.10.mlp.shared_experts.down_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.mlp.shared_experts.gate_proj", |
| "model.layers.11.mlp.shared_experts.up_proj", |
| "model.layers.11.mlp.shared_experts.down_proj", |
| "model.sam_model.patch_embed.proj", |
| "model.sam_model.blocks.0.attn.qkv", |
| "model.sam_model.blocks.0.attn.proj", |
| "model.sam_model.blocks.0.mlp.lin1", |
| "model.sam_model.blocks.0.mlp.lin2", |
| "model.sam_model.blocks.1.attn.qkv", |
| "model.sam_model.blocks.1.attn.proj", |
| "model.sam_model.blocks.1.mlp.lin1", |
| "model.sam_model.blocks.1.mlp.lin2", |
| "model.sam_model.blocks.2.attn.qkv", |
| "model.sam_model.blocks.2.attn.proj", |
| "model.sam_model.blocks.2.mlp.lin1", |
| "model.sam_model.blocks.2.mlp.lin2", |
| "model.sam_model.blocks.3.attn.qkv", |
| "model.sam_model.blocks.3.attn.proj", |
| "model.sam_model.blocks.3.mlp.lin1", |
| "model.sam_model.blocks.3.mlp.lin2", |
| "model.sam_model.blocks.4.attn.qkv", |
| "model.sam_model.blocks.4.attn.proj", |
| "model.sam_model.blocks.4.mlp.lin1", |
| "model.sam_model.blocks.4.mlp.lin2", |
| "model.sam_model.blocks.5.attn.qkv", |
| "model.sam_model.blocks.5.attn.proj", |
| "model.sam_model.blocks.5.mlp.lin1", |
| "model.sam_model.blocks.5.mlp.lin2", |
| "model.sam_model.blocks.6.attn.qkv", |
| "model.sam_model.blocks.6.attn.proj", |
| "model.sam_model.blocks.6.mlp.lin1", |
| "model.sam_model.blocks.6.mlp.lin2", |
| "model.sam_model.blocks.7.attn.qkv", |
| "model.sam_model.blocks.7.attn.proj", |
| "model.sam_model.blocks.7.mlp.lin1", |
| "model.sam_model.blocks.7.mlp.lin2", |
| "model.sam_model.blocks.8.attn.qkv", |
| "model.sam_model.blocks.8.attn.proj", |
| "model.sam_model.blocks.8.mlp.lin1", |
| "model.sam_model.blocks.8.mlp.lin2", |
| "model.sam_model.blocks.9.attn.qkv", |
| "model.sam_model.blocks.9.attn.proj", |
| "model.sam_model.blocks.9.mlp.lin1", |
| "model.sam_model.blocks.9.mlp.lin2", |
| "model.sam_model.blocks.10.attn.qkv", |
| "model.sam_model.blocks.10.attn.proj", |
| "model.sam_model.blocks.10.mlp.lin1", |
| "model.sam_model.blocks.10.mlp.lin2", |
| "model.sam_model.blocks.11.attn.qkv", |
| "model.sam_model.blocks.11.attn.proj", |
| "model.sam_model.blocks.11.mlp.lin1", |
| "model.sam_model.blocks.11.mlp.lin2", |
| "model.sam_model.neck.0", |
| "model.sam_model.neck.2", |
| "model.sam_model.net_2", |
| "model.sam_model.net_3", |
| "model.vision_model.embeddings.patch_embedding", |
| "model.vision_model.embeddings.position_embedding", |
| "model.vision_model.transformer.layers.0.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.0.self_attn.out_proj", |
| "model.vision_model.transformer.layers.0.mlp.fc1", |
| "model.vision_model.transformer.layers.0.mlp.fc2", |
| "model.vision_model.transformer.layers.1.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.1.self_attn.out_proj", |
| "model.vision_model.transformer.layers.1.mlp.fc1", |
| "model.vision_model.transformer.layers.1.mlp.fc2", |
| "model.vision_model.transformer.layers.2.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.2.self_attn.out_proj", |
| "model.vision_model.transformer.layers.2.mlp.fc1", |
| "model.vision_model.transformer.layers.2.mlp.fc2", |
| "model.vision_model.transformer.layers.3.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.3.self_attn.out_proj", |
| "model.vision_model.transformer.layers.3.mlp.fc1", |
| "model.vision_model.transformer.layers.3.mlp.fc2", |
| "model.vision_model.transformer.layers.4.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.4.self_attn.out_proj", |
| "model.vision_model.transformer.layers.4.mlp.fc1", |
| "model.vision_model.transformer.layers.4.mlp.fc2", |
| "model.vision_model.transformer.layers.5.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.5.self_attn.out_proj", |
| "model.vision_model.transformer.layers.5.mlp.fc1", |
| "model.vision_model.transformer.layers.5.mlp.fc2", |
| "model.vision_model.transformer.layers.6.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.6.self_attn.out_proj", |
| "model.vision_model.transformer.layers.6.mlp.fc1", |
| "model.vision_model.transformer.layers.6.mlp.fc2", |
| "model.vision_model.transformer.layers.7.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.7.self_attn.out_proj", |
| "model.vision_model.transformer.layers.7.mlp.fc1", |
| "model.vision_model.transformer.layers.7.mlp.fc2", |
| "model.vision_model.transformer.layers.8.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.8.self_attn.out_proj", |
| "model.vision_model.transformer.layers.8.mlp.fc1", |
| "model.vision_model.transformer.layers.8.mlp.fc2", |
| "model.vision_model.transformer.layers.9.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.9.self_attn.out_proj", |
| "model.vision_model.transformer.layers.9.mlp.fc1", |
| "model.vision_model.transformer.layers.9.mlp.fc2", |
| "model.vision_model.transformer.layers.10.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.10.self_attn.out_proj", |
| "model.vision_model.transformer.layers.10.mlp.fc1", |
| "model.vision_model.transformer.layers.10.mlp.fc2", |
| "model.vision_model.transformer.layers.11.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.11.self_attn.out_proj", |
| "model.vision_model.transformer.layers.11.mlp.fc1", |
| "model.vision_model.transformer.layers.11.mlp.fc2", |
| "model.vision_model.transformer.layers.12.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.12.self_attn.out_proj", |
| "model.vision_model.transformer.layers.12.mlp.fc1", |
| "model.vision_model.transformer.layers.12.mlp.fc2", |
| "model.vision_model.transformer.layers.13.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.13.self_attn.out_proj", |
| "model.vision_model.transformer.layers.13.mlp.fc1", |
| "model.vision_model.transformer.layers.13.mlp.fc2", |
| "model.vision_model.transformer.layers.14.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.14.self_attn.out_proj", |
| "model.vision_model.transformer.layers.14.mlp.fc1", |
| "model.vision_model.transformer.layers.14.mlp.fc2", |
| "model.vision_model.transformer.layers.15.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.15.self_attn.out_proj", |
| "model.vision_model.transformer.layers.15.mlp.fc1", |
| "model.vision_model.transformer.layers.15.mlp.fc2", |
| "model.vision_model.transformer.layers.16.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.16.self_attn.out_proj", |
| "model.vision_model.transformer.layers.16.mlp.fc1", |
| "model.vision_model.transformer.layers.16.mlp.fc2", |
| "model.vision_model.transformer.layers.17.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.17.self_attn.out_proj", |
| "model.vision_model.transformer.layers.17.mlp.fc1", |
| "model.vision_model.transformer.layers.17.mlp.fc2", |
| "model.vision_model.transformer.layers.18.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.18.self_attn.out_proj", |
| "model.vision_model.transformer.layers.18.mlp.fc1", |
| "model.vision_model.transformer.layers.18.mlp.fc2", |
| "model.vision_model.transformer.layers.19.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.19.self_attn.out_proj", |
| "model.vision_model.transformer.layers.19.mlp.fc1", |
| "model.vision_model.transformer.layers.19.mlp.fc2", |
| "model.vision_model.transformer.layers.20.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.20.self_attn.out_proj", |
| "model.vision_model.transformer.layers.20.mlp.fc1", |
| "model.vision_model.transformer.layers.20.mlp.fc2", |
| "model.vision_model.transformer.layers.21.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.21.self_attn.out_proj", |
| "model.vision_model.transformer.layers.21.mlp.fc1", |
| "model.vision_model.transformer.layers.21.mlp.fc2", |
| "model.vision_model.transformer.layers.22.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.22.self_attn.out_proj", |
| "model.vision_model.transformer.layers.22.mlp.fc1", |
| "model.vision_model.transformer.layers.22.mlp.fc2", |
| "model.vision_model.transformer.layers.23.self_attn.qkv_proj", |
| "model.vision_model.transformer.layers.23.self_attn.out_proj", |
| "model.vision_model.transformer.layers.23.mlp.fc1", |
| "model.vision_model.transformer.layers.23.mlp.fc2", |
| "model.projector.layers", |
| "lm_head" |
| ], |
| "export": { |
| "kv_cache_group": [], |
| "min_kv_scale": 0.0, |
| "pack_method": "reorder", |
| "weight_format": "real_quantized", |
| "weight_merge_groups": null |
| }, |
| "global_quant_config": { |
| "bias": null, |
| "input_tensors": { |
| "ch_axis": -1, |
| "dtype": "fp4", |
| "group_size": 32, |
| "is_dynamic": true, |
| "is_scale_quant": false, |
| "mx_element_dtype": null, |
| "observer_cls": "PerBlockMXObserver", |
| "qscheme": "per_group", |
| "round_method": "half_even", |
| "scale_calculation_mode": "even", |
| "scale_format": "e8m0", |
| "scale_type": "float", |
| "symmetric": null |
| }, |
| "output_tensors": null, |
| "target_device": null, |
| "weight": { |
| "ch_axis": -1, |
| "dtype": "fp4", |
| "group_size": 32, |
| "is_dynamic": false, |
| "is_scale_quant": false, |
| "mx_element_dtype": null, |
| "observer_cls": "PerBlockMXObserver", |
| "qscheme": "per_group", |
| "round_method": "half_even", |
| "scale_calculation_mode": "even", |
| "scale_format": "e8m0", |
| "scale_type": "float", |
| "symmetric": null |
| } |
| }, |
| "kv_cache_post_rope": false, |
| "kv_cache_quant_config": {}, |
| "layer_quant_config": {}, |
| "layer_type_quant_config": {}, |
| "quant_method": "quark", |
| "quant_mode": "eager_mode", |
| "softmax_quant_spec": null, |
| "version": "0.12+86d5498526" |
| }, |
| "rm_head": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "routed_scaling_factor": 1.0, |
| "seq_aux": true, |
| "tie_word_embeddings": false, |
| "tile_tag": "2D", |
| "topk_group": 1, |
| "topk_method": "greedy", |
| "transformers_version": "4.57.3", |
| "use_cache": true, |
| "use_mla": false, |
| "v_head_dim": 0, |
| "vision_config": { |
| "image_size": 1024, |
| "mlp_ratio": 3.7362, |
| "model_name": "deeplip_b_l", |
| "model_type": "vision", |
| "width": { |
| "clip-l-14-224": { |
| "heads": 16, |
| "image_size": 224, |
| "layers": 24, |
| "patch_size": 14, |
| "width": 1024 |
| }, |
| "sam_vit_b": { |
| "downsample_channels": [ |
| 512, |
| 1024 |
| ], |
| "global_attn_indexes": [ |
| 2, |
| 5, |
| 8, |
| 11 |
| ], |
| "heads": 12, |
| "layers": 12, |
| "width": 768 |
| } |
| } |
| }, |
| "vocab_size": 129280 |
| } |
|
|
