{ "_commit_hash": null, "_name_or_path": "/mnt/workspace/Chimera/checkpoints/solva-reasoner-4B", "architectures": [ "ChimeraChatModel" ], "auto_map": { "AutoConfig": "configuration_chimera.ChimeraChatConfig", "AutoModel": "modeling_chimera.ChimeraChatModel", "AutoModelForCausalLM": "modeling_chimera.ChimeraChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "expert_encoder_config": { "_attn_implementation_internal": null, "_commit_hash": null, "_name_or_path": "", "add_cross_attention": false, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "config_list": [ { "config": { "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/table_kosmos", "add_cross_attention": false, "architectures": [ "Kosmos2_5VisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "d_ff": 3968, "d_kv": 64, "decoder_start_token_id": null, "dense_act_fn": "gelu_new", "diversity_penalty": 0.0, "do_sample": false, "dropout_rate": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_size": 1536, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_factor": 1.0, "initializer_range": 1e-10, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 4096, "min_length": 0, "model_type": "kosmos_2_5_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 24, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 18, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_embed_hidden_size": 768, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "seq_len": 4096, "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": "float32", "torchscript": false, "transformers_version": "4.44.2", "typical_p": 1.0, "use_bfloat16": false }, "domain": "table", "index": 0, "select_layer": -1 }, { "config": { "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/math_clip", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "quick_gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 336, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "clip_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "projection_dim": 768, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "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": null, "torchscript": false, "transformers_version": "4.44.2", "typical_p": 1.0, "use_bfloat16": false }, "domain": "math", "index": 1, "select_layer": -2 }, { "config": { "_name_or_path": "/cpfs01/shared/ADLab/datasets/science_dataset/solva_modules/chart_p2s", "add_cross_attention": false, "architectures": [ "Pix2StructVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "d_ff": 3968, "d_kv": 64, "decoder_start_token_id": null, "dense_act_fn": "gelu_new", "diversity_penalty": 0.0, "do_sample": false, "dropout_rate": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_size": 1536, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_factor": 1.0, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_bias": false, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "pix2struct_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 24, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 18, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_embed_hidden_size": 768, "patch_size": 16, "prefix": null, "problem_type": null, "projection_dim": 768, "pruned_heads": {}, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "seq_len": 4096, "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": "float32", "torchscript": false, "transformers_version": "4.44.2", "typical_p": 1.0, "use_bfloat16": false }, "domain": "chart", "index": 2, "select_layer": -1 } ], "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": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "llm_hidden_size": 3072, "max_length": 20, "min_length": 0, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_encoder": 3, "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, "sep_token_id": null, "separate_load": false, "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": null, "torchscript": false, "transformers_version": null, "typical_p": 1.0, "use_bfloat16": false }, "force_image_size": 448, "llm_config": { "_name_or_path": "microsoft/Phi-3-mini-128k-instruct", "add_cross_attention": false, "architectures": [ "Phi3ForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_phi3.Phi3Config", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "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, "embd_pdrop": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 32000, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "phi3", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_return_sequences": 1, "original_max_position_embeddings": 4096, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 32000, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "resid_pdrop": 0.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0799999237060547, 1.2299998998641968, 1.2299998998641968, 1.2999999523162842, 1.4499999284744263, 1.5999999046325684, 1.6499998569488525, 1.8999998569488525, 2.859999895095825, 3.68999981880188, 5.419999599456787, 5.489999771118164, 5.489999771118164, 9.09000015258789, 11.579999923706055, 15.65999984741211, 15.769999504089355, 15.789999961853027, 18.360000610351562, 21.989999771118164, 23.079999923706055, 30.009998321533203, 32.35000228881836, 32.590003967285156, 35.56000518798828, 39.95000457763672, 53.840003967285156, 56.20000457763672, 57.95000457763672, 59.29000473022461, 59.77000427246094, 59.920005798339844, 61.190006256103516, 61.96000671386719, 62.50000762939453, 63.3700065612793, 63.48000717163086, 63.48000717163086, 63.66000747680664, 63.850006103515625, 64.08000946044922, 64.760009765625, 64.80001068115234, 64.81001281738281, 64.81001281738281 ], "short_factor": [ 1.05, 1.05, 1.05, 1.1, 1.1, 1.1500000000000001, 1.2000000000000002, 1.2500000000000002, 1.3000000000000003, 1.3500000000000003, 1.5000000000000004, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.1000000000000005, 2.1000000000000005, 2.1000000000000005, 2.1500000000000004, 2.1500000000000004, 2.3499999999999996, 2.549999999999999, 2.5999999999999988, 2.5999999999999988, 2.7499999999999982, 2.849999999999998, 2.849999999999998, 2.9499999999999975 ], "type": "su" }, "rope_theta": 10000.0, "sep_token_id": null, "sliding_window": 262144, "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": "4.44.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "vocab_size": 32025 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "chimera", "pad2square": false, "ps_version": "solva-chat", "select_layer": -1, "template": "solva-chat-phi3", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "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": 0.1, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "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": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "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": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "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": "4.44.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": true } }