Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +14 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/09f3cdf1e695f554bbfb.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/34d5c50f3539e73531f6.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/44f4532ed4d9bb143dfa.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/51271d7790b315d59b4d.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/701b435f22762b79be41.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/9babb4958cc9d418f609.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/9eab79ca9f620713c3b6.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/a9dc231a54d26bc25b15.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/aa212064b8aa2edddfdd.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/b093f9809ea1fa7a307b.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/beee0da2cee55a14898c.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/d9baeaee7d31148c77bd.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/e0790333588e5b65fe53.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/fbcf4b0b066c41a371e3.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.neff +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.neff +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.neff +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/model.log +65 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.neff +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.neff +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.neff +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.neff +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/compile_flags.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.done +0 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.hlo_module.pb +3 -0
- neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.neff +0 -0
.gitattributes
CHANGED
|
@@ -5724,3 +5724,17 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_14158148104910247593+0662544f/model.neff fi
|
|
| 5724 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_16168659915187360076+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5725 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_1989993258759457386+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5726 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_2024571157423918099+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5724 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_16168659915187360076+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5725 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_1989993258759457386+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5726 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_2024571157423918099+0662544f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5727 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5728 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5729 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5730 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5731 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_14731793871512305202+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5732 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_15483351146288424705+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5733 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_15788636837904843545+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5734 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_16607751994069438360+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5735 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_4951852759208268000+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5736 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_6058135137446111578+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5737 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_6306540268657633107+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5738 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_6710511417232479112+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5739 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_7554382855996901429+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5740 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_9418049537737090985+ebf00a7f/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/09f3cdf1e695f554bbfb.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 640], "chosen_input_ids": [1, 640], "chosen_labels": [1, 640], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 640], "prompt_input_ids": [1, 640], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 640], "rejected_input_ids": [1, 640], "rejected_labels": [1, 640], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/34d5c50f3539e73531f6.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/44f4532ed4d9bb143dfa.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/51271d7790b315d59b4d.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 640], "chosen_input_ids": [1, 640], "chosen_labels": [1, 640], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 640], "prompt_input_ids": [1, 640], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 640], "rejected_input_ids": [1, 640], "rejected_labels": [1, 640], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/701b435f22762b79be41.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 608], "chosen_input_ids": [1, 608], "chosen_labels": [1, 608], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 608], "prompt_input_ids": [1, 608], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 608], "rejected_input_ids": [1, 608], "rejected_labels": [1, 608], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/9babb4958cc9d418f609.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 1024], "chosen_input_ids": [1, 1024], "chosen_labels": [1, 1024], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 1024], "prompt_input_ids": [1, 1024], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 1024], "rejected_input_ids": [1, 1024], "rejected_labels": [1, 1024], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/9eab79ca9f620713c3b6.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 608], "chosen_input_ids": [1, 608], "chosen_labels": [1, 608], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 608], "prompt_input_ids": [1, 608], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 608], "rejected_input_ids": [1, 608], "rejected_labels": [1, 608], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/a9dc231a54d26bc25b15.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["To calculate the probability of rolling a sum of 7 with two 6-sided dice, we first need to find the total number of outcomes and the favorable outcomes. There are 6 sides on each die, so the total number of outcomes when rolling two dice is 6 * 6 = 36. Now, we need to find the combinations of rolls that add up to 7: (1, 6), (2, 5), (3, 4), (4, 3), (5, 2), and (6, 1). There are 6 favorable outcomes. To find the probability, divide the favorable outcomes by the total outcomes: 6 (favorable) / 36 (total) = 1/6. So the probability of rolling a sum of 7 with two 6-sided dice is 1/6 or roughly 16.67%."], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["Explain how to calculate the probability of rolling a sum of 7 using two 6-sided dice."], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["Explain how to calculate the probability of rolling a sum of 7 using two 6-sided dice."], "rejected": ["To calculate the probability of rolling a sum of 7 with two 6-sided dice, we first need to find the total number of outcomes and the favorable outcomes. There are 6 sides on each die, so the total number of outcomes when rolling two dice is 6 * 6 = 36. Now, we need to find the combinations of rolls that add up to 7: (1, 6), (2, 5), (3, 4), (4, 3), (5, 2), and (6, 1). There are 6 favorable outcomes. To find the probability, divide the favorable outcomes by the total outcomes: 6 (favorable) / 36 (total) = 1/6. So the probability of rolling a sum of 7 with two 6-sided dice is 1/6 or roughly 16.67%."], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["General-Instruct"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/aa212064b8aa2edddfdd.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 576], "chosen_input_ids": [1, 576], "chosen_labels": [1, 576], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 576], "prompt_input_ids": [1, 576], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 576], "rejected_input_ids": [1, 576], "rejected_labels": [1, 576], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/b093f9809ea1fa7a307b.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["40 * 865 = 34600"], "chosen_attention_mask": [1, 512], "chosen_input_ids": [1, 512], "chosen_labels": [1, 512], "prompt": ["Find 40 * 865. Exclude words; show only the math."], "prompt_attention_mask": [1, 512], "prompt_input_ids": [1, 512], "question": ["Find 40 * 865. Exclude words; show only the math."], "rejected": ["34,600\n\n40 x 865 = 34,600 \n\nNote: The response is purely numerical and does not contain any words or text that are not required for the calculation. It is helpful, accurate, truthful, and harmless. The final result is 34,600."], "rejected_attention_mask": [1, 512], "rejected_input_ids": [1, 512], "rejected_labels": [1, 512], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/beee0da2cee55a14898c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 768], "chosen_input_ids": [1, 768], "chosen_labels": [1, 768], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 768], "prompt_input_ids": [1, 768], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 768], "rejected_input_ids": [1, 768], "rejected_labels": [1, 768], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/d9baeaee7d31148c77bd.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 1024], "chosen_input_ids": [1, 1024], "chosen_labels": [1, 1024], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 1024], "prompt_input_ids": [1, 1024], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 1024], "rejected_input_ids": [1, 1024], "rejected_labels": [1, 1024], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/e0790333588e5b65fe53.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "chosen_attention_mask": [1, 768], "chosen_input_ids": [1, 768], "chosen_labels": [1, 768], "prompt": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "prompt_attention_mask": [1, 768], "prompt_input_ids": [1, 768], "question": ["What popular children's book series features a young orphaned wizard attending a magical school called Hogwarts?"], "rejected": ["The Harry Potter series, written by J.K. Rowling, follows the life of a young wizard, Harry Potter, and his friends Hermione Granger and Ron Weasley, all of whom are students at Hogwarts School of Witchcraft and Wizardry. This beloved book series consists of seven books, beginning with Harry's acceptance into Hogwarts and culminating with his final battle against the dark wizard, Lord Voldemort."], "rejected_attention_mask": [1, 768], "rejected_input_ids": [1, 768], "rejected_labels": [1, 768], "source": ["Airoboros"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/training/llama/meta-llama/Llama-3.2-1B/fbcf4b0b066c41a371e3.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "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": ["The sum of 9319357631 and 595 is 9319358226."], "chosen_attention_mask": [1, 576], "chosen_input_ids": [1, 576], "chosen_labels": [1, 576], "prompt": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "prompt_attention_mask": [1, 576], "prompt_input_ids": [1, 576], "question": ["Assist me in calculating 9319357631 plus 595. Numbers and symbols only, please."], "rejected": ["The result of adding 9319357631 and 595 is 9319363626."], "rejected_attention_mask": [1, 576], "rejected_input_ids": [1, 576], "rejected_labels": [1, 576], "source": ["GOAT"], "system": [null]}, "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, "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": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b983224ad94626d1e250599685c623eb3a606ed0ea133c3bc06dffaedb6839f6
|
| 3 |
+
size 468836
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10205760333230881129+ebf00a7f/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:078ac011925f7df859eb42f2eb13296a2cdd879693c306bf04d20dde3531ed89
|
| 3 |
+
size 20194304
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--disable-dge"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d570b930c013bf267177246d19bbdd10675be2cc5915d2ce5d381f2781ed95c6
|
| 3 |
+
size 9806
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_10239310764362802834+beef23cf/model.neff
ADDED
|
Binary file (11.3 kB). View file
|
|
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00a365a1683e57b8c067495bae10fb70490d4803728a56a06b50708e387e70d7
|
| 3 |
+
size 469028
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1115425843438104727+ebf00a7f/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d952f6dab9b7e8806e81298330ca1903018aabc6e0497898bffac8e90e5d2e
|
| 3 |
+
size 36578304
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd840c1a0c7077f5c4b7c5e3d3a010cbda38b0c400fde6b256f3a01e3039db3
|
| 3 |
+
size 393584
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_1131570854049582627+ebf00a7f/model.log
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Failed compilation with ['neuronx-cc', 'compile', '--target=trn1', '--framework=XLA', '/tmp/no-user/neuroncc_compile_workdir/bfb56763-4282-4aac-b054-291b35486cda/model.MODULE_1131570854049582627+ebf00a7f.hlo_module.pb', '--output', '/tmp/no-user/neuroncc_compile_workdir/bfb56763-4282-4aac-b054-291b35486cda/model.MODULE_1131570854049582627+ebf00a7f.neff', '--model-type=transformer', '--distribution-strategy=llm-training', '--enable-saturate-infinity', '--verbose=35']: 2024-10-23T10:57:49Z Warning: Non-output memory location with no reader: {_multiply.3.83822_i0}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 2 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i1}@SB<0,49224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 3 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i2}@SB<0,51224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 4 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i3}@SB<0,19472>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 5 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i4}@SB<0,30792>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 6 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i5}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 7 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i6}@SB<0,49224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 8 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i7}@SB<0,51224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 9 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i8}@SB<0,49224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 10 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i9}@SB<0,18448>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 11 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i10}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 12 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i11}@SB<0,20496>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 13 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i12}@SB<0,17448>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 14 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i13}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 15 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i14}@SB<0,21512>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 16 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i15}@SB<0,17432>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 17 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i16}@SB<0,18456>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 18 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i17}@SB<0,23568>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 19 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i18}@SB<0,29712>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 20 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i19}@SB<0,49224>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 21 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i20}@SB<0,19488>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 22 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i21}@SB<0,20512>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 23 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i22}@SB<0,17432>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 24 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i23}@SB<0,23576>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 25 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i24}@SB<0,32848>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 26 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i25}@SB<0,33888>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 27 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i26}@SB<0,34912>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 28 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i27}@SB<0,35936>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 29 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i28}@SB<0,36960>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 30 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i29}@SB<0,37984>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 31 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i30}@SB<0,39008>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 32 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i31}@SB<0,40032>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 33 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i32}@SB<0,17464>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 34 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i33}@SB<0,18504>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 35 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i34}@SB<0,19528>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 36 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i35}@SB<0,20552>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 37 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i36}@SB<0,21576>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 38 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i37}@SB<0,22600>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 39 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i38}@SB<0,23624>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 40 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i39}@SB<0,24648>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 41 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i40}@SB<0,41024>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 42 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i41}@SB<0,59496>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 43 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i42}@SB<0,43088>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 44 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i43}@SB<0,44112>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 45 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i44}@SB<0,45136>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 46 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i45}@SB<0,46160>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 47 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i46}@SB<0,49216>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 48 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i47}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 49 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i48}@SB<0,25664>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 50 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i49}@SB<0,26704>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 51 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i50}@SB<0,27728>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 52 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i51}@SB<0,28752>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 53 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i52}@SB<0,29776>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 54 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i53}@SB<0,30800>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 55 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i54}@SB<0,32784>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 56 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i55}@SB<0,33808>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 57 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i56}@SB<0,43080>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 58 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i57}@SB<0,44120>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 59 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i58}@SB<0,45144>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 60 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i59}@SB<0,46168>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 61 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i60}@SB<0,47192>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 62 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i61}@SB<0,16392>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 63 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i62}@SB<0,17416>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 64 |
+
Warning: Non-output memory location with no reader: {_multiply.3.83822_i63}@SB<0,18440>(128x1024)#Internal DebugInfo: <_multiply.3.83822||UNDEF||[128, 512, 1]>
|
| 65 |
+
[XCG815] Estimated peak HBM usage (16.571175) exceeds 16GB. Neff won't be able to load on chip - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3ff06f5a38a9c4089816b5ddbceddec3884a8c1d97daaddc49dd2e66a978daf
|
| 3 |
+
size 4936
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11325112573478867302+ebf00a7f/model.neff
ADDED
|
Binary file (185 kB). View file
|
|
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779ce19e314d4ec476e002fe209fc271731e0b5932c7b80efa54471b6dc96012
|
| 3 |
+
size 393584
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11628730652885210344+ebf00a7f/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f5c32513912e411404185a69de3ed12b4718361fa0bff9bc3739f2bc17e93d1
|
| 3 |
+
size 35738624
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab74212aeb5da32ef6f782daa88f82f3769a8938069e1c7596523df0fa521ba
|
| 3 |
+
size 4936
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_11765127214337168369+ebf00a7f/model.neff
ADDED
|
Binary file (185 kB). View file
|
|
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--distribution-strategy=llm-training", "--enable-saturate-infinity"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad3b8fbb9b6c60a2db140f35cd8c73d16e4fa22ee353bae58a035a48b4d552a7
|
| 3 |
+
size 393584
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_12416333974599687466+ebf00a7f/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5d800c46000a8656a5f42c60141413294706bb51c60025647a6385ae8e54c76
|
| 3 |
+
size 35769344
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--disable-dge"]
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22241725f29f733abb6b105db6d34444b8a2a9012c9ad865d0405e4c2bf09414
|
| 3 |
+
size 11954
|
neuronxcc-2.15.128.0+56dc5a86/MODULE_14257389128153740019+beef23cf/model.neff
ADDED
|
Binary file (11.3 kB). View file
|
|
|