{ "architectures": [ "LlavaForConditionalGeneration" ], "ignore_index": -100, "image_token_index": 50297, "model_type": "llava", "projector_hidden_act": "gelu", "projector_tokens_num": 5, "text_config": { "_name_or_path": "cognitivecomputations/dolphin-2_6-phi-2", "activation_function": "gelu_new", "add_cross_attention": false, "architectures": [ "PhiForCausalLM" ], "attn_pdrop": 0.0, "auto_map": { "AutoConfig": "cognitivecomputations/dolphin-2_6-phi-2--configuration_phi.PhiConfig", "AutoModelForCausalLM": "cognitivecomputations/dolphin-2_6-phi-2--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, "flash_attn": false, "flash_rotary": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "fused_dense": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "img_processor": null, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_epsilon": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "phi-msft", "n_embd": 2560, "n_head": 32, "n_head_kv": null, "n_inner": null, "n_layer": 32, "n_positions": 2048, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "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, "resid_pdrop": 0.1, "return_dict": true, "return_dict_in_generate": false, "rotary_dim": 32, "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": "float16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": false, "vocab_size": 51200 }, "preprocess_config": { "mean": [ 0.5, 0.5, 0.5 ], "std": [ 0.5, 0.5, 0.5 ], "interpolation": "bicubic", "resize_mode": "squash", "size": 384 }, "torch_dtype": "float16", "transformers_version": "4.36.2", "vision_embed_dim": 1152, "vision_tower_name": "ViT-SO400M-14-SigLIP-384", "vocab_size": 51200 }