{ "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--Qwen--Qwen2-VL-72B-Instruct/snapshots/f400120e59a6196b024298b7d09fb517f742db7d", "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": 29568, "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": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": 1.3357104612400095, "ignore": [ "visual.blocks.0.attn.qkv", "visual.blocks.0.attn.proj", "visual.blocks.0.mlp.fc1", "visual.blocks.0.mlp.fc2", "visual.blocks.1.attn.qkv", "visual.blocks.1.attn.proj", "visual.blocks.1.mlp.fc1", "visual.blocks.1.mlp.fc2", "visual.blocks.2.attn.qkv", "visual.blocks.2.attn.proj", "visual.blocks.2.mlp.fc1", "visual.blocks.2.mlp.fc2", "visual.blocks.3.attn.qkv", "visual.blocks.3.attn.proj", "visual.blocks.3.mlp.fc1", "visual.blocks.3.mlp.fc2", "visual.blocks.4.attn.qkv", "visual.blocks.4.attn.proj", "visual.blocks.4.mlp.fc1", "visual.blocks.4.mlp.fc2", "visual.blocks.5.attn.qkv", "visual.blocks.5.attn.proj", "visual.blocks.5.mlp.fc1", "visual.blocks.5.mlp.fc2", "visual.blocks.6.attn.qkv", "visual.blocks.6.attn.proj", "visual.blocks.6.mlp.fc1", "visual.blocks.6.mlp.fc2", "visual.blocks.7.attn.qkv", "visual.blocks.7.attn.proj", "visual.blocks.7.mlp.fc1", "visual.blocks.7.mlp.fc2", "visual.blocks.8.attn.qkv", "visual.blocks.8.attn.proj", "visual.blocks.8.mlp.fc1", "visual.blocks.8.mlp.fc2", "visual.blocks.9.attn.qkv", "visual.blocks.9.attn.proj", "visual.blocks.9.mlp.fc1", "visual.blocks.9.mlp.fc2", "visual.blocks.10.attn.qkv", "visual.blocks.10.attn.proj", "visual.blocks.10.mlp.fc1", "visual.blocks.10.mlp.fc2", "visual.blocks.11.attn.qkv", "visual.blocks.11.attn.proj", "visual.blocks.11.mlp.fc1", "visual.blocks.11.mlp.fc2", "visual.blocks.12.attn.qkv", "visual.blocks.12.attn.proj", "visual.blocks.12.mlp.fc1", "visual.blocks.12.mlp.fc2", "visual.blocks.13.attn.qkv", "visual.blocks.13.attn.proj", "visual.blocks.13.mlp.fc1", "visual.blocks.13.mlp.fc2", "visual.blocks.14.attn.qkv", "visual.blocks.14.attn.proj", "visual.blocks.14.mlp.fc1", "visual.blocks.14.mlp.fc2", "visual.blocks.15.attn.qkv", "visual.blocks.15.attn.proj", "visual.blocks.15.mlp.fc1", "visual.blocks.15.mlp.fc2", "visual.blocks.16.attn.qkv", "visual.blocks.16.attn.proj", "visual.blocks.16.mlp.fc1", "visual.blocks.16.mlp.fc2", "visual.blocks.17.attn.qkv", "visual.blocks.17.attn.proj", "visual.blocks.17.mlp.fc1", "visual.blocks.17.mlp.fc2", "visual.blocks.18.attn.qkv", "visual.blocks.18.attn.proj", "visual.blocks.18.mlp.fc1", "visual.blocks.18.mlp.fc2", "visual.blocks.19.attn.qkv", "visual.blocks.19.attn.proj", "visual.blocks.19.mlp.fc1", "visual.blocks.19.mlp.fc2", "visual.blocks.20.attn.qkv", "visual.blocks.20.attn.proj", "visual.blocks.20.mlp.fc1", "visual.blocks.20.mlp.fc2", "visual.blocks.21.attn.qkv", "visual.blocks.21.attn.proj", "visual.blocks.21.mlp.fc1", "visual.blocks.21.mlp.fc2", "visual.blocks.22.attn.qkv", "visual.blocks.22.attn.proj", "visual.blocks.22.mlp.fc1", "visual.blocks.22.mlp.fc2", "visual.blocks.23.attn.qkv", "visual.blocks.23.attn.proj", "visual.blocks.23.mlp.fc1", "visual.blocks.23.mlp.fc2", "visual.blocks.24.attn.qkv", "visual.blocks.24.attn.proj", "visual.blocks.24.mlp.fc1", "visual.blocks.24.mlp.fc2", "visual.blocks.25.attn.qkv", "visual.blocks.25.attn.proj", "visual.blocks.25.mlp.fc1", "visual.blocks.25.mlp.fc2", "visual.blocks.26.attn.qkv", "visual.blocks.26.attn.proj", "visual.blocks.26.mlp.fc1", "visual.blocks.26.mlp.fc2", "visual.blocks.27.attn.qkv", "visual.blocks.27.attn.proj", "visual.blocks.27.mlp.fc1", "visual.blocks.27.mlp.fc2", "visual.blocks.28.attn.qkv", "visual.blocks.28.attn.proj", "visual.blocks.28.mlp.fc1", "visual.blocks.28.mlp.fc2", "visual.blocks.29.attn.qkv", "visual.blocks.29.attn.proj", "visual.blocks.29.mlp.fc1", "visual.blocks.29.mlp.fc2", "visual.blocks.30.attn.qkv", "visual.blocks.30.attn.proj", "visual.blocks.30.mlp.fc1", "visual.blocks.30.mlp.fc2", "visual.blocks.31.attn.qkv", "visual.blocks.31.attn.proj", "visual.blocks.31.mlp.fc1", "visual.blocks.31.mlp.fc2", "visual.merger.mlp.0", "visual.merger.mlp.2", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "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 }