neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B-Instruct/b6a587e68d077b0a3153.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\nTeacher: The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Norwegian Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Norwegian language. 2) Also names ,dates and places should be preserved it should not get translated.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nThe Hound of the Baskervilles\nSolution: Hunden fra Baskerville\nReason: The 'hound' and 'Baskervilles' keyword in English matches exactly with the 'hunden' and 'Baskerville' word in Norwegian so the name entity is preserved.\n\nNow, solve this instance: Her bulky figure in a shawl and skirt might have been comic were it not for the intensity of feeling upon her face.\nStudent:<|im_end|>\n<|im_start|>assistant\nHennes kraftige skikkelse i et sjal og skj\u00f8rt kunne ha v\u00e6rt komisk, hvis det ikke hadde v\u00e6rt for intensiteten i f\u00f8lelsene p\u00e5 ansiktet hennes.<|im_end|>\n"], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["Teacher: The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Norwegian Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Norwegian language. 2) Also names ,dates and places should be preserved it should not get translated.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nThe Hound of the Baskervilles\nSolution: Hunden fra Baskerville\nReason: The 'hound' and 'Baskervilles' keyword in English matches exactly with the 'hunden' and 'Baskerville' word in Norwegian so the name entity is preserved.\n\nNow, solve this instance: Her bulky figure in a shawl and skirt might have been comic were it not for the intensity of feeling upon her face.\nStudent:"], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["Teacher: The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Norwegian Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Norwegian language. 2) Also names ,dates and places should be preserved it should not get translated.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nThe Hound of the Baskervilles\nSolution: Hunden fra Baskerville\nReason: The 'hound' and 'Baskervilles' keyword in English matches exactly with the 'hunden' and 'Baskerville' word in Norwegian so the name entity is preserved.\n\nNow, solve this instance: Her bulky figure in a shawl and skirt might have been comic were it not for the intensity of feeling upon her face.\nStudent:"], "rejected": ["<|im_start|>user\nTeacher: The provided files include famous book titles and sentences in the English language, and we ask you to translate those to the Norwegian Language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and form of each sentence in the Norwegian language. 2) Also names ,dates and places should be preserved it should not get translated.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nThe Hound of the Baskervilles\nSolution: Hunden fra Baskerville\nReason: The 'hound' and 'Baskervilles' keyword in English matches exactly with the 'hunden' and 'Baskerville' word in Norwegian so the name entity is preserved.\n\nNow, solve this instance: Her bulky figure in a shawl and skirt might have been comic were it not for the intensity of feeling upon her face.\nStudent:<|im_end|>\n<|im_start|>assistant\nSure, I'd be happy to help you with that! Here's my translation of the sentence into Norwegian:\n\nHennes kraftige skikkelse i en shawl og skj\u00f8rt kunne gyawt v\u00e6rt komisk, men intensiteten i f\u00f8lelsen i hennes ansikt gjorde det ikke mulig.\n\nI preserved the names and proper nouns, and tried to find the most natural way to express the sentence in Norwegian. I hope this meets your expectations!<|im_end|>\n"], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["flan_v2_niv2"]}, "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}