Upload rebuttal-004-llava-next-video-7b-dapo-v2-ckpt_229/config.json with huggingface_hub

rebuttal-004-llava-next-video-7b-dapo-v2-ckpt_229/config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "LlavaNextVideoForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      336,
+      1008
+    ]
+  ],
+  "image_seq_length": 576,
+  "image_token_index": 32001,
+  "model_type": "llava_next_video",
+  "multimodal_projector_bias": true,
+  "pad_token_id": 0,
+  "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"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 2.5,
+      "rope_type": "linear",
+      "type": "linear"
+    },
+    "rope_theta": 10000.0,
+    "type": "linear",
+    "use_cache": true,
+    "vocab_size": 32064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_image_newline_parameter": true,
+  "video_seq_length": 288,
+  "video_token_index": 32000,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "vocab_size": 32000
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default"
+}