Fine-tuning/result.txt

base) [root@localhost Fine-tuning]# docker exec finetune-backend cat /root/Fine-tuning/backend/data/models/Qwen/Qwen3.5-0.8B/config.json
{
    "architectures": [
        "Qwen3_5ForConditionalGeneration"
    ],
    "image_token_id": 248056,
    "model_type": "qwen3_5",
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_output_gate": true,
        "dtype": "bfloat16",
        "eos_token_id": 248044,
        "full_attention_interval": 4,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 3584,
        "layer_types": [
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention"
        ],
        "linear_conv_kernel_dim": 4,
        "linear_key_head_dim": 128,
        "linear_num_key_heads": 16,
        "linear_num_value_heads": 16,
        "linear_value_head_dim": 128,
        "max_position_embeddings": 262144,
        "mlp_only_layers": [],
        "model_type": "qwen3_5_text",
        "mtp_num_hidden_layers": 1,
        "mtp_use_dedicated_embeddings": false,
        "num_attention_heads": 8,
        "num_hidden_layers": 24,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "tie_word_embeddings": true,
        "use_cache": true,
        "vocab_size": 248320,
        "mamba_ssm_dtype": "float32",
        "rope_parameters": {
            "mrope_interleaved": true,
            "mrope_section": [
                11,
                11,
                10
            ],
            "rope_type": "default",
            "rope_theta": 10000000,
            "partial_rotary_factor": 0.25
        }
    },
    "tie_word_embeddings": true,
    "transformers_version": "4.57.0.dev0",
    "video_token_id": 248057,
    "vision_config": {
        "deepstack_visual_indexes": [],
        "depth": 12,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 768,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 3072,
        "model_type": "qwen3_5",
        "num_heads": 12,
        "num_position_embeddings": 2304,
        "out_hidden_size": 1024,
        "patch_size": 16,
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
}(base) [root@localhost Fine-tuning]#