Delete neuronxcc-2.15.143.0+e39249ad
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/22d17726e80ea55ae614.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/c343f7380f55f6bcceb5.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/d24d5570ae47fe88f7b7.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/de3d9e9a788067e92122.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/4538babd01182da34f41.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b40a794eff5ea470980f.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cdbdbf737272e98ae974.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/9125a78a53c4a0cd3507.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/aadac442fccfdd730bb5.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1f8668afaa87da7a4bc8.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/9055305e649c4ec32010.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af0ef68e4ec57e23cab5.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/e0c5534b610fbfb22b6e.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/0f046bbc33ab9d958fb0.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/b84feef8cecdb653f9a1.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/cdbb338b118c52802f02.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/granite/ibm-granite/granite-3.0-8b-instruct/89417199e26022010c7a.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/ff84bf8571014fc7a409.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/1ef3929e28ba91cc3cc6.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/71ec0a49c3535c618d03.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/eb3f26aa23141bff2292.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-13b-hf/94a031376aca05feef95.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/492f4a4a917dc8083206.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/700855cc8de9f05769b3.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-7b-hf/d93b4a3112ca56e2c754.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/066ec28242196b515c20.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/89875844c977bbe3f437.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/ec8a0a31a1ed3dfcee63.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/ecb8bd87e8237d81a4b7.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.2-1B/73d51cab3becd68ac842.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.2-3B/b46e891eeb5590cf2153.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-70B/b09c46bcc4f4543ace31.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-70B/f37e7e7421dd81889f47.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d5b2eb18cb07a01849a9.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/1b18351b079da6ecb559.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/362d66661fe62f0014b6.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/397b81d879ef583354a9.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4f1d0113672438882651.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/56b2c3315dda7cd3a4e6.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/a8897274a056db93a0db.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/f997d25c8b7363a830ac.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/272ae02cb2ee5dc319d1.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/b583d8ca856d4fb50088.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/03684cb7daca4d6b4e65.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/2889a8dede530dd92ff3.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/3f7985a3f441b4c6bc9c.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/7b6cb2e90062119fb6b7.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/a92f54c8ed379dc67ced.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/b50522d2e2c48d2d0f26.json +0 -1
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/Intel/neural-chat-7b-v3-3/70a4d98b2fb0efedacf4.json +0 -1
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/22d17726e80ea55ae614.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "1", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "position_embedding_type": "absolute", "task": "text-classification", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/c343f7380f55f6bcceb5.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "dynamic_batch_size": true, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "position_embedding_type": "absolute", "task": "text-classification", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/d24d5570ae47fe88f7b7.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "3", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "position_embedding_type": "absolute", "task": "text-classification", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bert/hf-internal-testing/tiny-random-BertModel/de3d9e9a788067e92122.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["BertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 16, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "position_embedding_type": "absolute", "task": "text-classification", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1124}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/4538babd01182da34f41.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": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b40a794eff5ea470980f.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": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cdbdbf737272e98ae974.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": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/9125a78a53c4a0cd3507.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": 1, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 128, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/aadac442fccfdd730bb5.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": "fp16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1f8668afaa87da7a4bc8.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": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/9055305e649c4ec32010.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": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 512, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af0ef68e4ec57e23cab5.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": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/e0c5534b610fbfb22b6e.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": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/0f046bbc33ab9d958fb0.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": "fp16", "batch_size": 16, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/b84feef8cecdb653f9a1.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": "fp16", "batch_size": 4, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/gpt2/openai-community/gpt2/cdbb338b118c52802f02.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": "fp16", "batch_size": 1, "checkpoint_id": "openai-community/gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/granite/ibm-granite/granite-3.0-8b-instruct/89417199e26022010c7a.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.0078125, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12800, "logits_scaling": 16.0, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm-granite/granite-3.0-8b-instruct", "checkpoint_revision": "8fe1e202a17f7763bd0af471253e00cc846d1c05", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/ff84bf8571014fc7a409.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/1ef3929e28ba91cc3cc6.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/71ec0a49c3535c618d03.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/llamafactory/tiny-random-Llama-3/eb3f26aa23141bff2292.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-13b-hf/94a031376aca05feef95.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-hf", "checkpoint_revision": "5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/492f4a4a917dc8083206.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": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-70b-chat-hf", "checkpoint_revision": "e9149a12809580e8602995856f8098ce973d1080", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-70b-chat-hf/700855cc8de9f05769b3.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": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-70b-chat-hf", "checkpoint_revision": "e9149a12809580e8602995856f8098ce973d1080", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-2-7b-hf/d93b4a3112ca56e2c754.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-hf", "checkpoint_revision": "01c7f73d771dfac7d292323805ebc428287df4f9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/066ec28242196b515c20.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-70B-Instruct", "checkpoint_revision": "1605565b47bb9346c5515c34102e054115b4f98b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/89875844c977bbe3f437.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.1-70B-Instruct", "checkpoint_revision": "1605565b47bb9346c5515c34102e054115b4f98b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/ec8a0a31a1ed3dfcee63.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.1-70B-Instruct", "checkpoint_revision": "945c8663693130f8be2ee66210e062158b2a9693", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.1-70B-Instruct/ecb8bd87e8237d81a4b7.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-70B-Instruct", "checkpoint_revision": "945c8663693130f8be2ee66210e062158b2a9693", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.2-1B/73d51cab3becd68ac842.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 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": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-1B", "checkpoint_revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Llama-3.2-3B/b46e891eeb5590cf2153.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-3B", "checkpoint_revision": "13afe5124825b4f3751f836b40dafda64c1ed062", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 24, "num_hidden_layers": 28, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-70B/b09c46bcc4f4543ace31.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-70B", "checkpoint_revision": "c82494877ce7f6d7d317c56ec081328e382c72fe", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-70B/f37e7e7421dd81889f47.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-70B", "checkpoint_revision": "c82494877ce7f6d7d317c56ec081328e382c72fe", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/d5b2eb18cb07a01849a9.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/1b18351b079da6ecb559.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/362d66661fe62f0014b6.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/397b81d879ef583354a9.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/4f1d0113672438882651.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/56b2c3315dda7cd3a4e6.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/a8897274a056db93a0db.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/meta-llama/Meta-Llama-3.1-8B/f997d25c8b7363a830ac.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3.1-8B", "checkpoint_revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "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": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
|
|
|
|
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/272ae02cb2ee5dc319d1.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/b583d8ca856d4fb50088.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/03684cb7daca4d6b4e65.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/2889a8dede530dd92ff3.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/3f7985a3f441b4c6bc9c.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": 8, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/7b6cb2e90062119fb6b7.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/a92f54c8ed379dc67ced.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/b50522d2e2c48d2d0f26.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": 16, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "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-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/mistral/Intel/neural-chat-7b-v3-3/70a4d98b2fb0efedacf4.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "Intel/neural-chat-7b-v3-3", "checkpoint_revision": "7506dfc5fb325a8a8e0c4f9a6a001671833e5b8e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "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": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
|
|
|
|
|