neuronxcc-2.14.213.0+013d129b/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-2.7B/65af25a07a9af664c36d.json

{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 6912, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-2.7B", "checkpoint_revision": "2f157a0306b75d37694ae05f6a4067220254d540", "compiler_type": "neuronx-cc", "compiler_version": "2.14.213.0+013d129b", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 20, "num_hidden_layers": 32, "num_key_value_heads": 20, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}