smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI

1{2  "architectures": [3    "SmolVLMForConditionalGeneration"4  ],5  "image_token_id": 49190,6  "model_type": "smolvlm",7  "pad_token_id": 128002,8  "scale_factor": 3,9  "text_config": {10    "_flash_attn_2_enabled": true,11    "_name_or_path": "None",12    "architectures": [13      "VLlama3ForCausalLM"14    ],15    "attention_bias": false,16    "attention_dropout": 0.0,17    "head_dim": 64,18    "hidden_act": "silu",19    "hidden_size": 2048,20    "initializer_range": 0.02,21    "intermediate_size": 8192,22    "max_position_embeddings": 8192,23    "mlp_bias": false,24    "model_type": "llama",25    "neftune_noise_alpha": 0.0,26    "num_attention_heads": 32,27    "num_hidden_layers": 24,28    "num_key_value_heads": 32,29    "pad_token_id": 2,30    "perceiver_config": {31      "_attn_implementation_autoset": false,32      "_name_or_path": "",33      "add_cross_attention": false,34      "architectures": null,35      "attention_dropout": 0.0,36      "bad_words_ids": null,37      "begin_suppress_tokens": null,38      "bos_token_id": null,39      "chunk_size_feed_forward": 0,40      "cross_attention_hidden_size": null,41      "decoder_start_token_id": null,42      "diversity_penalty": 0.0,43      "do_sample": false,44      "early_stopping": false,45      "encoder_no_repeat_ngram_size": 0,46      "eos_token_id": null,47      "exponential_decay_length_penalty": null,48      "finetuning_task": null,49      "forced_bos_token_id": null,50      "forced_eos_token_id": null,51      "hidden_act": "silu",52      "id2label": {53        "0": "LABEL_0",54        "1": "LABEL_1"55      },56      "is_decoder": false,57      "is_encoder_decoder": false,58      "label2id": {59        "LABEL_0": 0,60        "LABEL_1": 161      },62      "length_penalty": 1.0,63      "max_length": 20,64      "min_length": 0,65      "model_type": "vllama3",66      "no_repeat_ngram_size": 0,67      "num_beam_groups": 1,68      "num_beams": 1,69      "num_key_value_heads": 1,70      "num_return_sequences": 1,71      "output_attentions": false,72      "output_hidden_states": false,73      "output_scores": false,74      "pad_token_id": null,75      "prefix": null,76      "problem_type": null,77      "pruned_heads": {},78      "qk_layer_norms_perceiver": false,79      "remove_invalid_values": false,80      "repetition_penalty": 1.0,81      "resampler_depth": 6,82      "resampler_head_dim": 96,83      "resampler_n_heads": 16,84      "resampler_n_latents": 64,85      "return_dict": true,86      "return_dict_in_generate": false,87      "sep_token_id": null,88      "suppress_tokens": null,89      "task_specific_params": null,90      "temperature": 1.0,91      "tf_legacy_loss": false,92      "tie_encoder_decoder": false,93      "tie_word_embeddings": true,94      "tokenizer_class": null,95      "top_k": 50,96      "top_p": 1.0,97      "torch_dtype": null,98      "torchscript": false,99      "transformers_version": "4.46.0",100      "typical_p": 1.0,101      "use_bfloat16": false102    },103    "pixel_shuffle_factor": 3,104    "pretraining_tp": 1,105    "qk_layer_norms": false,106    "rms_norm_eps": 1e-05,107    "rope_scaling": null,108    "rope_theta": 130000,109    "torch_dtype": "bfloat16",110    "transformers.js_config": {111      "kv_cache_dtype": {112        "fp16": "float16",113        "q4f16": "float16"114      }115    },116    "use_cache": true,117    "use_resampler": false,118    "vocab_size": 49280119  },120  "tie_word_embeddings": false,121  "torch_dtype": "bfloat16",122  "transformers_version": "4.54.1",123  "use_cache": true,124  "use_reentrant_checkpointing": false,125  "vision_config": {126    "attention_dropout": 0.0,127    "hidden_act": "gelu_pytorch_tanh",128    "hidden_size": 1152,129    "image_size": 384,130    "initializer_range": 0.02,131    "intermediate_size": 4304,132    "layer_norm_eps": 1e-06,133    "max_image_size": {134      "longest_edge": 384135    },136    "model_type": "smolvlm_vision",137    "num_attention_heads": 16,138    "num_channels": 3,139    "num_hidden_layers": 27,140    "patch_size": 14,141    "size": {142      "longest_edge": 1920143    },144    "tie_word_embeddings": false,145    "torch_dtype": "bfloat16",146    "use_base_siglip": false147  },148  "vocab_size": 49280149}150