IntMeGroup/ICCVW_st2_mos2

1{2  "_commit_hash": null,3  "_name_or_path": "/dev/shm/wjr/weights/st1/mos2_st1",4  "architectures": [5    "InternVLChatModel"6  ],7  "auto_map": {8    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",9    "AutoModel": "modeling_internvl_chat.InternVLChatModel",10    "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"11  },12  "downsample_ratio": 0.5,13  "dynamic_image_size": true,14  "force_image_size": 448,15  "hidden_size": 4096,16  "image_fold": null,17  "llm_config": {18    "_attn_implementation_autoset": true,19    "_name_or_path": "/mnt/petrelfs/share_data/wangweiyun/share_ckpt/hf_home/internlm2-chat-7b",20    "add_cross_attention": false,21    "architectures": [22      "InternLM2ForCausalLM"23    ],24    "attn_implementation": "flash_attention_2",25    "auto_map": {26      "AutoConfig": "configuration_internlm2.InternLM2Config",27      "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",28      "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"29    },30    "bad_words_ids": null,31    "begin_suppress_tokens": null,32    "bias": false,33    "bos_token_id": 1,34    "chunk_size_feed_forward": 0,35    "cross_attention_hidden_size": null,36    "decoder_start_token_id": null,37    "diversity_penalty": 0.0,38    "do_sample": false,39    "early_stopping": false,40    "encoder_no_repeat_ngram_size": 0,41    "eos_token_id": 2,42    "exponential_decay_length_penalty": null,43    "finetuning_task": null,44    "forced_bos_token_id": null,45    "forced_eos_token_id": null,46    "hidden_act": "silu",47    "hidden_size": 4096,48    "id2label": {49      "0": "LABEL_0",50      "1": "LABEL_1"51    },52    "initializer_range": 0.02,53    "intermediate_size": 10240,54    "is_decoder": false,55    "is_encoder_decoder": false,56    "label2id": {57      "LABEL_0": 0,58      "LABEL_1": 159    },60    "length_penalty": 1.0,61    "max_length": 20,62    "max_position_embeddings": 32768,63    "min_length": 0,64    "model_type": "internlm2",65    "moe_config": null,66    "no_repeat_ngram_size": 0,67    "num_attention_heads": 32,68    "num_beam_groups": 1,69    "num_beams": 1,70    "num_hidden_layers": 48,71    "num_key_value_heads": 2,72    "num_return_sequences": 1,73    "output_attentions": false,74    "output_hidden_states": false,75    "output_scores": false,76    "pad_token_id": 2,77    "prefix": null,78    "pretraining_tp": 1,79    "problem_type": null,80    "pruned_heads": {},81    "remove_invalid_values": false,82    "repetition_penalty": 1.0,83    "return_dict": true,84    "return_dict_in_generate": false,85    "rms_norm_eps": 1e-05,86    "rope_scaling": {87      "factor": 2.0,88      "type": "dynamic"89    },90    "rope_theta": 50000000,91    "sep_token_id": null,92    "suppress_tokens": null,93    "task_specific_params": null,94    "temperature": 1.0,95    "tf_legacy_loss": false,96    "tie_encoder_decoder": false,97    "tie_word_embeddings": false,98    "tokenizer_class": null,99    "top_k": 50,100    "top_p": 1.0,101    "torch_dtype": "bfloat16",102    "torchscript": false,103    "transformers_version": "4.48.3",104    "typical_p": 1.0,105    "use_bfloat16": false,106    "use_cache": false,107    "vocab_size": 128142108  },109  "max_dynamic_patch": 6,110  "min_dynamic_patch": 1,111  "model_type": "internvl_chat",112  "pad2square": false,113  "ps_version": "v2",114  "select_layer": -1,115  "system_message": null,116  "template": "internlm2-chat",117  "tie_word_embeddings": false,118  "torch_dtype": "bfloat16",119  "transformers_version": null,120  "use_backbone_lora": 16,121  "use_img_start_end_token": true,122  "use_llm_lora": 16,123  "use_thumbnail": true,124  "vision_config": {125    "_attn_implementation_autoset": true,126    "_name_or_path": "pretrained/intern_vit_6b_448px_v1_2/",127    "add_cross_attention": false,128    "architectures": [129      "InternVisionModel"130    ],131    "attention_dropout": 0.0,132    "auto_map": {133      "AutoConfig": "configuration_intern_vit.InternVisionConfig",134      "AutoModel": "modeling_intern_vit.InternVisionModel"135    },136    "bad_words_ids": null,137    "begin_suppress_tokens": null,138    "bos_token_id": null,139    "capacity_factor": 1.2,140    "chunk_size_feed_forward": 0,141    "cross_attention_hidden_size": null,142    "decoder_start_token_id": null,143    "diversity_penalty": 0.0,144    "do_sample": false,145    "drop_path_rate": 0.1,146    "dropout": 0.0,147    "early_stopping": false,148    "encoder_no_repeat_ngram_size": 0,149    "eos_token_id": null,150    "eval_capacity_factor": 1.4,151    "exponential_decay_length_penalty": null,152    "finetuning_task": null,153    "forced_bos_token_id": null,154    "forced_eos_token_id": null,155    "hidden_act": "gelu",156    "hidden_size": 1024,157    "id2label": {158      "0": "LABEL_0",159      "1": "LABEL_1"160    },161    "image_size": 448,162    "initializer_factor": 0.1,163    "initializer_range": 1e-10,164    "intermediate_size": 4096,165    "is_decoder": false,166    "is_encoder_decoder": false,167    "label2id": {168      "LABEL_0": 0,169      "LABEL_1": 1170    },171    "laux_allreduce": "all_nodes",172    "layer_norm_eps": 1e-06,173    "length_penalty": 1.0,174    "max_length": 20,175    "min_length": 0,176    "model_type": "intern_vit_6b",177    "moe_coeff_ratio": 0.5,178    "moe_intermediate_size": 768,179    "moe_output_scale": 4.0,180    "no_repeat_ngram_size": 0,181    "noisy_gate_policy": "RSample_before",182    "norm_type": "layer_norm",183    "num_attention_heads": 16,184    "num_beam_groups": 1,185    "num_beams": 1,186    "num_channels": 3,187    "num_experts": 8,188    "num_hidden_layers": 24,189    "num_return_sequences": 1,190    "num_routed_experts": 4,191    "num_shared_experts": 4,192    "output_attentions": false,193    "output_hidden_states": false,194    "output_scores": false,195    "pad_token_id": null,196    "patch_size": 14,197    "prefix": null,198    "problem_type": null,199    "pruned_heads": {},200    "qk_normalization": false,201    "qkv_bias": true,202    "remove_invalid_values": false,203    "repetition_penalty": 1.0,204    "return_dict": true,205    "return_dict_in_generate": false,206    "sep_token_id": null,207    "shared_expert_intermediate_size": 3072,208    "suppress_tokens": null,209    "task_specific_params": null,210    "temperature": 1.0,211    "tf_legacy_loss": false,212    "tie_encoder_decoder": false,213    "tie_word_embeddings": true,214    "tokenizer_class": null,215    "top_k": 50,216    "top_p": 1.0,217    "torch_dtype": "bfloat16",218    "torchscript": false,219    "transformers_version": "4.48.3",220    "typical_p": 1.0,221    "use_bfloat16": false,222    "use_flash_attn": true,223    "use_moe": false,224    "use_residual": true,225    "use_rts": false,226    "use_weighted_residual": false227  }228}229