Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
- Phi3Unlocked.f16.gguf +3 -0
- Phi3Unlocked.q5_k.gguf +3 -0
- Phi3Unlocked.q6_k.gguf +3 -0
- Phi3Unlocked.q8_0.gguf +3 -0
- Phi3Unlocked.q8_p.gguf +3 -0
- Phi3Unlocked.q8q4.gguf +3 -0
- README.md +17 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,9 @@ 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 |
+
Phi3Unlocked.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Phi3Unlocked.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Phi3Unlocked.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Phi3Unlocked.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Phi3Unlocked.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
Phi3Unlocked.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
|
Phi3Unlocked.f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51e0d38e597b5af3a3ae3f21928509cdbc11ecd088d02113d13d07468bb3911e
|
| 3 |
+
size 7643296320
|
Phi3Unlocked.q5_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9c0ecfe10dc569d2df3cb796bdce3454bd8e8ea6fd8f9a63398d1db2b02ab78
|
| 3 |
+
size 3060757056
|
Phi3Unlocked.q6_k.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a55c95c7d155efedbb03dade1fe5bd7972825cfe77317c55035c12dcad4a45f3
|
| 3 |
+
size 3368251968
|
Phi3Unlocked.q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:648324136e551711f7486b522a9968f636702c58a4e65715a28b76dd1fce8568
|
| 3 |
+
size 4245910080
|
Phi3Unlocked.q8_p.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f34bb5c798502e7f80faeb328d941cb0233cf1d106fe840aafc6200ff27a54e4
|
| 3 |
+
size 4061221440
|
Phi3Unlocked.q8q4.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3c433a0914107e008f34e45d81419f95567ce12ecef5df39ef50ad5e7e238b7
|
| 3 |
+
size 2466337344
|
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: mit
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
My own (ZeroWw) quantizations.
|
| 10 |
+
output and embed tensors quantized to f16.
|
| 11 |
+
all other tensors quantized to q5_k or q6_k.
|
| 12 |
+
|
| 13 |
+
Result:
|
| 14 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
| 15 |
+
and they perform as well as the pure f16.
|
| 16 |
+
|
| 17 |
+
Updated on: Fri Oct 25, 14:14:40
|