| { |
| "_name_or_path": "Spravil/caption-via-translation-3_5B", |
| "architectures": [ |
| "FlorenceGemma2ForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "Spravil/caption-via-translation-3_5B--configuration_gemma2.FlorenceGemma2Config", |
| "AutoModelForCausalLM": "Spravil/caption-via-translation-3_5B--modeling_gemma2.FlorenceGemma2ForConditionalGeneration" |
| }, |
| "bos_token_id": 2, |
| "decoder_start_token_id": 1, |
| "encoder_vocab_size": 51289, |
| "eos_token_id": 1, |
| "forced_bos_token_id": 2, |
| "forced_eos_token_id": 1, |
| "ignore_index": -100, |
| "model_type": "florencegemma2", |
| "pad_token_id": 0, |
| "tie_word_embeddings": true, |
| "is_encoder_decoder": true, |
| "projection_dim": 1024, |
| "text_config": { |
| "_attn_implementation_autoset": false, |
| "_attn_implementation": "eager", |
| "_name_or_path": "", |
| "activation_dropout": 0.1, |
| "activation_function": "gelu", |
| "add_bias_logits": false, |
| "add_cross_attention": false, |
| "add_final_layer_norm": false, |
| "architectures": null, |
| "attention_dropout": 0.1, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 2, |
| "chunk_size_feed_forward": 0, |
| "classif_dropout": 0.1, |
| "classifier_dropout": 0.0, |
| "cross_attention_hidden_size": null, |
| "d_model": 1024, |
| "decoder_attention_heads": 16, |
| "decoder_ffn_dim": 4096, |
| "decoder_layerdrop": 0.0, |
| "decoder_layers": 12, |
| "decoder_start_token_id": 1, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dropout": 0.1, |
| "early_stopping": true, |
| "encoder_attention_heads": 16, |
| "encoder_bos_token_id": 0, |
| "encoder_eos_token_id": 2, |
| "encoder_ffn_dim": 4096, |
| "encoder_layerdrop": 0.0, |
| "encoder_layers": 12, |
| "encoder_no_repeat_ngram_size": 0, |
| "encoder_pad_token_id": 1, |
| "encoder_vocab_size": 51289, |
| "eos_token_id": 1, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "gemma_config": { |
| "_attn_implementation_autoset": false, |
| "_attn_implementation": "eager", |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": [ |
| "Gemma2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": 50.0, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 2, |
| "cache_implementation": "hybrid", |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": 1, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "early_stopping": false, |
| "encoder_hidden_size": 1024, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 1, |
| "exponential_decay_length_penalty": null, |
| "final_logit_softcapping": 30.0, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "head_dim": 256, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2304, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "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": "gemma2", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 8, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 4, |
| "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": {}, |
| "query_pre_attn_scalar": 256, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 10000.0, |
| "sep_token_id": null, |
| "sliding_window": 4096, |
| "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": "float32", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 256000 |
| }, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2" |
| }, |
| "init_std": 0.02, |
| "is_decoder": false, |
| "is_encoder_decoder": true, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 4096, |
| "min_length": 0, |
| "model_type": "florence2_language", |
| "no_repeat_ngram_size": 3, |
| "normalize_before": false, |
| "num_beam_groups": 1, |
| "num_beams": 3, |
| "num_hidden_layers": 12, |
| "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, |
| "scale_embedding": 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, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "use_encoder_tokenizer": false, |
| "vocab_size": 256000 |
| }, |
| "torch_dtype": "float16", |
| "transformers_version": "4.48.0", |
| "vision_config": { |
| "_attn_implementation_autoset": false, |
| "_attn_implementation": "eager", |
| "model_type": "davit", |
| "drop_path_rate": 0.1, |
| "patch_size": [ |
| 7, |
| 3, |
| 3, |
| 3 |
| ], |
| "patch_stride": [ |
| 4, |
| 2, |
| 2, |
| 2 |
| ], |
| "patch_padding": [ |
| 3, |
| 1, |
| 1, |
| 1 |
| ], |
| "patch_prenorm": [ |
| false, |
| true, |
| true, |
| true |
| ], |
| "enable_checkpoint": false, |
| "dim_embed": [ |
| 256, |
| 512, |
| 1024, |
| 2048 |
| ], |
| "num_heads": [ |
| 8, |
| 16, |
| 32, |
| 64 |
| ], |
| "num_groups": [ |
| 8, |
| 16, |
| 32, |
| 64 |
| ], |
| "depths": [ |
| 1, |
| 1, |
| 9, |
| 1 |
| ], |
| "window_size": 12, |
| "projection_dim": 1024, |
| "visual_temporal_embedding": { |
| "type": "COSINE", |
| "max_temporal_embeddings": 100 |
| }, |
| "image_pos_embed": { |
| "type": "learned_abs_2d", |
| "max_pos_embeddings": 50 |
| }, |
| "image_feature_source": [ |
| "spatial_avg_pool", |
| "temporal_avg_pool" |
| ] |
| }, |
| "vocab_size": 256000 |
| } |
