| { | |
| "ADA_ACT": false, | |
| "ADA_DIM": 1024, | |
| "ADA_LOSS_WEIGHT": 1.0, | |
| "ADA_MASK_WEIGHT": 10.0, | |
| "ADA_SVD": false, | |
| "ADA_TOPK": 1024, | |
| "ADA_TOPK_WEIGHT": 0.1, | |
| "_name_or_path": "experiment_ckpts/gemma-2b_SFT-2024-06-10-123619/checkpoint-11592", | |
| "architectures": [ | |
| "AdaVocabGemmaforCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoModelForCausalLM": "ada_vocab_factory.AdaVocabGemmaforCausalLM" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "head_dim": 256, | |
| "hidden_act": "gelu", | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "max_position_embeddings": 8192, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "vocab_size": 256000 | |
| } | |