| { | |
| "_name_or_path": "/workspace/restore/finetuning-subnet/local-models/training/2024-03-29_23-04-54_0_1_2_3_4_5_6_7_8_9_10_11_12_13_14_15_16_17_18_19_20_21_22_23_24_25_26_27_28_29_30_31_32_33_34_35_36_37_38_39_40_41_42_43", | |
| "architectures": [ | |
| "StableLmForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100257, | |
| "eos_token_id": 100257, | |
| "hidden_act": "silu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5632, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4096, | |
| "model_type": "stablelm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 32, | |
| "partial_rotary_factor": 0.25, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.38.2", | |
| "use_cache": false, | |
| "use_qkv_bias": true, | |
| "vocab_size": 100352 | |
| } | |