MC-LLaVA-3b / config.json
visheratin's picture
Update modeling file
2d3aedb verified
{
"auto_map": {
"AutoConfig": "modeling_llava.LlavaConfig",
"AutoModel": "modeling_llava.LlavaForCausalLM",
"AutoModelForCausalLM": "modeling_llava.LlavaForCausalLM"
},
"model_type": "mc-llava",
"ignore_index": -100,
"image_token_index": 50297,
"projector_hidden_act": "gelu",
"projector_tokens_num": 1,
"text_config": {
"_name_or_path": "vince62s/phi-2-psy",
"add_cross_attention": false,
"architectures": [
"PhiForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "vince62s/phi-2-psy--configuration_phi.PhiConfig",
"AutoModelForCausalLM": "vince62s/phi-2-psy--modeling_phi.PhiForCausalLM"
},
"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,
"embd_pdrop": 0.0,
"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_new",
"hidden_size": 2560,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 10240,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 2048,
"min_length": 0,
"model_type": "phi",
"no_repeat_ngram_size": 0,
"num_attention_heads": 32,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"partial_rotary_factor": 0.4,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"qk_layernorm": false,
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"resid_pdrop": 0.1,
"return_dict": true,
"return_dict_in_generate": false,
"rope_scaling": null,
"rope_theta": 10000.0,
"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": 51200
},
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"vision_config": {
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
},
"vision_embed_dim": 1152,
"vision_tower_name": "google/siglip-so400m-patch14-384",
"vocab_size": 51200
}