config.json

{
  "_commit_hash": null,
  "architectures": [
    "NVLM_D"
  ],
  "auto_map": {
    "AutoConfig": "configuration_nvlm_d.NVLM_D_Config",
    "AutoModel": "modeling_nvlm_d.NVLM_D_Model",
    "AutoModelForCausalLM": "modeling_nvlm_d.NVLM_D_Model"
  },
  "downsample_ratio": 0.5,
  "dynamic_image_size": true,
  "force_image_size": 448,
  "llm_config": {
    "_name_or_path": "Qwen/Qwen2-72B-Instruct",
    "add_cross_attention": false,
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_bias": true,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 151643,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 151645,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "silu",
    "hidden_size": 8192,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 29568,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 32768,
    "min_length": 0,
    "mlp_bias": false,
    "model_type": "llama",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 64,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 80,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
      "factor": 3.0,
      "type": "dynamic"
    },
    "rope_theta": 1000000.0,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 1,
    "top_p": 0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "transformers_version": "4.39.3",
    "typical_p": 1.0,
    "use_bfloat16": true,
    "use_cache": true,
    "vocab_size": 152064
  },
  "max_dynamic_patch": 6,
  "min_dynamic_patch": 1,
  "model_type": "NVLM_D",
  "ps_version": "v2",
  "select_layer": -1,
  "template": "chatml",
  "torch_dtype": "bfloat16",
  "transformers_version": null,
  "use_backbone_lora": 0,
  "use_llm_lora": 0,
  "use_thumbnail": true,
  "vision_config": {
    "architectures": [
      "InternVisionModel"
    ],
    "attention_dropout": 0.0,
    "drop_path_rate": 0.0,
    "dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 3200,
    "image_size": 448,
    "initializer_factor": 0.1,
    "initializer_range": 1e-10,
    "intermediate_size": 12800,
    "layer_norm_eps": 1e-06,
    "model_type": "intern_vit_6b",
    "norm_type": "rms_norm",
    "num_attention_heads": 25,
    "num_channels": 3,
    "num_hidden_layers": 45,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 14,
    "qk_normalization": true,
    "qkv_bias": false,
    "return_dict": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.39.3",
    "use_bfloat16": true,
    "use_flash_attn": true
  }
}