stk5/deval4-2
05
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 128000,8 "eos_token_id": [9 128001,10 128008,11 12800912 ],13 "head_dim": 128,14 "hidden_act": "silu",15 "hidden_size": 4096,16 "initializer_range": 0.02,17 "intermediate_size": 14336,18 "max_position_embeddings": 131072,19 "mlp_bias": false,20 "model_type": "llama",21 "num_attention_heads": 32,22 "num_hidden_layers": 32,23 "num_key_value_heads": 8,24 "pad_token_id": 128004,25 "pretraining_tp": 1,26 "rms_norm_eps": 1e-05,27 "rope_scaling": {28 "factor": 8.0,29 "high_freq_factor": 4.0,30 "low_freq_factor": 1.0,31 "original_max_position_embeddings": 8192,32 "rope_type": "llama3"33 },34 "rope_theta": 500000.0,35 "tie_word_embeddings": false,36 "torch_dtype": "bfloat16",37 "transformers_version": "4.46.3",38 "unsloth_version": "2024.11.9",39 "use_cache": true,40 "vocab_size": 12825641}42 