model/config.json

{
    "_name_or_path": "qh360vl-8B",
    "architectures": [
      "QH360_VL_LlamaForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "modeling_360vl.QH360_VLConfig",
      "AutoModelForCausalLM": "modeling_360vl.QH360_VL_LlamaForCausalLM"
    },
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 128001,
    "freeze_mm_mlp_adapter": false,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "image_aspect_ratio": "pad",
    "image_grid_pinpoints": null,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 8192,
    "mm_hidden_size": 1024,
    "mm_num_tokens": 577,
    "mm_projector_config": "config.json",
    "mm_projector_lr": null,
    "mm_projector_type": "c-abs",
    "mm_use_im_patch_token": false,
    "mm_use_im_start_end": false,
    "mm_vision_select_feature": "patch",
    "mm_vision_select_layer": -2,
    "mm_vision_tower": "openai/clip-vit-large-patch14-336",
    "model_type": "QH_360VL",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "proj_2": true,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.37.2",
    "tune_mm_mlp_adapter": false,
    "use_cache": true,
    "use_mm_proj": true,
    "vocab_size": 128256,
    "visual_projector_config": {
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "attention_probs_dropout_prob": 0.1,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "depth": 3,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "early_stopping": false,
      "encoder_hidden_size": 1024,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "feature_layer_index": -2,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_size": 1024,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 4096,
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-06,
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "mlp_depth": 2,
      "model_type": "mllm_visual_projector",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 16,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_eos_tokens": 0,
      "num_hidden_layers": 6,
      "num_queries": 576,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "pos_emb": true,
      "prefix": null,
      "prenorm": false,
      "problem_type": null,
      "projector_type": "c-abs",
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "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": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "transformers_version": "4.30.2",
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_cls": true
    }
  }