Upload config.json

config.json

@@ -0,0 +1,79 @@
+{
+  "architectures": [
+    "TinyEmoForConditionalGeneration"
+  ],
+  "cache_dir": null,
+  "connector_type": "mlp2x_gelu",
+  "hidden_size": 2560,
+  "ignore_index": -100,
+  "image_aspect_ratio": "square",
+  "image_token_index": -200,
+  "llm_model_name_or_path": "microsoft/phi-2",
+  "model_type": "tinyemo",
+  "num_queries": 128,
+  "num_resampler_layers": 3,
+  "pad_token": "<|endoftext|>",
+  "pad_token_id": 50256,
+  "resampler_hidden_size": 768,
+  "text_config": {
+    "_name_or_path": "microsoft/phi-2",
+    "architectures": [
+      "PhiForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 50256,
+    "embd_pdrop": 0.0,
+    "eos_token_id": 50256,
+    "hidden_act": "gelu_new",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 2048,
+    "model_type": "phi",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "partial_rotary_factor": 0.4,
+    "qk_layernorm": false,
+    "resid_pdrop": 0.1,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.37.0",
+    "use_cache": true,
+    "vocab_size": 51200
+  },
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "tokenizer_use_fast": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0",
+  "tune_type_connector": "full",
+  "tune_type_llm": "full",
+  "tune_type_vision_tower": "frozen",
+  "tune_vision_tower_from_layer": 0,
+  "use_cache": true,
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-large-patch14",
+    "architectures": [
+      "CLIPModel"
+    ],
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 224,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "patch",
+  "vision_hidden_size": 1024,
+  "vision_model_name_or_path": "openai/clip-vit-large-patch14",
+  "vocab_size": 51200
+}