Quantized Models (#9)

- updated quantized models (a0604e28df2d1ed8f79810872b85c027f02945ce)

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "AutoTrain",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "KoalaAI/Text-Moderation",
   "_num_labels": 9,
   "architectures": [
     "DebertaForSequenceClassification"
@@ -50,8 +51,7 @@
   ],
   "position_biased_input": false,
   "relative_attention": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.46.1",
   "type_vocab_size": 0,
   "vocab_size": 50265
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697d2cce4b6468b385f45b5b6504767dd7ed663f6d2abf4522d3350ee88ea9c7
-size 557347903
+oid sha256:fad115a8cd91eb803fb278249024fd9be85ec3566e996a19ba0c3d55f49379c5
+size 557224900

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5245778f5c4f80f3ffa9bc756a6e07b2749b6bfe24b7cdfb513d756c687085
+size 216612754

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5bb69d6f7ea1b3fe17aa70fea1498b0752e6380c5502de588dee781ca55c2c
+size 278826418

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f453d21e8e4dd42acf90bd8cc67e04ca1490b5987279778df65208d05e45f5c1
+size 142967535

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c8d652d6cc8c599dcc7131421fea58bf6af0cf5c6544a3a474bce2f2a1a270
+size 222805366

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6afc17ea9577a47c0bcb14f0e23a6101ea43b5af5c08c89b8099de5fc35b50f
+size 136394668

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dcab041de741692239119e5967efcb197f1d4a1d1da3713bbbeee3a3e139a6
-size 143281992
+oid sha256:f453d21e8e4dd42acf90bd8cc67e04ca1490b5987279778df65208d05e45f5c1
+size 142967535

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6584dc5c064021c74314e463b11c1af853df4c662f28fce3db2af423ad31f977
+size 142967535

quantize_config.json

@@ -0,0 +1,17 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc39e4a9ef588149e8513a2d7e0d1cda450b1884a5f6c62a945d9ec1e5bdbfe4
-size 2109876
+oid sha256:02eccb4743ef6eeb5bf1fa77bca58cf5a42094ec91852a767e3825b1617f550b
+size 3559904

tokenizer_config.json

@@ -1,66 +1,66 @@
 {
   "add_bos_token": false,
   "add_prefix_space": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": {
-    "__type": "AddedToken",
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
   "do_lower_case": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "[SEP]",
   "errors": "replace",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "[MASK]",
+  "max_length": 384,
   "model_max_length": 512,
-  "pad_token": {
-    "__type": "AddedToken",
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "__type": "AddedToken",
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
   "tokenizer_class": "DebertaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
   "vocab_type": "gpt2"
 }