Update with important fields from original config.json

config.json

@@ -13,24 +13,67 @@
   "hidden_size": 3584,
   "image_fold": null,
   "llm_config": {
+    "_attn_implementation_autoset": true,
     "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+    "add_cross_attention": false,
     "architectures": [
       "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
     "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 151643,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
     "hidden_act": "silu",
     "hidden_size": 3584,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "initializer_range": 0.02,
     "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1,
+    "max_length": 20,
     "max_position_embeddings": 32768,
     "max_window_layers": 70,
+    "min_length": 0,
     "model_type": "qwen2",
     "moe_config": null,
+    "no_repeat_ngram_size": 0,
     "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_hidden_layers": 28,
     "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-06,
     "rope_scaling": {
       "factor": 2.0,
@@ -38,8 +81,19 @@
       "type": "dynamic"
     },
     "rope_theta": 1000000.0,
+    "sep_token_id": null,
     "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1,
     "torch_dtype": "bfloat16",
+    "typical_p": 1,
     "use_bfloat16": true,
     "use_cache": false,
     "use_sliding_window": false,
@@ -200,7 +254,9 @@
   "use_llm_lora": 0,
   "use_thumbnail": true,
   "vision_config": {
+    "_attn_implementation_autoset": true,
     "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+    "add_cross_attention": false,
     "architectures": [
       "InternVisionModel"
     ],
@@ -209,35 +265,89 @@
       "AutoConfig": "configuration_intern_vit.InternVisionConfig",
       "AutoModel": "modeling_intern_vit.InternVisionModel"
     },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
     "capacity_factor": 1.2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0,
+    "do_sample": false,
     "drop_path_rate": 0.1,
     "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
     "eval_capacity_factor": 1.4,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "image_size": 448,
     "initializer_factor": 0.1,
     "initializer_range": 1e-10,
     "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
     "laux_allreduce": "all_nodes",
     "layer_norm_eps": 1e-06,
+    "length_penalty": 1,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "intern_vit_6b",
     "moe_coeff_ratio": 0.5,
     "moe_intermediate_size": 768,
     "moe_output_scale": 4.0,
+    "no_repeat_ngram_size": 0,
     "noisy_gate_policy": "RSample_before",
     "norm_type": "layer_norm",
     "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_channels": 3,
     "num_experts": 8,
     "num_hidden_layers": 24,
+    "num_return_sequences": 1,
     "num_routed_experts": 4,
     "num_shared_experts": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
     "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
     "qk_normalization": false,
     "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
     "shared_expert_intermediate_size": 3072,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1,
     "torch_dtype": "bfloat16",
+    "typical_p": 1,
     "use_bfloat16": true,
     "use_flash_attn": true,
     "use_moe": false,