Xenova HF Staff commited on
Commit
3bad3d7
·
1 Parent(s): c68e0a2

Improve q4 weights (#1)

Browse files

- Upload folder using huggingface_hub (f047fb0fa5ccdfa52145ad7ba18d0d41e08d477f)
- Delete onnx/model_q4.onnx_data_2 (75a34fd8f02926fa410d018b8b3c053d47a41c93)
- Update config.json (a08a9330582c97e4d0bf05821a458239de831303)

config.json CHANGED
@@ -108,7 +108,7 @@
108
  "model.onnx": 13,
109
  "model_fp16.onnx": 6,
110
  "model_quantized.onnx": 4,
111
- "model_q4.onnx": 3,
112
  "model_q4f16.onnx": 2
113
  },
114
  "kv_cache_dtype": {
 
108
  "model.onnx": 13,
109
  "model_fp16.onnx": 6,
110
  "model_quantized.onnx": 4,
111
+ "model_q4.onnx": 2,
112
  "model_q4f16.onnx": 2
113
  },
114
  "kv_cache_dtype": {
onnx/model_q4.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:690116b42e50e568ae8a14ff1f26d6c6ab97df4f7c4c6d6e3d3a34ed02418b43
3
- size 1125424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c85bd493c756ab69674f8832c8600cab32bc270bc39aa6df9d6d070f30afdb
3
+ size 1207309
onnx/model_q4.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aab412296a1642e4949a3db1f27ac8884739a86484e1b0158660b80ad1e0f12b
3
- size 2090987520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e69b2b74bcf72a1be91e07305c2fa3db310f62879800feb846ee227ba3baf8
3
+ size 2096230400
onnx/model_q4.onnx_data_1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:777afb9980120da6084bd0110e96219c59189aab8ed3cef88b151d4f3234af53
3
- size 2076180480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ace2998a232f4e28c39810521d8a69ad0c9f1501c12ec72f8f12af11e49e99c
3
+ size 2082971648
onnx/model_q4.onnx_data_2 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a0273aa3869c8271006e46ed7291f03b0878cdf804a48ded5330685f1160674
3
- size 426815488
 
 
 
 
onnx/model_q4f16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42d1305825274e5425a9c0dce9e476346f0774a49d7439ad77fe9eced95c578b
3
- size 1363317
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21014169edcaef142d1ff023476ecba32049bb5297c5ba0b87533a8f3be052f
3
+ size 1445578
onnx/model_q4f16.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2a0747ecc6f1d9275455d4f1cff3a89705866c840031b28cfe41fb984155e35
3
- size 2092855296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f8bb47562a2c3b1dd148c662fb4f403335c791a9c10ca4c6bbea34fb0d4eb0c
3
+ size 2072408064
onnx/model_q4f16.onnx_data_1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:815c7a858bccfa2ace9d7a177887fb36210729344ad2d20416ca90fb6a9f08ec
3
- size 1686892544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da05f44e8d8ad18540d7b9ac29c006b264f2ddd58c34541981db6651b33e06f
3
+ size 1531781120