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 +1 -1
- onnx/model_q4.onnx +2 -2
- onnx/model_q4.onnx_data +2 -2
- onnx/model_q4.onnx_data_1 +2 -2
- onnx/model_q4.onnx_data_2 +0 -3
- onnx/model_q4f16.onnx +2 -2
- onnx/model_q4f16.onnx_data +2 -2
- onnx/model_q4f16.onnx_data_1 +2 -2
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":
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2da05f44e8d8ad18540d7b9ac29c006b264f2ddd58c34541981db6651b33e06f
|
| 3 |
+
size 1531781120
|