{
  "_name_or_path": "/data/sc1_7b/",
  "architectures": [
    "MarkupDMForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_markupdm.MarkupDMConfig",
    "AutoModelForCausalLM": "modeling_markupdm.MarkupDMForCausalLM"
  },
  "freeze_text_embeddings": false,
  "image_loss_weight": 1.0,
  "image_pos_sigma": 10.0,
  "image_pos_size": 4,
  "image_size": 256,
  "initializer_range": 0.02,
  "is_decoder": true,
  "loss_type": "WeightedCausalLMLoss",
  "model_type": "markupdm",
  "text_model": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "bigcode/starcoderbase-7b",
    "activation_function": "gelu",
    "add_cross_attention": false,
    "architectures": [
      "GPTBigCodeForCausalLM"
    ],
    "attention_softmax_in_fp32": true,
    "attn_pdrop": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "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,
    "embd_pdrop": 0.1,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 0,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "inference_runner": 0,
    "initializer_range": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_epsilon": 1e-05,
    "length_penalty": 1.0,
    "max_batch_size": null,
    "max_length": 20,
    "max_sequence_length": null,
    "min_length": 0,
    "model_type": "gpt_bigcode",
    "multi_query": true,
    "n_embd": 4096,
    "n_head": 32,
    "n_inner": 16384,
    "n_layer": 42,
    "n_positions": 8192,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_key_length": true,
    "pad_token_id": null,
    "pre_allocate_kv_cache": false,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "resid_pdrop": 0.1,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_attention_softmax_in_fp32": true,
    "scale_attn_weights": true,
    "sep_token_id": null,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "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,
    "dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "validate_runner_input": true,
    "vocab_size": 49156
  },
  "dtype": "float32",
  "transformers_version": "4.47.1",
  "vision_model": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "cyberagent/ldm-vq-f16-rgba",
    "add_cross_attention": false,
    "architectures": [
      "VQModel"
    ],
    "auto_map": {
      "AutoConfig": "cyberagent/ldm-vq-f16-rgba--configuration_vqmodel.VQModelConfig",
      "AutoModel": "cyberagent/ldm-vq-f16-rgba--modeling_vqmodel.VQModel"
    },
    "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,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "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,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "vqmodel",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "repo_id": "cyberagent/ldm-vq-f16-rgba",
    "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,
    "dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "yaml_path": "config.yaml"
  },
  "vocab_size": 49156
}