Upload (#1)

- Upload (803f9cc8511fc02e123d47259ca4edc5e3fe04ea)

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_aspect_ratio": "square",
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1152,
+  "mm_projector_lr": null,
+  "mm_projector_type": "stc_connector_v35",
+  "mm_region_encoder_type": "pooling",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "model_type": "videorefer_qwen2",
+  "num_attention_heads": 28,
+  "num_frames": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "tune_mm_mlp_adapter": false,
+  "tune_region_encoder": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "vocab_size": 151647
+}

region_encoder.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135413a5f03d42f6baf1282a20463c6559ebe5df89311556afeeca730727de27
+size 33964168