| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Lfm2VlForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_lfm2_vl.Lfm2VlConfig", | |
| "AutoModelForImageTextToText": "modeling_lfm2_vl.Lfm2VlForConditionalGeneration" | |
| }, | |
| "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_image_splitting": true, | |
| "do_sample": false, | |
| "downsample_factor": 2, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "encoder_patch_size": 16, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_token_index": 396, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_image_tokens": 256, | |
| "max_length": 20, | |
| "max_num_patches": 1024, | |
| "max_pixels_tolerance": 1.5, | |
| "max_tiles": 10, | |
| "min_image_tokens": 64, | |
| "min_length": 0, | |
| "min_tiles": 2, | |
| "model_type": "lfm2-vl", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "projector_bias": true, | |
| "projector_hidden_act": "gelu", | |
| "projector_hidden_size": 2560, | |
| "pruned_heads": {}, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "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, | |
| "text_config": { | |
| "vocab_size": 65536, | |
| "hidden_size": 2048, | |
| "num_hidden_layers": 16, | |
| "rope_theta": 1000000.0, | |
| "max_position_embeddings": 128000, | |
| "use_cache": true, | |
| "norm_eps": 1e-05, | |
| "initializer_range": 0.02, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "conv_bias": false, | |
| "conv_L_cache": 3, | |
| "intermediate_size": 12288, | |
| "block_multiple_of": 256, | |
| "block_ffn_dim_multiplier": 1.0, | |
| "block_auto_adjust_ff_dim": true, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv" | |
| ], | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "torch_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": [ | |
| "Lfm2ForCausalLM" | |
| ], | |
| "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": 1, | |
| "pad_token_id": 0, | |
| "eos_token_id": 7, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "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, | |
| "_name_or_path": "LiquidAI/LFM2-1.2B", | |
| "block_dim": 2048, | |
| "block_ff_dim": 12288, | |
| "block_mlp_init_scale": 1.0, | |
| "block_norm_eps": 1e-05, | |
| "block_out_init_scale": 1.0, | |
| "block_use_swiglu": true, | |
| "block_use_xavier_init": true, | |
| "conv_dim": 2048, | |
| "conv_dim_out": 2048, | |
| "conv_use_xavier_init": true, | |
| "model_type": "lfm2", | |
| "num_heads": 32, | |
| "use_pos_enc": true, | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "output_attentions": false | |
| }, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tile_size": 512, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "transformers_version": "4.55.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_image_special_tokens": true, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "torch_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, | |
| "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, | |
| "_name_or_path": "", | |
| "model_type": "siglip2_vision_model", | |
| "vision_use_head": false, | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "num_hidden_layers": 27, | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "patch_size": 16, | |
| "attention_dropout": 0.0, | |
| "layer_norm_eps": 1e-06, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "num_patches": 256, | |
| "output_attentions": false | |
| }, | |
| "vision_feature_layer": -2 | |
| } |