| { |
| "adapter_layer_norm_eps": 1e-06, |
| "architectures": [ |
| "TinyAyaVisionForConditionalGeneration" |
| ], |
| "cache_dir": null, |
| "connector_intermediate_size": 2048, |
| "connector_type": "pixel_shuffle", |
| "downsample_factor": 2, |
| "dtype": "bfloat16", |
| "image_size": 384, |
| "image_token": "<image>", |
| "image_token_id": 261008, |
| "in_token_limit": 1024, |
| "llm_hidden_size": 2048, |
| "llm_model_name": "CohereLabs/tiny-aya-global", |
| "llm_vocab_size": 262144, |
| "model_type": "tiny_aya_vision", |
| "num_llm_layers": 36, |
| "num_tokens_after_shuffle": 196, |
| "num_vision_tokens": 729, |
| "padded_grid_size": 28, |
| "patch_size": 14, |
| "pixel_shuffle_embed_dim": 4608, |
| "post_projector_rms_norm": false, |
| "text_config": { |
| "_name_or_path": "CohereLabs/tiny-aya-global", |
| "_sliding_window_pattern": 4, |
| "add_cross_attention": false, |
| "architectures": [ |
| "Cohere2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "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": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 3, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-05, |
| "layer_switch": 4, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "length_penalty": 1.0, |
| "logit_scale": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 500000, |
| "min_length": 0, |
| "model_type": "cohere2", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 4, |
| "num_return_sequences": 1, |
| "order_of_interleaved_layers": "local_attn_first", |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 0, |
| "position_embedding_type": "rope_gptj", |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rope_scaling": null, |
| "rope_theta": 50000, |
| "rotary_pct": 1.0, |
| "sep_token_id": null, |
| "sliding_window": 4096, |
| "sliding_window_pattern": 4, |
| "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, |
| "torchscript": false, |
| "transformers_version": "4.57.2", |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "use_embedding_sharing": true, |
| "use_gated_activation": true, |
| "use_parallel_block": true, |
| "use_parallel_embedding": false, |
| "use_qk_norm": false, |
| "vocab_size": 262144 |
| }, |
| "tokens_per_tile": 4, |
| "transformers_version": "4.57.2", |
| "trust_remote_code": false, |
| "vision_encoder_type": "siglip", |
| "vision_feature_layer": -1, |
| "vision_feature_select_strategy": "full", |
| "vision_grid_size": 27, |
| "vision_hidden_size": 1152, |
| "vision_model_name": "google/siglip2-so400m-patch14-384", |
| "vision_tower_config": { |
| "_name_or_path": "google/siglip2-so400m-patch14-384", |
| "add_cross_attention": false, |
| "architectures": null, |
| "attention_dropout": 0.0, |
| "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, |
| "dtype": "bfloat16", |
| "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, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_size": 384, |
| "intermediate_size": 4304, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-06, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "siglip_vision_model", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_channels": 3, |
| "num_hidden_layers": 27, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "patch_size": 14, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "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, |
| "torchscript": false, |
| "transformers_version": "4.57.2", |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| } |
| } |
|
|
