Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,880 @@
+{
+  "_name_or_path": "/share/LXRlxr0_0/code/Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "beacon_accum": true,
+  "beacon_attend_prev": true,
+  "beacon_attn": "full-coverage",
+  "beacon_embed_init": "eos",
+  "beacon_parallel_window": 1,
+  "beacon_param": [
+    "q",
+    "k",
+    "v"
+  ],
+  "beacon_pos": "interleave",
+  "beacon_ratio": [
+    2,
+    4,
+    8
+  ],
+  "beacon_ratio_mix": "step-random",
+  "beacon_sink_size": 0,
+  "beacon_stride": 1440,
+  "beacon_window": 1440,
+  "bos_token_id": 151643,
+  "enable_beacon": true,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "anyres",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      336,
+      1008
+    ],
+    [
+      336,
+      1344
+    ],
+    [
+      336,
+      1680
+    ],
+    [
+      336,
+      2016
+    ],
+    [
+      336,
+      2352
+    ],
+    [
+      336,
+      2688
+    ],
+    [
+      336,
+      3024
+    ],
+    [
+      336,
+      3360
+    ],
+    [
+      336,
+      3696
+    ],
+    [
+      336,
+      4032
+    ],
+    [
+      336,
+      4368
+    ],
+    [
+      336,
+      4704
+    ],
+    [
+      336,
+      5040
+    ],
+    [
+      336,
+      5376
+    ],
+    [
+      336,
+      5712
+    ],
+    [
+      336,
+      6048
+    ],
+    [
+      336,
+      6384
+    ],
+    [
+      336,
+      6720
+    ],
+    [
+      336,
+      7056
+    ],
+    [
+      336,
+      7392
+    ],
+    [
+      336,
+      7728
+    ],
+    [
+      336,
+      8064
+    ],
+    [
+      336,
+      8400
+    ],
+    [
+      336,
+      8736
+    ],
+    [
+      336,
+      9072
+    ],
+    [
+      336,
+      9408
+    ],
+    [
+      336,
+      9744
+    ],
+    [
+      336,
+      10080
+    ],
+    [
+      336,
+      10416
+    ],
+    [
+      336,
+      10752
+    ],
+    [
+      336,
+      11088
+    ],
+    [
+      336,
+      11424
+    ],
+    [
+      336,
+      11760
+    ],
+    [
+      336,
+      12096
+    ],
+    [
+      336,
+      12432
+    ],
+    [
+      336,
+      12768
+    ],
+    [
+      336,
+      13104
+    ],
+    [
+      336,
+      13440
+    ],
+    [
+      336,
+      13776
+    ],
+    [
+      336,
+      14112
+    ],
+    [
+      336,
+      14448
+    ],
+    [
+      336,
+      14784
+    ],
+    [
+      336,
+      15120
+    ],
+    [
+      336,
+      15456
+    ],
+    [
+      336,
+      15792
+    ],
+    [
+      336,
+      16128
+    ],
+    [
+      336,
+      16464
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      672,
+      1008
+    ],
+    [
+      672,
+      1344
+    ],
+    [
+      672,
+      1680
+    ],
+    [
+      672,
+      2016
+    ],
+    [
+      672,
+      2352
+    ],
+    [
+      672,
+      2688
+    ],
+    [
+      672,
+      3024
+    ],
+    [
+      672,
+      3360
+    ],
+    [
+      672,
+      3696
+    ],
+    [
+      672,
+      4032
+    ],
+    [
+      672,
+      4368
+    ],
+    [
+      672,
+      4704
+    ],
+    [
+      672,
+      5040
+    ],
+    [
+      672,
+      5376
+    ],
+    [
+      672,
+      5712
+    ],
+    [
+      672,
+      6048
+    ],
+    [
+      672,
+      6384
+    ],
+    [
+      672,
+      6720
+    ],
+    [
+      672,
+      7056
+    ],
+    [
+      672,
+      7392
+    ],
+    [
+      672,
+      7728
+    ],
+    [
+      672,
+      8064
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      1008,
+      672
+    ],
+    [
+      1008,
+      1008
+    ],
+    [
+      1008,
+      1344
+    ],
+    [
+      1008,
+      1680
+    ],
+    [
+      1008,
+      2016
+    ],
+    [
+      1008,
+      2352
+    ],
+    [
+      1008,
+      2688
+    ],
+    [
+      1008,
+      3024
+    ],
+    [
+      1008,
+      3360
+    ],
+    [
+      1008,
+      3696
+    ],
+    [
+      1008,
+      4032
+    ],
+    [
+      1008,
+      4368
+    ],
+    [
+      1008,
+      4704
+    ],
+    [
+      1008,
+      5040
+    ],
+    [
+      1008,
+      5376
+    ],
+    [
+      1344,
+      336
+    ],
+    [
+      1344,
+      672
+    ],
+    [
+      1344,
+      1008
+    ],
+    [
+      1344,
+      1344
+    ],
+    [
+      1344,
+      1680
+    ],
+    [
+      1344,
+      2016
+    ],
+    [
+      1344,
+      2352
+    ],
+    [
+      1344,
+      2688
+    ],
+    [
+      1344,
+      3024
+    ],
+    [
+      1344,
+      3360
+    ],
+    [
+      1344,
+      3696
+    ],
+    [
+      1344,
+      4032
+    ],
+    [
+      1680,
+      336
+    ],
+    [
+      1680,
+      672
+    ],
+    [
+      1680,
+      1008
+    ],
+    [
+      1680,
+      1344
+    ],
+    [
+      1680,
+      1680
+    ],
+    [
+      1680,
+      2016
+    ],
+    [
+      1680,
+      2352
+    ],
+    [
+      1680,
+      2688
+    ],
+    [
+      1680,
+      3024
+    ],
+    [
+      2016,
+      336
+    ],
+    [
+      2016,
+      672
+    ],
+    [
+      2016,
+      1008
+    ],
+    [
+      2016,
+      1344
+    ],
+    [
+      2016,
+      1680
+    ],
+    [
+      2016,
+      2016
+    ],
+    [
+      2016,
+      2352
+    ],
+    [
+      2016,
+      2688
+    ],
+    [
+      2352,
+      336
+    ],
+    [
+      2352,
+      672
+    ],
+    [
+      2352,
+      1008
+    ],
+    [
+      2352,
+      1344
+    ],
+    [
+      2352,
+      1680
+    ],
+    [
+      2352,
+      2016
+    ],
+    [
+      2352,
+      2352
+    ],
+    [
+      2688,
+      336
+    ],
+    [
+      2688,
+      672
+    ],
+    [
+      2688,
+      1008
+    ],
+    [
+      2688,
+      1344
+    ],
+    [
+      2688,
+      1680
+    ],
+    [
+      2688,
+      2016
+    ],
+    [
+      3024,
+      336
+    ],
+    [
+      3024,
+      672
+    ],
+    [
+      3024,
+      1008
+    ],
+    [
+      3024,
+      1344
+    ],
+    [
+      3024,
+      1680
+    ],
+    [
+      3360,
+      336
+    ],
+    [
+      3360,
+      672
+    ],
+    [
+      3360,
+      1008
+    ],
+    [
+      3360,
+      1344
+    ],
+    [
+      3696,
+      336
+    ],
+    [
+      3696,
+      672
+    ],
+    [
+      3696,
+      1008
+    ],
+    [
+      3696,
+      1344
+    ],
+    [
+      4032,
+      336
+    ],
+    [
+      4032,
+      672
+    ],
+    [
+      4032,
+      1008
+    ],
+    [
+      4032,
+      1344
+    ],
+    [
+      4368,
+      336
+    ],
+    [
+      4368,
+      672
+    ],
+    [
+      4368,
+      1008
+    ],
+    [
+      4704,
+      336
+    ],
+    [
+      4704,
+      672
+    ],
+    [
+      4704,
+      1008
+    ],
+    [
+      5040,
+      336
+    ],
+    [
+      5040,
+      672
+    ],
+    [
+      5040,
+      1008
+    ],
+    [
+      5376,
+      336
+    ],
+    [
+      5376,
+      672
+    ],
+    [
+      5376,
+      1008
+    ],
+    [
+      5712,
+      336
+    ],
+    [
+      5712,
+      672
+    ],
+    [
+      6048,
+      336
+    ],
+    [
+      6048,
+      672
+    ],
+    [
+      6384,
+      336
+    ],
+    [
+      6384,
+      672
+    ],
+    [
+      6720,
+      336
+    ],
+    [
+      6720,
+      672
+    ],
+    [
+      7056,
+      336
+    ],
+    [
+      7056,
+      672
+    ],
+    [
+      7392,
+      336
+    ],
+    [
+      7392,
+      672
+    ],
+    [
+      7728,
+      336
+    ],
+    [
+      7728,
+      672
+    ],
+    [
+      8064,
+      336
+    ],
+    [
+      8064,
+      672
+    ],
+    [
+      8400,
+      336
+    ],
+    [
+      8736,
+      336
+    ],
+    [
+      9072,
+      336
+    ],
+    [
+      9408,
+      336
+    ],
+    [
+      9744,
+      336
+    ],
+    [
+      10080,
+      336
+    ],
+    [
+      10416,
+      336
+    ],
+    [
+      10752,
+      336
+    ],
+    [
+      11088,
+      336
+    ],
+    [
+      11424,
+      336
+    ],
+    [
+      11760,
+      336
+    ],
+    [
+      12096,
+      336
+    ],
+    [
+      12432,
+      336
+    ],
+    [
+      12768,
+      336
+    ],
+    [
+      13104,
+      336
+    ],
+    [
+      13440,
+      336
+    ],
+    [
+      13776,
+      336
+    ],
+    [
+      14112,
+      336
+    ],
+    [
+      14448,
+      336
+    ],
+    [
+      14784,
+      336
+    ],
+    [
+      15120,
+      336
+    ],
+    [
+      15456,
+      336
+    ],
+    [
+      15792,
+      336
+    ],
+    [
+      16128,
+      336
+    ],
+    [
+      16464,
+      336
+    ]
+  ],
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "mm_hidden_size": 1152,
+  "mm_patch_merge_type": "unires",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": "spatial_pool",
+  "mm_spatial_pool_mode": "average",
+  "mm_spatial_pool_out_channels": 1152,
+  "mm_spatial_pool_stride": 2,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "/share/LXRlxr0_0/code/videoxlturbo2.0/videoxl/google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 151936
+}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,880 @@
+{
+  "_name_or_path": "/share/LXRlxr0_0/code/Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "beacon_accum": true,
+  "beacon_attend_prev": true,
+  "beacon_attn": "full-coverage",
+  "beacon_embed_init": "eos",
+  "beacon_parallel_window": 1,
+  "beacon_param": [
+    "q",
+    "k",
+    "v"
+  ],
+  "beacon_pos": "interleave",
+  "beacon_ratio": [
+    2,
+    4,
+    8
+  ],
+  "beacon_ratio_mix": "step-random",
+  "beacon_sink_size": 0,
+  "beacon_stride": 1440,
+  "beacon_window": 1440,
+  "bos_token_id": 151643,
+  "enable_beacon": true,
+  "eos_token_id": 151645,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_aspect_ratio": "anyres",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      336,
+      672
+    ],
+    [
+      336,
+      1008
+    ],
+    [
+      336,
+      1344
+    ],
+    [
+      336,
+      1680
+    ],
+    [
+      336,
+      2016
+    ],
+    [
+      336,
+      2352
+    ],
+    [
+      336,
+      2688
+    ],
+    [
+      336,
+      3024
+    ],
+    [
+      336,
+      3360
+    ],
+    [
+      336,
+      3696
+    ],
+    [
+      336,
+      4032
+    ],
+    [
+      336,
+      4368
+    ],
+    [
+      336,
+      4704
+    ],
+    [
+      336,
+      5040
+    ],
+    [
+      336,
+      5376
+    ],
+    [
+      336,
+      5712
+    ],
+    [
+      336,
+      6048
+    ],
+    [
+      336,
+      6384
+    ],
+    [
+      336,
+      6720
+    ],
+    [
+      336,
+      7056
+    ],
+    [
+      336,
+      7392
+    ],
+    [
+      336,
+      7728
+    ],
+    [
+      336,
+      8064
+    ],
+    [
+      336,
+      8400
+    ],
+    [
+      336,
+      8736
+    ],
+    [
+      336,
+      9072
+    ],
+    [
+      336,
+      9408
+    ],
+    [
+      336,
+      9744
+    ],
+    [
+      336,
+      10080
+    ],
+    [
+      336,
+      10416
+    ],
+    [
+      336,
+      10752
+    ],
+    [
+      336,
+      11088
+    ],
+    [
+      336,
+      11424
+    ],
+    [
+      336,
+      11760
+    ],
+    [
+      336,
+      12096
+    ],
+    [
+      336,
+      12432
+    ],
+    [
+      336,
+      12768
+    ],
+    [
+      336,
+      13104
+    ],
+    [
+      336,
+      13440
+    ],
+    [
+      336,
+      13776
+    ],
+    [
+      336,
+      14112
+    ],
+    [
+      336,
+      14448
+    ],
+    [
+      336,
+      14784
+    ],
+    [
+      336,
+      15120
+    ],
+    [
+      336,
+      15456
+    ],
+    [
+      336,
+      15792
+    ],
+    [
+      336,
+      16128
+    ],
+    [
+      336,
+      16464
+    ],
+    [
+      672,
+      336
+    ],
+    [
+      672,
+      672
+    ],
+    [
+      672,
+      1008
+    ],
+    [
+      672,
+      1344
+    ],
+    [
+      672,
+      1680
+    ],
+    [
+      672,
+      2016
+    ],
+    [
+      672,
+      2352
+    ],
+    [
+      672,
+      2688
+    ],
+    [
+      672,
+      3024
+    ],
+    [
+      672,
+      3360
+    ],
+    [
+      672,
+      3696
+    ],
+    [
+      672,
+      4032
+    ],
+    [
+      672,
+      4368
+    ],
+    [
+      672,
+      4704
+    ],
+    [
+      672,
+      5040
+    ],
+    [
+      672,
+      5376
+    ],
+    [
+      672,
+      5712
+    ],
+    [
+      672,
+      6048
+    ],
+    [
+      672,
+      6384
+    ],
+    [
+      672,
+      6720
+    ],
+    [
+      672,
+      7056
+    ],
+    [
+      672,
+      7392
+    ],
+    [
+      672,
+      7728
+    ],
+    [
+      672,
+      8064
+    ],
+    [
+      1008,
+      336
+    ],
+    [
+      1008,
+      672
+    ],
+    [
+      1008,
+      1008
+    ],
+    [
+      1008,
+      1344
+    ],
+    [
+      1008,
+      1680
+    ],
+    [
+      1008,
+      2016
+    ],
+    [
+      1008,
+      2352
+    ],
+    [
+      1008,
+      2688
+    ],
+    [
+      1008,
+      3024
+    ],
+    [
+      1008,
+      3360
+    ],
+    [
+      1008,
+      3696
+    ],
+    [
+      1008,
+      4032
+    ],
+    [
+      1008,
+      4368
+    ],
+    [
+      1008,
+      4704
+    ],
+    [
+      1008,
+      5040
+    ],
+    [
+      1008,
+      5376
+    ],
+    [
+      1344,
+      336
+    ],
+    [
+      1344,
+      672
+    ],
+    [
+      1344,
+      1008
+    ],
+    [
+      1344,
+      1344
+    ],
+    [
+      1344,
+      1680
+    ],
+    [
+      1344,
+      2016
+    ],
+    [
+      1344,
+      2352
+    ],
+    [
+      1344,
+      2688
+    ],
+    [
+      1344,
+      3024
+    ],
+    [
+      1344,
+      3360
+    ],
+    [
+      1344,
+      3696
+    ],
+    [
+      1344,
+      4032
+    ],
+    [
+      1680,
+      336
+    ],
+    [
+      1680,
+      672
+    ],
+    [
+      1680,
+      1008
+    ],
+    [
+      1680,
+      1344
+    ],
+    [
+      1680,
+      1680
+    ],
+    [
+      1680,
+      2016
+    ],
+    [
+      1680,
+      2352
+    ],
+    [
+      1680,
+      2688
+    ],
+    [
+      1680,
+      3024
+    ],
+    [
+      2016,
+      336
+    ],
+    [
+      2016,
+      672
+    ],
+    [
+      2016,
+      1008
+    ],
+    [
+      2016,
+      1344
+    ],
+    [
+      2016,
+      1680
+    ],
+    [
+      2016,
+      2016
+    ],
+    [
+      2016,
+      2352
+    ],
+    [
+      2016,
+      2688
+    ],
+    [
+      2352,
+      336
+    ],
+    [
+      2352,
+      672
+    ],
+    [
+      2352,
+      1008
+    ],
+    [
+      2352,
+      1344
+    ],
+    [
+      2352,
+      1680
+    ],
+    [
+      2352,
+      2016
+    ],
+    [
+      2352,
+      2352
+    ],
+    [
+      2688,
+      336
+    ],
+    [
+      2688,
+      672
+    ],
+    [
+      2688,
+      1008
+    ],
+    [
+      2688,
+      1344
+    ],
+    [
+      2688,
+      1680
+    ],
+    [
+      2688,
+      2016
+    ],
+    [
+      3024,
+      336
+    ],
+    [
+      3024,
+      672
+    ],
+    [
+      3024,
+      1008
+    ],
+    [
+      3024,
+      1344
+    ],
+    [
+      3024,
+      1680
+    ],
+    [
+      3360,
+      336
+    ],
+    [
+      3360,
+      672
+    ],
+    [
+      3360,
+      1008
+    ],
+    [
+      3360,
+      1344
+    ],
+    [
+      3696,
+      336
+    ],
+    [
+      3696,
+      672
+    ],
+    [
+      3696,
+      1008
+    ],
+    [
+      3696,
+      1344
+    ],
+    [
+      4032,
+      336
+    ],
+    [
+      4032,
+      672
+    ],
+    [
+      4032,
+      1008
+    ],
+    [
+      4032,
+      1344
+    ],
+    [
+      4368,
+      336
+    ],
+    [
+      4368,
+      672
+    ],
+    [
+      4368,
+      1008
+    ],
+    [
+      4704,
+      336
+    ],
+    [
+      4704,
+      672
+    ],
+    [
+      4704,
+      1008
+    ],
+    [
+      5040,
+      336
+    ],
+    [
+      5040,
+      672
+    ],
+    [
+      5040,
+      1008
+    ],
+    [
+      5376,
+      336
+    ],
+    [
+      5376,
+      672
+    ],
+    [
+      5376,
+      1008
+    ],
+    [
+      5712,
+      336
+    ],
+    [
+      5712,
+      672
+    ],
+    [
+      6048,
+      336
+    ],
+    [
+      6048,
+      672
+    ],
+    [
+      6384,
+      336
+    ],
+    [
+      6384,
+      672
+    ],
+    [
+      6720,
+      336
+    ],
+    [
+      6720,
+      672
+    ],
+    [
+      7056,
+      336
+    ],
+    [
+      7056,
+      672
+    ],
+    [
+      7392,
+      336
+    ],
+    [
+      7392,
+      672
+    ],
+    [
+      7728,
+      336
+    ],
+    [
+      7728,
+      672
+    ],
+    [
+      8064,
+      336
+    ],
+    [
+      8064,
+      672
+    ],
+    [
+      8400,
+      336
+    ],
+    [
+      8736,
+      336
+    ],
+    [
+      9072,
+      336
+    ],
+    [
+      9408,
+      336
+    ],
+    [
+      9744,
+      336
+    ],
+    [
+      10080,
+      336
+    ],
+    [
+      10416,
+      336
+    ],
+    [
+      10752,
+      336
+    ],
+    [
+      11088,
+      336
+    ],
+    [
+      11424,
+      336
+    ],
+    [
+      11760,
+      336
+    ],
+    [
+      12096,
+      336
+    ],
+    [
+      12432,
+      336
+    ],
+    [
+      12768,
+      336
+    ],
+    [
+      13104,
+      336
+    ],
+    [
+      13440,
+      336
+    ],
+    [
+      13776,
+      336
+    ],
+    [
+      14112,
+      336
+    ],
+    [
+      14448,
+      336
+    ],
+    [
+      14784,
+      336
+    ],
+    [
+      15120,
+      336
+    ],
+    [
+      15456,
+      336
+    ],
+    [
+      15792,
+      336
+    ],
+    [
+      16128,
+      336
+    ],
+    [
+      16464,
+      336
+    ]
+  ],
+  "image_split_resolution": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "mm_hidden_size": 1152,
+  "mm_patch_merge_type": "unires",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": "spatial_pool",
+  "mm_spatial_pool_mode": "average",
+  "mm_spatial_pool_out_channels": 1152,
+  "mm_spatial_pool_stride": 2,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -1,
+  "mm_vision_tower": "/share/LXRlxr0_0/code/videoxlturbo2.0/videoxl_adaptfps/google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": null,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.43.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482a5114f34c14d352dc9765e39c755cd3c27bd8efc4bc42886c8fdd699a5543
+size 4977615904

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e8e43de53317dbe90e98a2e51554edc1cb4cdfbbf0d7f00a59f011e56f1438
+size 3198470440

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fdc26965f066ea3a3653fe2cb89637260eb67c664cc2a8c6fae40eeaa9fbc6
+size 7352