| { | |
| "_name_or_path": "/users/zyong2/data/zyong2/m_mech_toxic/data/processed/010-llama/lora_merged_models/aya-23-8B/lora_aya-23-8B-LR1e-5_final_checkpoint", | |
| "architectures": [ | |
| "CohereForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 5, | |
| "eos_token_id": 255001, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "layer_norm_eps": 1e-05, | |
| "logit_scale": 0.0625, | |
| "max_position_embeddings": 8192, | |
| "model_type": "cohere", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rope_theta": 10000, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.2", | |
| "use_cache": true, | |
| "use_qk_norm": false, | |
| "vocab_size": 256000 | |
| } | |