Upload VideoBlipForConditionalGeneration

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "/nfs/turbo/coe-chaijy/kpyu/eilev-checkpoints/eilev-blip2-flan-t5-xl-ego4d//",
+  "architectures": [
+    "VideoBlipForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bos_token_id": 1,
+    "classifier_dropout": 0.0,
+    "d_ff": 5120,
+    "d_kv": 64,
+    "d_model": 2048,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu",
+    "dropout_rate": 0.1,
+    "eos_token_id": 1,
+    "feed_forward_proj": "gated-gelu",
+    "initializer_factor": 1.0,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "n_positions": 512,
+    "num_decoder_layers": 24,
+    "num_heads": 32,
+    "num_layers": 24,
+    "output_past": true,
+    "pad_token_id": 0,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "vocab_size": 32128
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_decoder_only_language_model": false,
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a124f8de3561f00b86f8dfc17f67324e097357ca3ed13660f8a192dbb613862
+size 4978004864

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595ca8cb3f7c24a22343bf7a2047d469624f06b34cd0dab84e42d4ad7e7c1ad3
+size 4983312888

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb4139e3b8d4b5e620d3756c0850516f4d72d6d9fa78476e1f4d52c473a01ad
+size 4983337064

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ed407a0f17dbe6e345f65feb1a29095ee2e33d6e5096756186aae0fbd8bb58
+size 825299208