FLOPS-Squared/KeystoneFuse-Baseline-Epoch-2-Instruct-PyTorch

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 1024,12  "initializer_range": 0.02,13  "intermediate_size": 4096,14  "max_position_embeddings": 8192,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 8,18  "num_hidden_layers": 14,19  "num_key_value_heads": 2,20  "pad_token_id": 0,21  "rms_norm_eps": 1e-06,22  "rope_scaling": null,23  "rope_theta": 10000.0,24  "tie_word_embeddings": true,25  "transformers_version": "4.52.3",26  "use_cache": true,27  "vocab_size": 3814428}29