We introduce CyberSolve, the flan-t5-large model fintuned on all 2M records of the DeepMind LinAlg 1D dataset. This is the first model checkpoint, scoring 86.56 on the eval dataset
71a7616
verified
| { | |
| "_name_or_path": "/Volumes/workspace_dogfood/jgr/hugging_face_cache/CyberSolve-DeepMind-LinAlg-1D", | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 2816, | |
| "d_kv": 64, | |
| "d_model": 1024, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 24, | |
| "num_heads": 16, | |
| "num_layers": 24, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.1", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |