optimum-neuron-cache
/
neuronxcc-2.15.128.0+56dc5a86
/0_REGISTRY
/0.0.25.dev0
/training
/llama
/meta-llama
/Llama-3.2-1B-Instruct
/b1a3975e13331e25e6cc.json
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128256, "eos_token_id": 128257, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"compiler_version": "2.15.128.0+56dc5a86", "input_specs": {"chosen": ["<|im_start|>user\nDetermine the answer to 169716 / 520 for me. equations/math only, no commentary.<|im_end|>\n<|im_start|>assistant\nTo solve the equation 169716 / 520, simply divide the numerator by the denominator:\n\n169716 \u00f7 520 = 326\n\nSo, the result of 169716 / 520 is 326.<|im_end|>\n"], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["Determine the answer to 169716 / 520 for me. equations/math only, no commentary."], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["Determine the answer to 169716 / 520 for me. equations/math only, no commentary."], "rejected": ["<|im_start|>user\nDetermine the answer to 169716 / 520 for me. equations/math only, no commentary.<|im_end|>\n<|im_start|>assistant\n169716 - 520 * 300 = 169716 - 156000 = 13716\n13716 - 520 * 20 = 13716 - 10400 = 3316\n3316 - 520 * 6 = 3316 - 3120 = 196\nTherefore, 169716 / 520 = 326 R 196<|im_end|>\n"], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["GOAT"]}, "model_class": "PeftModelForCausalLM", "num_neuron_cores_per_node": 2, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 1, "training": true}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 128257, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128258} |