| { | |
| "_name_or_path": "ckpts/checkpoints-siglip/phi_35/PiXLLaVAPhi35-3b-pretrain", | |
| "architectures": [ | |
| "PIXLPhi3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_phi3.Phi3Config", | |
| "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 32000, | |
| "freeze_vision_tower": true, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "image_aspect_ratio": "square", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mm_projector_lr": null, | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "model_type": "pixl_phi3", | |
| "non_lora_lr": null, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "original_max_position_embeddings": 4096, | |
| "pad_token_id": 32000, | |
| "resid_pdrop": 0.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "long_factor": [ | |
| 1.0800000429153442, | |
| 1.1100000143051147, | |
| 1.1399999856948853, | |
| 1.340000033378601, | |
| 1.5899999141693115, | |
| 1.600000023841858, | |
| 1.6200000047683716, | |
| 2.620000123977661, | |
| 3.2300000190734863, | |
| 3.2300000190734863, | |
| 4.789999961853027, | |
| 7.400000095367432, | |
| 7.700000286102295, | |
| 9.09000015258789, | |
| 12.199999809265137, | |
| 17.670000076293945, | |
| 24.46000099182129, | |
| 28.57000160217285, | |
| 30.420001983642578, | |
| 30.840002059936523, | |
| 32.590003967285156, | |
| 32.93000411987305, | |
| 42.320003509521484, | |
| 44.96000289916992, | |
| 50.340003967285156, | |
| 50.45000457763672, | |
| 57.55000305175781, | |
| 57.93000411987305, | |
| 58.21000289916992, | |
| 60.1400032043457, | |
| 62.61000442504883, | |
| 62.62000274658203, | |
| 62.71000289916992, | |
| 63.1400032043457, | |
| 63.1400032043457, | |
| 63.77000427246094, | |
| 63.93000411987305, | |
| 63.96000289916992, | |
| 63.970001220703125, | |
| 64.02999877929688, | |
| 64.06999969482422, | |
| 64.08000183105469, | |
| 64.12000274658203, | |
| 64.41000366210938, | |
| 64.4800033569336, | |
| 64.51000213623047, | |
| 64.52999877929688, | |
| 64.83999633789062 | |
| ], | |
| "short_factor": [ | |
| 1.0, | |
| 1.0199999809265137, | |
| 1.0299999713897705, | |
| 1.0299999713897705, | |
| 1.0499999523162842, | |
| 1.0499999523162842, | |
| 1.0499999523162842, | |
| 1.0499999523162842, | |
| 1.0499999523162842, | |
| 1.0699999332427979, | |
| 1.0999999046325684, | |
| 1.1099998950958252, | |
| 1.1599998474121094, | |
| 1.1599998474121094, | |
| 1.1699998378753662, | |
| 1.2899998426437378, | |
| 1.339999794960022, | |
| 1.679999828338623, | |
| 1.7899998426437378, | |
| 1.8199998140335083, | |
| 1.8499997854232788, | |
| 1.8799997568130493, | |
| 1.9099997282028198, | |
| 1.9399996995925903, | |
| 1.9899996519088745, | |
| 2.0199997425079346, | |
| 2.0199997425079346, | |
| 2.0199997425079346, | |
| 2.0199997425079346, | |
| 2.0199997425079346, | |
| 2.0199997425079346, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0299997329711914, | |
| 2.0799996852874756, | |
| 2.0899996757507324, | |
| 2.189999580383301, | |
| 2.2199995517730713, | |
| 2.5899994373321533, | |
| 2.729999542236328, | |
| 2.749999523162842, | |
| 2.8399994373321533 | |
| ], | |
| "type": "longrope" | |
| }, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 262144, | |
| "tie_word_embeddings": false, | |
| "tokenizer_model_max_length": 4096, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.47.0", | |
| "tune_mm_mlp_adapter": true, | |
| "use_cache": true, | |
| "vision_config": { | |
| "mm_projector": { | |
| "_attn_implementation_autoset": false, | |
| "_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, | |
| "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, | |
| "hidden_size": 3072, | |
| "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, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "model_type": "pixl_projector", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "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, | |
| "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": "4.46.3", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "vision_tower": { | |
| "_attn_implementation_autoset": false, | |
| "_name_or_path": "", | |
| "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, | |
| "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_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 384, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "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, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "model_type": "pixl_vision_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "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": 512, | |
| "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": "4.46.3", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vision_model_name_or_path": "./ckpts/siglip-so400m-patch14-384" | |
| } | |
| }, | |
| "vocab_size": 32064 | |
| } | |