Delete neuronxcc-2.13.68.0+6dfecc895
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/NousResearch/Llama-2-13b-hf/88f5eb9e6ca24670f54a.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/NousResearch/Llama-2-13b-hf/c72ab389f76526a9f660.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/llama/meta-llama/Llama-2-7b-chat-hf/45e72c385f2c8f78486d.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/mistral/mistralai/Mistral-7B-v0.1/79175df896785fcde622.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/mistral/yam-peleg/Experiment31-7B/45c8b478d085d6ae8f6b.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b29d5f053c4c5af651f1.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/gpt2/gpt2/fae3ae23f13a4f428971.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/66264664d48765246aec.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/50584cef543338c1a262.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/dacorvo/tiny-random-llama/081859480b7ce66dc486.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/9f5a5c9456ddc5060e2d.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/20240adbdbe6ba19f27a.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/0a80519c6427c128c980.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/5ea5616c808e926ec6e8.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/7285c26ddf8adbbba87e.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/7703f460c4a2749c18bd.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mixtral/dacorvo/Mixtral-tiny/2e58aeb898a4a1bb4c62.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/03d3ea71eff9b2b849e4.json +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/model.hlo_module.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/model.hlo_module.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/model.neff +0 -0
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/model.neff +0 -0
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/model.hlo.pb +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/model.neff +0 -3
- neuronxcc-2.13.68.0+6dfecc895/MODULE_1147ab57421e09b0a487+2c2d707e/compile_flags.txt +0 -1
- neuronxcc-2.13.68.0+6dfecc895/MODULE_1147ab57421e09b0a487+2c2d707e/model.hlo_module.pb +0 -3
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/NousResearch/Llama-2-13b-hf/88f5eb9e6ca24670f54a.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "NousResearch/Llama-2-13b-hf", "checkpoint_revision": "b0491461253755d8c60bf22f0d696b9e337c6375", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 8, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/NousResearch/Llama-2-13b-hf/c72ab389f76526a9f660.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "NousResearch/Llama-2-13b-hf", "checkpoint_revision": "b0491461253755d8c60bf22f0d696b9e337c6375", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 8, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/llama/meta-llama/Llama-2-7b-chat-hf/45e72c385f2c8f78486d.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"compiler_version": "2.13.68.0+6dfecc895", "input_specs": {"attention_mask": [2, 512], "input_ids": [2, 512], "labels": [2, 512]}, "model_class": "LlamaForCausalLM", "num_neuron_cores_per_node": 64, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 8, "training": false}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/mistral/mistralai/Mistral-7B-v0.1/79175df896785fcde622.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"compiler_version": "2.13.68.0+6dfecc895", "input_specs": {"attention_mask": [2, 512], "input_ids": [2, 512], "labels": [2, 512]}, "model_class": "MistralForCausalLM", "num_neuron_cores_per_node": 64, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 8, "training": false}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.21/training/mistral/yam-peleg/Experiment31-7B/45c8b478d085d6ae8f6b.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"compiler_version": "2.13.68.0+6dfecc895", "input_specs": {"attention_mask": [2, 512], "input_ids": [2, 512], "labels": [2, 512]}, "model_class": "MistralForCausalLM", "num_neuron_cores_per_node": 64, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 8, "training": false}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b29d5f053c4c5af651f1.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/gpt2/gpt2/fae3ae23f13a4f428971.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp32", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/66264664d48765246aec.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/50584cef543338c1a262.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "f16", "batch_size": 4, "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "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": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/dacorvo/tiny-random-llama/081859480b7ce66dc486.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 256, "max_position_embeddings": 512, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-llama", "checkpoint_revision": "7fdafd2fe6a2d31c6abb72ae60db606d8bb23196", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 1, "num_hidden_layers": 1, "num_key_value_heads": 1, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/9f5a5c9456ddc5060e2d.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5504, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "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}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/20240adbdbe6ba19f27a.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/0a80519c6427c128c980.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "mistralai/Mistral-7b-Instruct-v0.2", "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/5ea5616c808e926ec6e8.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7b-Instruct-v0.2", "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/7285c26ddf8adbbba87e.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "mistralai/Mistral-7b-Instruct-v0.2", "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mistral/mistralai/Mistral-7b-Instruct-v0.2/7703f460c4a2749c18bd.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-7b-Instruct-v0.2", "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/mixtral/dacorvo/Mixtral-tiny/2e58aeb898a4a1bb4c62.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 131072, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "dce0e7b71159ad011c84de5a5bd9515bb9176220", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/0_REGISTRY/0.0.22.dev0/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/03d3ea71eff9b2b849e4.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp32", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.13.68.0+6dfecc895", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --auto-cast=none
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/model.hlo_module.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:38ab710ad9046d2dfcacc917847511a9bb053abfd30fe84b5e34c1d30232e1d6
|
| 3 |
-
size 346154
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_0406d654284cbd36a965+2c2d707e/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c80204bc415ecaeca2b692eb8f163553449c0f151091ec40a6345778a9ec34be
|
| 3 |
-
size 13128704
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --auto-cast=none
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/model.hlo_module.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0dd8e2bcc93dcb98decd1a2dc5e614aab49905707753c4805b381bb5b1e7575e
|
| 3 |
-
size 131100
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_05c54d3634daf421dee1+2c2d707e/model.neff
DELETED
|
Binary file (687 kB)
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:00a8c4ada3e5548c0c4f004dfbbc019350bbb0b229c166e53daa34cdfa6b16ec
|
| 3 |
-
size 581397
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10321151248243986212+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8f46dabdfd8c67de30308825ff6b30d1248ff0aa4774a0c865e1b650317fea5f
|
| 3 |
-
size 1414144
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:283f73ab4848d2d591fd4dcb50103a59c25944a210cf13e909c8e033a943d56f
|
| 3 |
-
size 581397
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10415564251552867075+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3f38128ae4d29b468d7d9a33c0e680d1121d2b53b5300a0059445172b8bccc9d
|
| 3 |
-
size 1414144
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ec076f3be235f619920f956156ab77c8ef98885540c90b4fa562e65816fa4121
|
| 3 |
-
size 579353
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10479010230249837840+55d6a20f/model.neff
DELETED
|
Binary file (984 kB)
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:397098d4d5b67eb3da1df00952b902e4bf4bc24abcfcae1ab3cf32b8565e47d7
|
| 3 |
-
size 3396295
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_10803941037092105663+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2a70d56c205d1fc4981282554169fb4c8202b7a7193ca9151717cc6210d09ac2
|
| 3 |
-
size 8254464
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cde2d6cf3e6170a0fa3d275e0bcffdba3e94f65b78a0329ac518b970b7aefb74
|
| 3 |
-
size 3480376
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11006361944182896657+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:132fe292d19dd7cc496e399da45ea5953f0b3a0e103906ebe3fc82609a8504fb
|
| 3 |
-
size 9186304
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:59928334cd796f2744cba6732fb3a2ed140845e627f6624694196057587404a0
|
| 3 |
-
size 3480411
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_110845439330275588+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e767a53cd7273a513d93aeb76902e862bf2f5281184f33fc1ae469151136e9b8
|
| 3 |
-
size 9186304
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:84a3981e41ea33ae78d289912a0ec5fd7b315da9ac7bd1990a0587ad987b78b1
|
| 3 |
-
size 3582575
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11274133061875925427+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d34e13f2a2cb1f1a21fc20a04daa98a4598c9e6cc4af7430781780515e7a7851
|
| 3 |
-
size 10046464
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --distribution-strategy=llm-training --enable-saturate-infinity -O2 --model-type=transformer
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/model.hlo.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e754a6cd207837cf526776599b95d75841bf44627c1dd82a9c3f3eb8138b2ae5
|
| 3 |
-
size 3580531
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_11286488092871774928+55d6a20f/model.neff
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a6023998176fdfc0bf1f24bda32524ca4440257d16b6c56761def92f65a39417
|
| 3 |
-
size 8745984
|
|
|
|
|
|
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_1147ab57421e09b0a487+2c2d707e/compile_flags.txt
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
--model-type=transformer --auto-cast=none
|
|
|
|
|
|
neuronxcc-2.13.68.0+6dfecc895/MODULE_1147ab57421e09b0a487+2c2d707e/model.hlo_module.pb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1c6439395d96a39416dd263c63464d2d56672b82d048c3665e586bd15ca196ae
|
| 3 |
-
size 57813
|
|
|
|
|
|
|
|
|
|
|
|