| { |
| "_name_or_path": "/u/xpan2/projects/scalebio/finetune/output_models/scalebio-scalebio-meta-llama-Meta-Llama-3-8B-pxyyy-rlhflow_mixture_clean_empty_round_with_dart-math_downsampled-20k-1-2e-5-lisa_2_20", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": 128001, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 128001, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.44.2", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
