126 lines
3.3 KiB
JSON
126 lines
3.3 KiB
JSON
|
{
|
||
|
"_name_or_path": "Infinigence/Megrez-3B-Omni",
|
||
|
"architectures": [
|
||
|
"MegrezO"
|
||
|
],
|
||
|
"attention_bias": false,
|
||
|
"attention_dropout": 0.0,
|
||
|
"audio_config": {
|
||
|
"add_audio_bos_eos_token": true,
|
||
|
"avg_pool": true,
|
||
|
"n_ctx": 1500,
|
||
|
"n_head": 20,
|
||
|
"n_layer": 32,
|
||
|
"n_mels": 128,
|
||
|
"n_state": 1280,
|
||
|
"output_dim": 2560
|
||
|
},
|
||
|
"auto_map": {
|
||
|
"AutoModel": "modeling_megrezo.MegrezO",
|
||
|
"AutoModelForCausalLM": "modeling_megrezo.MegrezO",
|
||
|
"AutoConfig": "configuration_megrezo.MegrezOConfig",
|
||
|
"AutoProcessor": "processing_megrezo.MegrezOProcessor",
|
||
|
"AutoImageProcessor": "image_processing_megrezo.MegrezOImageProcessor"
|
||
|
},
|
||
|
"bos_token_id": null,
|
||
|
"drop_vision_last_layer": false,
|
||
|
"eos_token_id": 120005,
|
||
|
"hidden_act": "silu",
|
||
|
"hidden_size": 2560,
|
||
|
"initializer_range": 0.02,
|
||
|
"intermediate_size": 7168,
|
||
|
"max_position_embeddings": 4096,
|
||
|
"max_sequence_length": 4096,
|
||
|
"mlp_bias": false,
|
||
|
"model_type": "megrezo",
|
||
|
"num_attention_heads": 40,
|
||
|
"num_hidden_layers": 32,
|
||
|
"num_key_value_heads": 10,
|
||
|
"pad_token_id": 0,
|
||
|
"patch_size": 14,
|
||
|
"pretraining_tp": 1,
|
||
|
"query_num": 64,
|
||
|
"rms_norm_eps": 1e-05,
|
||
|
"rope_scaling": null,
|
||
|
"rope_theta": 5000000.0,
|
||
|
"tie_word_embeddings": false,
|
||
|
"torch_dtype": "bfloat16",
|
||
|
"transformers_version": "4.42.0",
|
||
|
"use_cache": false,
|
||
|
"vision_batch_size": 8,
|
||
|
"vision_config": {
|
||
|
"_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": 980,
|
||
|
"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,
|
||
|
"typical_p": 1.0,
|
||
|
"use_bfloat16": false
|
||
|
},
|
||
|
"vocab_size": 122880
|
||
|
}
|