| { |
| "_commit_hash": null, |
| "_name_or_path": "/mnt/petrelfs/wangweiyun/workspace_wwy/open_source/InternVL/internvl_chat/work_dirs/internvl_chat_v3_0/InternVL3_0-78B-MPO-try0-2/checkpoint-400", |
| "architectures": [ |
| "InternVLChatModel" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" |
| }, |
| "downsample_ratio": 0.5, |
| "dynamic_image_size": true, |
| "force_image_size": 448, |
| "hidden_size": 8192, |
| "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": 0.0, |
| "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": 8192, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 29568, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "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": 64, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 8, |
| "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": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "factor": 2.0, |
| "rope_type": "dynamic", |
| "type": "dynamic" |
| }, |
| "rope_theta": 1000000.0, |
| "sep_token_id": null, |
| "sliding_window": null, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torch_dtype": "bfloat16", |
| "torchscript": false, |
| "transformers_version": "4.48.3", |
| "typical_p": 1.0, |
| "use_bfloat16": true, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 151674 |
| }, |
| "max_dynamic_patch": 12, |
| "min_dynamic_patch": 1, |
| "model_type": "internvl_chat", |
| "pad2square": false, |
| "ps_version": "v2", |
| "select_layer": -1, |
| "system_message": null, |
| "template": "internvl2_5", |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": null, |
| "use_backbone_lora": 0, |
| "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" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "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": 0.0, |
| "do_sample": false, |
| "drop_path_rate": 0.4, |
| "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": 3200, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 448, |
| "initializer_factor": 0.1, |
| "initializer_range": 1e-10, |
| "intermediate_size": 12800, |
| "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": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "intern_vit_6b", |
| "moe_coeff_ratio": 0.5, |
| "moe_intermediate_size": 3200, |
| "moe_output_scale": 4.0, |
| "no_repeat_ngram_size": 0, |
| "noisy_gate_policy": "RSample_before", |
| "norm_type": "rms_norm", |
| "num_attention_heads": 25, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_channels": 3, |
| "num_experts": 8, |
| "num_hidden_layers": 45, |
| "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": true, |
| "qkv_bias": false, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "sep_token_id": null, |
| "shared_expert_intermediate_size": 12800, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torch_dtype": "bfloat16", |
| "torchscript": false, |
| "transformers_version": "4.48.3", |
| "typical_p": 1.0, |
| "use_bfloat16": true, |
| "use_flash_attn": true, |
| "use_moe": false, |
| "use_residual": true, |
| "use_rts": false, |
| "use_weighted_residual": false |
| } |
| } |
|
|
