| { |
| "architectures": [ |
| "DeepseekOCR2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "modeling_deepseekocr2.DeepseekOCR2Config", |
| "AutoModel": "modeling_deepseekocr2.DeepseekOCR2ForCausalLM" |
| }, |
| "aux_loss_alpha": 0.001, |
| "bos_token_id": 0, |
| "candidate_resolutions": [ |
| [ |
| 1024, |
| 1024 |
| ] |
| ], |
| "torch_dtype": "bfloat16", |
| "eos_token_id": 1, |
| "first_k_dense_replace": 1, |
| "global_view_pos": "head", |
| "head_dim": 0, |
| "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": 896, |
| "model_type": "mlp_projector", |
| "n_embed": 1280, |
| "projector_type": "linear" |
| }, |
| "q_lora_rank": null, |
| "qk_nope_head_dim": 0, |
| "qk_rope_head_dim": 0, |
| "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": "4.57.6", |
| "use_cache": true, |
| "use_mla": false, |
| "v_head_dim": 0, |
| "vision_config": { |
| "image_size": 1024, |
| "mlp_ratio": 3.7362, |
| "model_name": "deepencoderv2", |
| "model_type": "vision", |
| "width": { |
| "qwen2-0-5b": { |
| "dim": 896 |
| }, |
| "sam_vit_b": { |
| "downsample_channels": [ |
| 512, |
| 1024 |
| ], |
| "global_attn_indexes": [ |
| 2, |
| 5, |
| 8, |
| 11 |
| ], |
| "heads": 12, |
| "layers": 12, |
| "width": 768 |
| } |
| } |
| }, |
| "vocab_size": 129280 |
| } |
