| { |
| "model_type": "vision_language_model", |
| "language_model": { |
| "return_dict": true, |
| "output_hidden_states": false, |
| "torchscript": false, |
| "dtype": "bfloat16", |
| "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, |
| "architectures": [ |
| "Gemma3ForCausalLM" |
| ], |
| "finetuning_task": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "task_specific_params": null, |
| "problem_type": null, |
| "tokenizer_class": null, |
| "prefix": null, |
| "bos_token_id": 2, |
| "pad_token_id": 0, |
| "eos_token_id": [ |
| 1, |
| 106 |
| ], |
| "sep_token_id": null, |
| "decoder_start_token_id": null, |
| "max_length": 20, |
| "min_length": 0, |
| "do_sample": false, |
| "early_stopping": false, |
| "num_beams": 1, |
| "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, |
| "num_beam_groups": 1, |
| "diversity_penalty": 0.0, |
| "_name_or_path": "checkpoints/models/gemma-3-1b-it", |
| "transformers_version": "4.57.3", |
| "cache_implementation": "hybrid", |
| "model_type": "gemma3_text", |
| "sliding_window_pattern": 6, |
| "tf_legacy_loss": false, |
| "use_bfloat16": false, |
| "vocab_size": 262145, |
| "max_position_embeddings": 32768, |
| "hidden_size": 1152, |
| "intermediate_size": 6912, |
| "num_hidden_layers": 26, |
| "num_attention_heads": 4, |
| "head_dim": 256, |
| "num_key_value_heads": 1, |
| "initializer_range": 0.02, |
| "rms_norm_eps": 1e-06, |
| "use_cache": true, |
| "rope_theta": 1000000, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "query_pre_attn_scalar": 256, |
| "sliding_window": 512, |
| "final_logit_softcapping": null, |
| "attn_logit_softcapping": null, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention" |
| ], |
| "use_bidirectional_attention": false, |
| "rope_local_base_freq": 10000, |
| "rope_scaling": null, |
| "_sliding_window_pattern": 6, |
| "image_token_id": 262144, |
| "output_attentions": false |
| }, |
| "vision_model": { |
| "return_dict": true, |
| "output_hidden_states": false, |
| "torchscript": false, |
| "dtype": "bfloat16", |
| "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, |
| "architectures": null, |
| "finetuning_task": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "task_specific_params": null, |
| "problem_type": null, |
| "tokenizer_class": null, |
| "prefix": null, |
| "bos_token_id": null, |
| "pad_token_id": null, |
| "eos_token_id": null, |
| "sep_token_id": null, |
| "decoder_start_token_id": null, |
| "max_length": 20, |
| "min_length": 0, |
| "do_sample": false, |
| "early_stopping": false, |
| "num_beams": 1, |
| "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, |
| "num_beam_groups": 1, |
| "diversity_penalty": 0.0, |
| "_name_or_path": "checkpoints/models/siglip-base-patch16-256-multilingual", |
| "transformers_version": "4.57.3", |
| "model_type": "siglip_vision_model", |
| "tf_legacy_loss": false, |
| "use_bfloat16": false, |
| "hidden_size": 768, |
| "intermediate_size": 3072, |
| "num_hidden_layers": 12, |
| "num_attention_heads": 12, |
| "num_channels": 3, |
| "patch_size": 16, |
| "image_size": 256, |
| "attention_dropout": 0.0, |
| "layer_norm_eps": 1e-06, |
| "hidden_act": "gelu_pytorch_tanh", |
| "output_attentions": false |
| }, |
| "projector": { |
| "vision_dim": 768, |
| "hidden_dim": 1152 |
| } |
| } |
