config.json

{
   "vocab_size": 151665,
   "max_position_embeddings": 32768,
   "hidden_size": 896,
   "intermediate_size": 4864,
   "num_hidden_layers": 24,
   "num_attention_heads": 14,
   "use_sliding_window": false,
   "sliding_window": 32768,
   "max_window_layers": 21,
   "num_key_value_heads": 2,
   "hidden_act": "silu",
   "initializer_range": 0.02,
   "rms_norm_eps": 1e-06,
   "use_cache": false,
   "rope_theta": 1000000.0,
   "attention_dropout": 0.0,
   "return_dict": true,
   "output_hidden_states": false,
   "output_attentions": false,
   "torchscript": false,
   "torch_dtype": "bfloat16",
   "use_bfloat16": false,
   "tf_legacy_loss": false,
   "pruned_heads": {},
   "tie_word_embeddings": true,
   "chunk_size_feed_forward": 0,
   "is_encoder_decoder": false,
   "is_decoder": false,
   "cross_attention_hidden_size": null,
   "add_cross_attention": false,
   "tie_encoder_decoder": false,
   "max_length": 20,
   "min_length": 0,
   "do_sample": false,
   "early_stopping": false,
   "num_beams": 1,
   "num_beam_groups": 1,
   "diversity_penalty": 0.0,
   "temperature": 1.0,
   "top_k": 50,
   "top_p": 1.0,
   "typical_p": 1.0,
   "repetition_penalty": 1.0,
   "length_penalty": 1.0,
   "no_repeat_ngram_size": 0,
   "encoder_no_repeat_ngram_size": 0,
   "bad_words_ids": null,
   "num_return_sequences": 1,
   "output_scores": false,
   "return_dict_in_generate": false,
   "forced_bos_token_id": null,
   "forced_eos_token_id": null,
   "remove_invalid_values": false,
   "exponential_decay_length_penalty": null,
   "suppress_tokens": null,
   "begin_suppress_tokens": null,
   "architectures": [
      "BunnyQwen2ForCausalLM"
   ],
   "finetuning_task": null,
   "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
   },
   "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
   },
   "tokenizer_class": null,
   "prefix": null,
   "bos_token_id": 151643,
   "pad_token_id": null,
   "eos_token_id": 151645,
   "sep_token_id": null,
   "decoder_start_token_id": null,
   "task_specific_params": null,
   "problem_type": null,
   "_name_or_path": "./save_models/vai_0.5_qwen2.5_mid_merge",
   "transformers_version": "4.45.0",
   "continuous_training": true,
   "freeze_mm_mlp_adapter": false,
   "image_aspect_ratio": "pad",
   "mm_hidden_size": 3456,
   "mm_projector_lr": 2e-06,
   "mm_projector_type": "mlp2x_gelu",
   "mm_vision_tower": "./save_models/siglip-so400m-patch14-384/",
   "model_type": "bunny-qwen2",
   "tokenizer_model_max_length": 8192,
   "tokenizer_padding_side": "right",
   "tune_mm_mlp_adapter": false,
   "unfreeze_vision_tower": true,
   "use_mm_proj": true,
   "use_s2": true
}