Nisk36/DPO_normalchosen_diffseed
06
1{2 "_name_or_path": "elyza/Llama-3-ELYZA-JP-8B",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 128000,9 "eos_token_id": 128009,10 "head_dim": 128,11 "hidden_act": "silu",12 "hidden_size": 4096,13 "initializer_range": 0.02,14 "intermediate_size": 14336,15 "max_position_embeddings": 8192,16 "mlp_bias": false,17 "model_type": "llama",18 "num_attention_heads": 32,19 "num_hidden_layers": 32,20 "num_key_value_heads": 8,21 "pretraining_tp": 1,22 "rms_norm_eps": 1e-05,23 "rope_scaling": null,24 "rope_theta": 500000.0,25 "tie_word_embeddings": false,26 "torch_dtype": "bfloat16",27 "transformers_version": "4.45.2",28 "use_cache": true,29 "vocab_size": 12825630}31 