{ "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_type": "drift-diffusion", "baseline_each_head": true, "bos_token_id": 1, "cache_dir": "./output/models/llama-cosmopedia-drift-sigmoid-2B-base", "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 12, "num_hidden_layers": 24, "num_key_value_heads": 12, "only_diffusion": false, "only_drift": true, "pretraining_tp": 1, "revision": "zero", "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.49.0", "use_cache": false, "vocab_size": 128257 }