config.json

{
  "attention": "self",
  "base_config": {
    "_name_or_path": "google/gemma-2b",
    "add_cross_attention": false,
    "architectures": [
      "GemmaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 2,
    "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": 1,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "head_dim": 128,
    "hidden_act": "gelu",
    "hidden_activation": "gelu_pytorch_tanh",
    "hidden_size": 3072,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 8192,
    "min_length": 0,
    "model_type": "gemma",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 24,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 18,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "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": null,
    "rope_theta": 10000.0,
    "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": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 256000
  },
  "dit_hidden_size": 3072,
  "dit_num_hidden_layers": 28,
  "in_channels": 16,
  "initial_layers": 0,
  "model_type": "DiT",
  "out_channels": 16,
  "patch_size": 2,
  "pos_embed": "ape",
  "pos_embed_max_size": 64,
  "qk_norm": true,
  "repa_enable": false,
  "repa_enc_depth": 4,
  "repa_projector_dim": 2048,
  "repa_z_dim": 768,
  "sample_size": 32,
  "sandwich_norm": false,
  "shared_attention_layers": "all",
  "text_hidden_size": 2048,
  "text_hidden_states_index": -1,
  "text_modulation_embeds_dim": null,
  "timestep_conditioning": null,
  "transformers_version": "4.43.3"
}