| { | |
| "_name_or_path": "/notebooks/finetuning-subnet/local-models/training/2024-05-08_00-08-59_1", | |
| "architectures": [ | |
| "StableLmForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 100289, | |
| "eos_token_id": 100290, | |
| "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, | |
| "qk_layernorm": false, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": false, | |
| "use_parallel_residual": false, | |
| "use_qkv_bias": true, | |
| "vocab_size": 100352 | |
| } | |