Add model weights and configuration

README.md

@@ -0,0 +1,19 @@
+---
+language: en
+license: apache-2.0
+datasets:
+- sst-2
+---
+
+# DistilBERT base uncased finetuned SST-2
+
+This model is a fine-tune checkpoint of [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased), fine-tuned on SST-2.
+This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).
+
+# Fine-tuning hyper-parameters
+
+- learning_rate = 1e-5
+- batch_size = 32
+- warmup = 600
+- max_seq_length = 128
+- num_train_epochs = 3.0

config.json

@@ -0,0 +1,31 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60554cbd7781b09d87f1ececbea8c064b94e49a7f03fd88e8775bfe6cc3d9f88
+size 267844284

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44df675bb34ccd8e57c14292c811ac7358b7c8e37c7f212745f640cd6019ac8
+size 267949840

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512, "do_lower_case": true}