neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/a737859203da7a2e914f.json

{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 2048, "intermediate_size": 5504, "num_hidden_layers": 24, "num_attention_heads": 16, "num_key_value_heads": 16, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float32", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4"}}