Remove sharded checkpoints, add torch checkpoint

model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da0f12aa6562672e8ca46bc1a1749709b54bb8c9ce221d8b0174a083681befbc
-size 131208

model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:84bd6702becf9c83f53db9b81f7be84fa432d696d91a88de241551f06c9119c8
-size 120368

model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6a184dc03fbcd67ca7acd4712f2bdefc90f015b04e88c2779ce3fe7a6359e259
-size 96332

model.safetensors.index.json

@@ -1,94 +0,0 @@
-{
-  "metadata": {
-    "total_size": 338916
-  },
-  "weight_map": {
-    "embeddings.LayerNorm.bias": "model-00002-of-00003.safetensors",
-    "embeddings.LayerNorm.weight": "model-00002-of-00003.safetensors",
-    "embeddings.position_embeddings.weight": "model-00002-of-00003.safetensors",
-    "embeddings.token_type_embeddings.weight": "model-00002-of-00003.safetensors",
-    "embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
-    "encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.output.dense.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.output.dense.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.key.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.key.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.query.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.query.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.value.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.attention.self.value.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.intermediate.dense.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.intermediate.dense.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.output.dense.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.0.output.dense.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.output.dense.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.output.dense.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.key.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.key.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.query.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.query.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.value.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.attention.self.value.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.intermediate.dense.bias": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.intermediate.dense.weight": "model-00002-of-00003.safetensors",
-    "encoder.layer.1.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.1.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.1.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.1.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.key.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.key.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.query.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.query.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.value.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.attention.self.value.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.intermediate.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.intermediate.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.2.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.key.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.key.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.query.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.query.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.value.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.attention.self.value.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.intermediate.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.intermediate.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.3.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.output.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.key.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.key.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.query.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.query.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.value.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.attention.self.value.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.intermediate.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.intermediate.dense.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.output.dense.bias": "model-00003-of-00003.safetensors",
-    "encoder.layer.4.output.dense.weight": "model-00003-of-00003.safetensors",
-    "pooler.dense.bias": "model-00003-of-00003.safetensors",
-    "pooler.dense.weight": "model-00003-of-00003.safetensors"
-  }
-}