Training in progress, step 1768

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Salesforce/blip2-opt-2.7b",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "_name_or_path": "beomi/kykim-gpt3-kor-small_based_on_gpt2",
+    "activation_function": "gelu_new",
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bos_token_id": 3,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 3,
+    "gradient_checkpointing": false,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gpt2",
+    "n_ctx": 2048,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 2048,
+    "pad_token_id": null,
+    "reorder_and_upcast_attn": false,
+    "resid_pdrop": 0.1,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "vocab_size": 42000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe3bc2858b5a00a93f34b5fa3b130bcafdfa32062f739bd986fd16e2efbfad5
+size 4842467520

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6339a21b34644c86ad3b77dce16353de154467dcf78d87de112129ea019f77ba
+size 4664