upload int8 model

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "jimypbr/bert-base-uncased-squad",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "device_iterations": 2,
+  "embedding_serialization_factor": 0,
+  "enable_half_first_order_momentum": true,
+  "enable_half_partials": true,
+  "executable_cache_dir": "./exe_cache",
+  "gradient_accumulation_steps": 16,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "inference_device_iterations": 4,
+  "inference_replication_factor": 4,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "ipus_per_replica": 4,
+  "layer_norm_eps": 1e-12,
+  "layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "matmul_proportion": [
+    0.25,
+    0.2,
+    0.2,
+    0.25
+  ],
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "optimizer_state_offchip": false,
+  "optimum_version": "0.1.2",
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "profile_dir": null,
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": null,
+  "synthetic_data": false,
+  "torch_dtype": "int8",
+  "transformers_version": "4.21.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "use_popdist": false,
+  "vocab_size": 30522
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e120d80f8694cc7f2c2fa5b2e36760d2f10123c5ec6421a2f4548f66cdc3bcc
+size 49265116

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cd15e7d7eb1aa870a8ee9ac571c05435f8b1d68935991f1f170d8f0166c597
+size 139323541

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "jimypbr/bert-base-uncased-squad",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36dce23f296aefd11338f087f5ec0659d23135a8d2b73f8883057e0e06e75dfc
+size 3311