config.json

{
  "architectures": [
    "Qwen2VLForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2_vl",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "paddlenlp_version": "3.0.0b2",
  "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,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attn_implementation": "eager",
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "context_parallel_degree": 1,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "depth": 32,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dtype": "float32",
    "early_stopping": false,
    "embed_dim": 1280,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "fuse_attention_ffn": false,
    "fuse_attention_qkv": false,
    "fuse_sequence_parallel_allreduce": false,
    "hidden_act": "quick_gelu",
    "hidden_size": 3584,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "in_channels": 3,
    "in_chans": 3,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4,
    "model_type": "qwen2_vl",
    "no_recompute_layers": null,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_choices": null,
    "num_heads": 16,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "pipeline_parallel_degree": 1,
    "pp_recompute_interval": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "quantization_config": {
      "act_quant_method": "abs_max",
      "llm_int8_threshold": 6.0,
      "quant_round_type": 0,
      "quant_type": null,
      "shift": false,
      "shift_smooth_all_linears": false,
      "smooth": false,
      "weight_blocksize": 64,
      "weight_double_quant": false,
      "weight_double_quant_block_size": 256,
      "weight_quant_method": "abs_max_channel_wise",
      "weight_quantize_algo": null
    },
    "recompute": false,
    "recompute_granularity": "full",
    "recompute_use_reentrant": false,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": false,
    "return_dict_in_generate": false,
    "sep_parallel_degree": 1,
    "sep_token_id": null,
    "sequence_parallel": false,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "temporal_patch_size": 2,
    "tensor_parallel_degree": 1,
    "tensor_parallel_output": true,
    "tensor_parallel_rank": 0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "use_cache": false,
    "use_flash_attention": false,
    "use_fused_dropout_add": false,
    "use_fused_linear": false,
    "use_fused_rms_norm": false,
    "use_fused_rope": false,
    "virtual_pp_degree": 1
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vocab_size": 152064
}