Training in progress, step 500

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Duckq/blip2-opt-2.7b-v2-emotion-llm-v2",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "image_token_index": null,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "_attn_implementation_autoset": true,
+    "encoder_hidden_size": 1024,
+    "hidden_size": 1408,
+    "model_type": "blip_2_qformer",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 16
+  },
+  "text_config": {
+    "model_type": "opt"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "hidden_size": 1024,
+    "model_type": "blip_2_vision_model",
+    "num_hidden_layers": 16
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1b29066f4d7f9242075b94335791bbc317e847e8e1f4b53e57f1093b790b72
+size 2865362168

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:815321da0dc4eaf2c355cb86f5ab653e92c8cbd6cbdde61cd83b543279453763
+size 5368