config.json

{
    "architectures": [
        "Qwen2VLForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 1536,
    "image_token_id": 151655,
    "initializer_range": 0.02,
    "intermediate_size": 8960,
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "model_type": "qwen2_vl",
    "num_attention_heads": 12,
    "num_hidden_layers": 28,
    "num_key_value_heads": 2,
    "pad_token_id": 151654,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
        "mrope_section": [
            16,
            24,
            24
        ],
        "rope_type": "default",
        "type": "default"
    },
    "rope_theta": 1000000.0,
    "sliding_window": 32768,
    "text_config": {
        "_name_or_path": "unsloth/Qwen2-VL-2B-Instruct",
        "architectures": [
            "Qwen2VLForConditionalGeneration"
        ],
        "attention_dropout": 0.0,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 1536,
        "image_token_id": null,
        "initializer_range": 0.02,
        "intermediate_size": 8960,
        "layer_types": [
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention",
            "full_attention"
        ],
        "max_position_embeddings": 32768,
        "max_window_layers": 28,
        "model_type": "qwen2_vl_text",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 2,
        "pad_token_id": 151654,
        "quantization_config": {
            "_load_in_4bit": true,
            "_load_in_8bit": false,
            "bnb_4bit_compute_dtype": "bfloat16",
            "bnb_4bit_quant_storage": "uint8",
            "bnb_4bit_quant_type": "nf4",
            "bnb_4bit_use_double_quant": true,
            "llm_int8_enable_fp32_cpu_offload": false,
            "llm_int8_has_fp16_weight": false,
            "llm_int8_skip_modules": [
                "lm_head",
                "multi_modal_projector",
                "merger",
                "modality_projection"
            ],
            "llm_int8_threshold": 6.0,
            "load_in_4bit": true,
            "load_in_8bit": false,
            "quant_method": "bitsandbytes"
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
            "mrope_section": [
                16,
                24,
                24
            ],
            "rope_type": "default",
            "type": "default"
        },
        "rope_theta": 1000000.0,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "unsloth_fixed": true,
        "use_cache": true,
        "use_sliding_window": false,
        "video_token_id": null,
        "vision_end_token_id": 151653,
        "vision_start_token_id": 151652,
        "vision_token_id": 151654,
        "vocab_size": 151936
    },
    "torch_dtype": "bfloat16",
    "transformers_version": "4.55.4",
    "unsloth_fixed": true,
    "unsloth_version": "2025.9.11",
    "use_cache": true,
    "use_sliding_window": false,
    "video_token_id": 151656,
    "vision_config": {
        "depth": 32,
        "embed_dim": 1280,
        "hidden_act": "quick_gelu",
        "hidden_size": 1536,
        "in_channels": 3,
        "in_chans": 3,
        "initializer_range": 0.02,
        "mlp_ratio": 4,
        "model_type": "qwen2_vl",
        "num_heads": 16,
        "patch_size": 14,
        "spatial_merge_size": 2,
        "spatial_patch_size": 14,
        "temporal_patch_size": 2,
        "torch_dtype": "bfloat16"
    },
    "vision_end_token_id": 151653,
    "vision_start_token_id": 151652,
    "vision_token_id": 151654,
    "vocab_size": 151936
}