configjson

config.json

@@ -0,0 +1,57 @@
+{
+ "_name_or_path": "Qwen/Qwen2-VL-72B-Instruct-315-fix-dim-pad",
+ "architectures": [
+ "Qwen2VLForConditionalGeneration"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151645,
+ "hidden_act": "silu",
+ "hidden_size": 8192,
+ "image_token_id": 151655,
+ "initializer_range": 0.02,
+ "intermediate_size": 29696,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 80,
+ "model_type": "qwen2_vl",
+ "num_attention_heads": 64,
+ "num_hidden_layers": 80,
+ "num_key_value_heads": 8,
+ "quantization_config": {
+ "bits": 4,
+ "group_size": 128,
+ "modules_to_not_convert": [
+ "visual"
+ ],
+ "quant_method": "awq",
+ "version": "gemm",
+ "zero_point": true
+ },
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": {
+ "mrope_section": [
+ 16,
+ 24,
+ 24
+ ],
+ "type": "mrope"
+ },
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.45.0.dev0",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "video_token_id": 151656,
+ "vision_config": {
+ "hidden_size": 8192,
+ "in_chans": 3,
+ "model_type": "qwen2_vl",
+ "spatial_patch_size": 14
+ },
+ "vision_end_token_id": 151653,
+ "vision_start_token_id": 151652,
+ "vision_token_id": 151654,
+ "vocab_size": 152064
+ }