Update config.json

config.json

@@ -1,187 +1,46 @@
 {
-  "_name_or_path": "checkpoints/llavaPhi-v0-3b-finetune/checkpoint-4000",
+  "_name_or_path": "/p/project/laionize/marianna/bakllava_original/llava-phi-2-3b",
   "architectures": [
     "LlavaPhiForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
+  "auto_map": {
+    "AutoConfig": "configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": null,
   "embd_pdrop": 0.0,
-  "eos_token_id": 2,
-  "freeze_vision_tower": false,
+  "eos_token_id": null,
+  "freeze_mm_mlp_adapter": false,
   "hidden_act": "gelu_new",
   "hidden_size": 2560,
   "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
   "initializer_range": 0.02,
   "intermediate_size": 10240,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
-  "mm_projector_lr": null,
+  "mm_hidden_size": 1024,
+  "mm_projector_type": "mlp2x_gelu",
   "mm_use_im_patch_token": false,
   "mm_use_im_start_end": false,
-  "model_type": "llava_phi",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "phi-llava",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "partial_rotary_factor": 0.4,
-  "pretraining_tp": 1,
   "qk_layernorm": false,
   "resid_pdrop": 0.1,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 2048,
-  "tokenizer_padding_side": "right",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
-  "tune_mm_mlp_adapter": true,
-  "use_cache": false,
-  "vision_config": {
-    "mm_projector": {
-      "_name_or_path": "",
-      "add_cross_attention": false,
-      "architectures": null,
-      "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_size": 2560,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "is_decoder": false,
-      "is_encoder_decoder": false,
-      "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-      },
-      "length_penalty": 1.0,
-      "max_length": 20,
-      "min_length": 0,
-      "mm_hidden_size": 1024,
-      "mm_projector_type": "mlp2x_gelu",
-      "model_type": "llava_phi_projector",
-      "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,
-      "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,
-      "transformers_version": "4.36.2",
-      "typical_p": 1.0,
-      "use_bfloat16": false
-    },
-    "vision_tower": {
-      "_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,
-      "dropout": 0.0,
-      "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,
-      "hidden_act": "quick_gelu",
-      "hidden_size": 1024,
-      "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-      },
-      "image_size": 336,
-      "initializer_factor": 1.0,
-      "initializer_range": 0.02,
-      "intermediate_size": 4096,
-      "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,
-      "min_length": 0,
-      "mm_vision_select_feature": "patch",
-      "mm_vision_select_layer": -2,
-      "model_type": "llava_phi_clip_vision_model",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 16,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_channels": 3,
-      "num_hidden_layers": 24,
-      "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,
-      "projection_dim": 768,
-      "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,
-      "transformers_version": "4.36.2",
-      "typical_p": 1.0,
-      "use_bfloat16": false
-    }
-  },
+  "transformers_version": "4.37.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
   "vocab_size": 51200
-}
+}