{ "_name_or_path": "/g0001sr/code/allsparkv2_250120/model_zoo/point_stage1/allsparkv2_qwen25_0.5B_vision_stage1_stage1_5_stage2_point_reusetext_stage1", "add_moe": true, "architectures": [ "AllSparkForCausalLM" ], "hidden_size": 896, "ignore_index": -100, "initializer_range": 0.02, "llm_config": { "_attn_implementation_autoset": true, "_name_or_path": "./model_weights/Qwen2.5-0.5B-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": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "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": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "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": null, "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": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 151667 }, "llm_name_or_path": "./model_weights/Qwen2.5-0.5B-Instruct", "modal_configs": [ { "encoder_cfg": { "_attn_implementation_autoset": true, "_name_or_path": "./model_weights/siglip-so400m-patch14-384", "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, "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, "model_type": "siglip_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, "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": "4.47.0", "typical_p": 1.0, "use_bfloat16": false }, "modal_placeholder_token": "<|vision_placeholder|>", "modal_placeholder_token_id": 151665, "modal_tag": "vision", "model_name_or_path": "./model_weights/siglip-so400m-patch14-384", "multi_grid": false, "proj_input_dim": 1152, "proj_num_layers": 2, "proj_output_dim": 896 }, { "depth": 24, "drop_path_rate": 0.1, "embed_dim": 1024, "encoder_cfg": { "depth": 24, "drop_path_rate": 0.1, "embed_dim": 1024, "group_size": 32, "img_queries": 13, "large_embedding": false, "mask_type": "rand", "modal_placeholder_token": "<|point_placeholder|>", "modal_tag": "point", "model_path": "/g0001sr/code/allsparkv2_250120/model_weights/pointencoder/recon2_converted.pth", "num_group": 512, "num_heads": 16, "output_dim": 896, "pretrained_model_name": "eva_large_patch14_336.in22k_ft_in22k_in1k", "stop_grad": false, "text_queries": 3, "with_color": true }, "group_size": 32, "img_queries": 13, "large_embedding": false, "mask_type": "rand", "modal_placeholder_token": "<|point_placeholder|>", "modal_placeholder_token_id": 151666, "modal_tag": "point", "model_path": "/g0001sr/code/allsparkv2_250120/model_weights/pointencoder/recon2_converted.pth", "num_group": 512, "num_heads": 16, "output_dim": 896, "pretrained_model_name": "eva_large_patch14_336.in22k_ft_in22k_in1k", "stop_grad": false, "text_queries": 3, "with_color": true } ], "model_type": "allspark", "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.47.0" }