Upload optimized ONNX model

#1
by Xenova HF Staff - opened
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -53,5 +53,15 @@
53
  "transformers_version": "5.3.0.dev0",
54
  "use_cache": true,
55
  "v_head_dim": 16,
56
- "vocab_size": 32000
57
- }
 
 
 
 
 
 
 
 
 
 
 
53
  "transformers_version": "5.3.0.dev0",
54
  "use_cache": true,
55
  "v_head_dim": 16,
56
+ "vocab_size": 32000,
57
+ "transformers.js_config": {
58
+ "use_external_data_format": {
59
+ "model.onnx": 1,
60
+ "model_fp16.onnx": 1
61
+ },
62
+ "kv_cache_dtype": {
63
+ "q4f16": "float16",
64
+ "fp16": "float16"
65
+ }
66
+ }
67
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc38fd8c09185dc2df35cd65b788ed03478f84e1036cecbdc60a2ecf41db163f
3
+ size 78739
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422cb890b1b106c02e9998c491124310dc4cb68d29d629abbf00085becd07b6d
3
+ size 83795968
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:250ed31a00cd286f2d7d621187cebcb65b4daf35c42f664bbc0746b123b594d8
3
+ size 78537
onnx/model_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72229d04d311f13969043d0969fcbe81f927e64c5a419535333a4dc16a22d5f2
3
+ size 41896960
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -14,4 +14,4 @@
14
  "tokenizer_class": "TokenizersBackend",
15
  "unk_token": "<unk>",
16
  "use_default_system_prompt": false
17
- }
 
14
  "tokenizer_class": "TokenizersBackend",
15
  "unk_token": "<unk>",
16
  "use_default_system_prompt": false
17
+ }