llm-stacking/G_zero_width

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 2048,10  "initializer_range": 0.02,11  "intermediate_size": 5632,12  "max_position_embeddings": 2048,13  "model_type": "llama",14  "num_attention_heads": 32,15  "num_hidden_layers": 24,16  "num_key_value_heads": 32,17  "pad_token_id": 0,18  "pretraining_tp": 1,19  "rms_norm_eps": 1e-05,20  "rope_scaling": null,21  "rope_theta": 10000.0,22  "tie_word_embeddings": false,23  "torch_dtype": "float32",24  "transformers_version": "4.31.0",25  "use_cache": true,26  "vocab_size": 3200027}28