{ "fixture": "huggingface-mic/tipsv2-b14-mic", "key": "4fa35b9d60f3d95105b139ecd67f3a4a365a7cec9ef6bee109519492808b19df", "key_fields": { "architectures": [ "TIPSv2Model" ], "output_hidden_states": false, "return_dict": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "text_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 32000, "hidden_size": 64, "intermediate_size": 128, "num_hidden_layers": 2, "num_attention_heads": 4, "max_position_embeddings": 64, "hidden_act": "relu", "layer_norm_eps": 1e-05, "attention_dropout": 0.0, "pad_token_id": 0, "bos_token_id": null, "eos_token_id": null, "initializer_range": 0.02, "scale_sqrt_depth": true, "pooling_epsilon": 1e-08, "_name_or_path": "", "model_type": "tipsv2_text_model", "output_attentions": false }, "vision_config": { "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": null, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "hidden_size": 64, "num_hidden_layers": 2, "num_attention_heads": 4, "mlp_ratio": 4, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "attention_probs_dropout_prob": 0.0, "initializer_range": 0.02, "layer_norm_eps": 1e-06, "image_size": 448, "patch_size": 14, "num_channels": 3, "qkv_bias": true, "layerscale_value": 1.0, "drop_path_rate": 0.0, "use_swiglu_ffn": false, "num_register_tokens": 1, "apply_layernorm": true, "reshape_hidden_states": true, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4", "stage5", "stage6", "stage7", "stage8", "stage9", "stage10", "stage11", "stage12" ], "_name_or_path": "", "interpolate_antialias": true, "interpolate_offset": 0.0, "model_type": "tipsv2_vision_model", "output_attentions": false, "out_features": [ "stage2" ], "out_indices": [ 2 ] }, "temperature_init_value": 0.005065968260169029, "auto_map": { "AutoConfig": "configuration_tips.TIPSv2Config", "AutoModel": "modeling_tips.TIPSv2Model" }, "model_type": "tipsv2", "output_attentions": false }, "covers": { "google/tipsv2-b14": "ed1e4dc6b74bf3935ae099e9d5eb30fa96528454" }, "built_from": { "repo": "google/tipsv2-b14", "revision": "ed1e4dc6b74bf3935ae099e9d5eb30fa96528454" }, "seed": 17, "dtype": "float32", "builder": "example/build_fixtures.py", "builder_revision": "e60cfd37adc70f455a7adcba3317dff71b612f80", "recipe": { "seed": 17, "model_class": "Tipsv2Model" }, "shrink": "rule", "model_class": "Tipsv2Model", "parameters": 2318913, "missing_parameters": [], "checkpoint_inspection": "parameter headers/indexes; bounded binary fallback", "numeric_health_scope": "CPU float32/bfloat16/float16; autocast for low-precision losses", "captured": { "call": "training step", "inputs": [ "attention_mask", "input_ids", "pixel_values", "return_loss" ], "class": "Tipsv2Model" }, "weights": "random", "gate": { "random": { "pass": true, "accepted_insensitive": {}, "threshold": 0.001, "deltas": { "input_ids:roll_batch": 1.0175971984863281, "input_ids:reverse": 0.8126106262207031, "attention_mask:all_ones": null, "pixel_values:roll_batch": 21.11993980407715, "pixel_values:swap_channels": 21.157976150512695, "pixel_values:reverse": 0.0375213623046875, "pixel_values:halve": 0.5448436737060547 }, "weakest": "pixel_values:reverse", "no_perturbation_defined": [], "not_a_forward_parameter": [] } }, "numeric_health": { "float32": { "outputs_finite": true, "loss_finite": true, "gradients_finite": true, "finite": true }, "bfloat16": { "outputs_finite": true, "loss_finite": true, "gradients_finite": true, "finite": true }, "float16": { "outputs_finite": true, "loss_finite": true, "unscaled_gradients_finite": true, "finite": true } }, "copied_unchanged": [ "configuration_tips.py", "image_encoder.py", "modeling_tips.py", "processor_config.json", "text_encoder.py", "tokenizer.model", "tokenizer_config.json" ], "environment": { "python": "3.12.12", "machine": "arm64", "torch": "2.14.1", "transformers": "5.22.0.dev0", "tokenizers": "0.23.3" }, "sha256": { "config.json": "038a6a9af77b537918529c4b63f53bd8c2b78cb41548f5a9f89e9793f21c34cb", "configuration_tips.py": "ef8306a43dc0826dbe4e563089b6a3269c60680a02281e2533cdc5d1a6516e42", "image_encoder.py": "862fab50ddd623222112bd589b348bba57ead44523ac4dcc399422955ad76de3", "model.safetensors": "37a803f666c3061761189bc2ffa0862a8841382051fe3da9163981912b225b9a", "modeling_tips.py": "11dae40ee6aa32cd0bb0ddcbfdcd871abbc358a489e7d916651342acecff8a8f", "processor_config.json": "a3da1bf8a182db305c5dacfcf2f28fb09567028bade087e7344497819124523f", "text_encoder.py": "04addbc2f19664e48ef963452e855d1bce185be9aaf276fbd9e0a70d7f0918df", "tokenizer.model": "4c40e7723348d5d9a3d3c2bdcec5120d97fb29edfe1bf118b4494bce02fc7624", "tokenizer_config.json": "0da353fd61bc490106aa9f0ae2e097802182106d1af182cfe4aa654df0ce729b" } }