Magma-8B / config.json
jw2yang's picture
remove abundant contents
ba47289
{
"_name_or_path": "microsoft/Magma-8B",
"architectures": [
"MagmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "microsoft/Magma-8B--configuration_magma.MagmaConfig",
"AutoModelForCausalLM": "microsoft/Magma-8B--modeling_magma.MagmaForCausalLM"
},
"hidden_act": "silu",
"hidden_size": 4096,
"image_token_index": 128257,
"img_size": 512,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mm_use_image_history": true,
"mm_use_image_start_end": true,
"mm_use_trace_speed": true,
"mm_use_trace_start_end": false,
"model_type": "magma",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"remove_static_trace_pts": true,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"spatial_quant_size": 256,
"text_config": {
"_name_or_path": "meta-llama/Meta-Llama-3-8B-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": 128009,
"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": 8192,
"min_length": 0,
"mlp_bias": false,
"model_type": "llama",
"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": 128256,
"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": null,
"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": false,
"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": 128261
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.1",
"use_cache": false,
"vision_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"feature_outs": "encoder",
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "square",
"img_anyres_strategy": "crop",
"img_size": 768,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_num_crops": 4,
"max_position_embeddings": 8192,
"mm_hidden_size": 3072,
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"proj_vis_to_txt_tokens": false,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"tune_mm_mlp_adapter": false,
"tune_vision_tokenizer": "all",
"use_cache": true,
"use_mm_proj": true,
"vision_backbone": "convnextxxlarge",
"vision_feature_layer": "clip_vis_dense",
"vision_tokenizer_lr": null,
"vocab_size": 128257
},
"vocab_size": 128320
}