Update config.json

config.json

@@ -33,161 +33,22 @@
   },
   "torch_dtype": "float16",
   "transformers_version": "4.48.0",
-  "vision_config": {
-    "_name_or_path": "google/siglip-so400m-patch14-384",
+   "vision_config": {
+    "_name_or_path": "./iter_45000_ft/vit_merge_lora",
     "architectures": [
-      "SiglipModel"
+      "SiglipVisionModel"
     ],
-    "model_type": "siglip",
-    "text_config": {
-      "_attn_implementation_autoset": false,
-      "_name_or_path": "",
-      "add_cross_attention": false,
-      "architectures": null,
-      "attention_dropout": 0.0,
-      "bad_words_ids": null,
-      "begin_suppress_tokens": null,
-      "bos_token_id": 49406,
-      "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": 49407,
-      "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"
-      },
-      "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,
-      "max_position_embeddings": 64,
-      "min_length": 0,
-      "model_type": "siglip_text_model",
-      "no_repeat_ngram_size": 0,
-      "num_attention_heads": 16,
-      "num_beam_groups": 1,
-      "num_beams": 1,
-      "num_hidden_layers": 27,
-      "num_return_sequences": 1,
-      "output_attentions": false,
-      "output_hidden_states": false,
-      "output_scores": false,
-      "pad_token_id": 1,
-      "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": 32000
-    },
-    "torch_dtype": "float32",
-    "vision_config": {
-      "_attn_implementation_autoset": false,
-      "_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": 384,
-      "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
-    }
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "float32"
   },
   "vision_feature_layer": -2,
-  "vision_feature_select_strategy": "full"
+  "vision_feature_select_strategy": "default"
 }