archit11/worldmodel2

1{2  "_name_or_path": "nisten/Biggie-SmoLlm-0.15B-Base",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 0,9  "eos_token_id": 0,10  "hidden_act": "silu",11  "hidden_size": 576,12  "initializer_range": 0.02,13  "intermediate_size": 1536,14  "max_position_embeddings": 2048,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 9,18  "num_hidden_layers": 35,19  "num_key_value_heads": 3,20  "pretraining_tp": 1,21  "rms_norm_eps": 1e-05,22  "rope_scaling": null,23  "rope_theta": 10000.0,24  "tie_word_embeddings": true,25  "torch_dtype": "bfloat16",26  "transformers_version": "4.44.2",27  "use_cache": true,28  "vocab_size": 4915229}30