MedM-VL-CT-3B-en / config.json
shiym2000's picture
Upload 6 files
94f0308 verified
{
"_name_or_path": "/hdd/shiym/work_dirs/MedM-VL/MedM-VL-CT-3B-en-pretrain",
"architectures": [
"LVLMForConditionalGeneration"
],
"cache_dir_hf": "/mnt/nfs_share/shiym/ckpts/cache_dir_hf",
"connector_image3d_config": {
"connector_name": "mlp2x_gelu",
"connector_path": null,
"connector_type": "spatial_pooling",
"img_size": [
32,
256,
256
],
"input_dim": 768,
"model_type": "",
"output_dim": 3072,
"patch_size": [
4,
16,
16
]
},
"connector_image3d_name": "mlp2x_gelu",
"connector_image3d_path": null,
"connector_image3d_type": "spatial_pooling",
"connector_image_config": null,
"connector_image_name": null,
"connector_image_path": null,
"connector_image_type": null,
"encoder_image3d_config": {
"_name_or_path": "GoodBaiBai88/M3D-CLIP",
"add_cross_attention": false,
"architectures": [
"M3DCLIP"
],
"auto_map": {
"AutoConfig": "GoodBaiBai88/M3D-CLIP--configuration_m3d_clip.M3DCLIPConfig",
"AutoModel": "GoodBaiBai88/M3D-CLIP--modeling_m3d_clip.M3DCLIP"
},
"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_rate": 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,
"gather_loss": true,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"img_size": [
32,
256,
256
],
"in_channels": 1,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"language_model_name_or_path": "bert-base-uncased",
"length_penalty": 1.0,
"local_loss": false,
"max_length": 20,
"max_text_len": 128,
"min_length": 0,
"mlp_dim": 3072,
"model_type": "m3d_clip",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_heads": 12,
"num_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"patch_size": [
4,
16,
16
],
"pos_embed": "perceptron",
"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,
"spatial_dims": 3,
"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,
"typical_p": 1.0,
"use_bfloat16": false,
"vocab_size": 30522
},
"encoder_image3d_name_or_path": "GoodBaiBai88/M3D-CLIP",
"encoder_image3d_select_feature": "patch",
"encoder_image3d_select_layer": -1,
"encoder_image3d_type": "m3dclip",
"encoder_image_config": null,
"encoder_image_name_or_path": null,
"encoder_image_select_feature": null,
"encoder_image_select_layer": null,
"encoder_image_type": null,
"hidden_size": 3072,
"llm_attn_implementation": "flash_attention_2",
"llm_config": {
"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
"add_cross_attention": false,
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 128000,
"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": [
128001,
128008,
128009
],
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"head_dim": 128,
"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,
"mlp_bias": false,
"model_type": "llama",
"no_repeat_ngram_size": 0,
"num_attention_heads": 24,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 28,
"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,
"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": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3",
"type": "linear"
},
"rope_theta": 500000.0,
"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,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 128256
},
"llm_max_length": 512,
"llm_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
"llm_padding_side": "right",
"llm_type": "llama3",
"tokenizer_use_fast": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.4",
"use_cache": false
}