IFM/K2

1{2  "_name_or_path": "llm360/k2",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": null,9  "eos_token_id": 2,10  "hidden_act": "silu",11  "hidden_size": 8192,12  "initializer_range": 0.02,13  "intermediate_size": 22016,14  "max_position_embeddings": 8192,15  "max_sequence_length": 8192,16  "model_type": "llama",17  "num_attention_heads": 64,18  "num_hidden_layers": 80,19  "num_key_value_heads": 64,20  "pad_token_id": 0,21  "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": "float16",27  "transformers_version": "4.39.3",28  "use_cache": true,29  "vocab_size": 3203230}31