PrimeIntellect/INTELLECT-1-step-28600
1201
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 "hidden_act": "silu",14 "hidden_size": 4096,15 "initializer_range": 0.02,16 "intermediate_size": 14336,17 "max_position_embeddings": 8192,18 "mlp_bias": false,19 "model_type": "llama",20 "num_attention_heads": 32,21 "num_hidden_layers": 42,22 "num_key_value_heads": 8,23 "pretraining_tp": 1,24 "rms_norm_eps": 1e-05,25 "rope_scaling": {26 "original_max_position_embeddings": 8192,27 "rope_type": "default"28 },29 "rope_theta": 500000.0,30 "tie_word_embeddings": false,31 "transformers_version": "4.44.2",32 "use_cache": true,33 "vocab_size": 12825634}35 