| { |
| "_commit_hash": null, |
| "_name_or_path": "/mnt/workspace/Chimera/checkpoints/solva-reasoner-8B", |
| "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": 4096, |
| "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": "internlm/internlm2_5-7b-chat", |
| "add_cross_attention": false, |
| "architectures": [ |
| "InternLM2ForCausalLM" |
| ], |
| "attn_implementation": "flash_attention_2", |
| "auto_map": { |
| "AutoConfig": "configuration_internlm2.InternLM2Config", |
| "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", |
| "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM" |
| }, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bias": false, |
| "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, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 2, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "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, |
| "min_length": 0, |
| "model_type": "internlm2", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 32, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 2, |
| "prefix": null, |
| "pretraining_tp": 1, |
| "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-05, |
| "rope_scaling": { |
| "factor": 2.0, |
| "type": "dynamic" |
| }, |
| "rope_theta": 1000000, |
| "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": 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": 92558 |
| }, |
| "max_dynamic_patch": 6, |
| "min_dynamic_patch": 1, |
| "model_type": "chimera", |
| "pad2square": false, |
| "ps_version": "solva-chat", |
| "select_layer": -1, |
| "template": "solva-chat", |
| "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 |
| } |
| } |
|
|
