Synchronizing local compiler cache.

.gitattributes

@@ -1542,3 +1542,4 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_f37ba14e8cecd0289618+39f12043/model.neff fi
 neuronxcc-2.15.143.0+e39249ad/MODULE_f6695fce8439b8324614+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.143.0+e39249ad/MODULE_113edf6039829677d7d6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.15.143.0+e39249ad/MODULE_a4bb4e6e225de0782e33+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/model.neuron filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev1/inference/albert/hf-internal-testing/tiny-random-AlbertModel/4d29ce95cb17d18f69e6.json

@@ -0,0 +1 @@
+{"_attn_implementation_autoset": true, "architectures": ["AlbertModel"], "attention_probs_dropout_prob": 0.1, "classifier_dropout_prob": 0.1, "embedding_size": 128, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 36, "initializer_range": 0.02, "inner_group_num": 1, "intermediate_size": 37, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "albert", "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 32, "tensor_parallel_size": 1}, "num_attention_heads": 6, "num_hidden_groups": 6, "num_hidden_layers": 6, "position_embedding_type": "absolute", "task": "feature-extraction", "type_vocab_size": 16, "vocab_size": 30000}

neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.28.dev1/inference/mixtral/dacorvo/Mixtral-tiny/7a2d784983216beac6b9.json

@@ -0,0 +1 @@
+{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 32, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 1024, "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, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.15.143.0+e39249ad/MODULE_12626660774007863165+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.143.0+e39249ad/MODULE_12626660774007863165+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:893551b9ef9c14337534ace7b65bbc273b45013967c89128e8dfa9b3400d6ced
+size 24949

neuronxcc-2.15.143.0+e39249ad/MODULE_13380170886023092797+d7517139/compile_flags.json

@@ -0,0 +1 @@
+[]

neuronxcc-2.15.143.0+e39249ad/MODULE_13380170886023092797+d7517139/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df189034a6c3e2fb6dd576c5c3560685d36df41ae639190ea3651f2e266be69f
+size 24869

neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/config.json

@@ -0,0 +1,57 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "hf-internal-testing/tiny-random-AlbertModel",
+  "architectures": [
+    "AlbertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 36,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 37,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "neuron": {
+    "auto_cast": null,
+    "auto_cast_type": null,
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.15.143.0+e39249ad",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": true,
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "input_ids",
+      "attention_mask",
+      "token_type_ids"
+    ],
+    "model_type": "albert",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "last_hidden_state",
+      "pooler_output"
+    ],
+    "static_batch_size": 1,
+    "static_sequence_length": 32,
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 6,
+  "num_hidden_groups": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task": "feature-extraction",
+  "torchscript": true,
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 16,
+  "vocab_size": 30000
+}

neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92163373d98b005c4e687572ccedf3799edc3750c18e560d65d57420b546e1fe
+size 14598461

neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neuronxcc-2.15.143.0+e39249ad/MODULE_4d29ce95cb17d18f69e6/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}