Add files

config.json

@@ -1,48 +1,69 @@
 {
-    "model_type": "llava",
-    "architectures": ["LLaVAForVideoClassification"], 
-    "learning_rate": 5e-05,
-    "train_batch_size": 2,
-    "eval_batch_size": 8,
-    "seed": 42,
-    "distributed_type": "multi-GPU",
-    "num_devices": 2,
-    "gradient_accumulation_steps": 8,
-    "total_train_batch_size": 32,
-    "total_eval_batch_size": 16,
-    "optimizer": "AdamW_Torch",
-    "betas": [0.9, 0.999],
-    "epsilon": 1e-08,
-    "lr_scheduler_type": "cosine",
-    "lr_scheduler_warmup_steps": 100,
-    "num_epochs": 1.0,
-    "framework_versions": {
-      "PEFT": "0.12.0",
-      "Transformers": "4.46.1",
-      "Pytorch": "2.3.1+cu121",
-      "Datasets": "3.1.0",
-      "Tokenizers": "0.20.3"
+  "architectures": [
+    "LlavaNextVideoForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_token_index": 32001,
+  "model_type": "llava_next_video",
+  "projector_hidden_act": "gelu",
+  "spatial_pool_mode": "average",
+  "spatial_pool_out_channels": 1024,
+  "spatial_pool_stride": 2,
+  "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "rope_scaling" : {
+      "factor": 2.5,
+      "type": "linear"
     },
-    "description": "This model is a fine-tuned version of llava-hf/LLaVA-NeXT-Video-7B-hf on the merger, the LLM_dataset(4o) and the LLM_dataset(4mini) datasets.",
-    "training_data": {
-      "dataset_names": ["merger", "LLM_dataset(4o)", "LLM_dataset(4mini)"]
-    },
-    "training_hyperparameters": {
-      "learning_rate": 5e-05,
-      "train_batch_size": 2,
-      "eval_batch_size": 8,
-      "seed": 42,
-      "distributed_type": "multi-GPU",
-      "num_devices": 2,
-      "gradient_accumulation_steps": 8,
-      "total_train_batch_size": 32,
-      "total_eval_batch_size": 16,
-      "optimizer": "AdamW_Torch",
-      "betas": [0.9, 0.999],
-      "epsilon": 1e-08,
-      "lr_scheduler_type": "cosine",
-      "lr_scheduler_warmup_steps": 100,
-      "num_epochs": 1.0
-    }
-  }
-  
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "torch_dtype": "float16",
+    "type": "linear",
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0.dev0",
+  "use_image_newline_parameter": true,
+  "video_token_index": 32000,
+  "vision_config": {
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc32753ce8e75e89748b95677d9349d2b47af998457b4ebe22d27dece7338a3d
+size 4992938952

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c50112e9dffcb204f90a5be738d28e33b92cd14332cabde6e8f39171d999a1b
+size 4957878552

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8022077b98e08236a07b999f1f51ab577bda9c8aa2dc66d12853b1b162731100
+size 4176137496