| { | |
| "_name_or_path": "/tmp/rrt_model-1_7b-lora-2loops", | |
| "alpha": 1024, | |
| "architectures": [ | |
| "RelaxedRecursiveLlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama-rrt", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "pretraining_tp": 1, | |
| "rank": 512, | |
| "recurse_layers": 12, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 130000, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.1", | |
| "use_cache": true, | |
| "use_dora": false, | |
| "vocab_size": 49152 | |
| } | |