Upload folder using huggingface_hub
Browse files- .gitattributes +5 -0
- Mistral-7B-Instruct-v0.3.f16.gguf +3 -0
- Mistral-7B-Instruct-v0.3.q5_k.gguf +3 -0
- Mistral-7B-Instruct-v0.3.q6_k.gguf +3 -0
- Mistral-7B-Instruct-v0.3.q8_0.gguf +3 -0
- Mistral-7B-Instruct-v0.3.q8_p.gguf +3 -0
- README.md +16 -0
.gitattributes
CHANGED
@@ -33,3 +33,8 @@ 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 |
+
Mistral-7B-Instruct-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mistral-7B-Instruct-v0.3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mistral-7B-Instruct-v0.3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mistral-7B-Instruct-v0.3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Mistral-7B-Instruct-v0.3.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
Mistral-7B-Instruct-v0.3.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d72a0b2e3ad353195e88875705ad2d5f2d56cd2a54e77479519b8f3ee949ea8a
|
3 |
+
size 14497338176
|
Mistral-7B-Instruct-v0.3.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51de8e5e4abe5a0ce6f62d81729d9e6e956d80adf1bb5a22c75fc80b981f3529
|
3 |
+
size 5470671680
|
Mistral-7B-Instruct-v0.3.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30eea4b854f35095cc0f44017c315a46725629bcd86e4b45e2b7899463554d10
|
3 |
+
size 6263919424
|
Mistral-7B-Instruct-v0.3.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d441f655d8cd1878131d6dc19327fff40d0e08b54c4d1864eb2cd8373257403
|
3 |
+
size 7954223936
|
Mistral-7B-Instruct-v0.3.q8_p.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56ff3a6176474304ccaba670ab2404517f5147b426d56134a79ec3a25fd90241
|
3 |
+
size 7702565696
|
README.md
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: mit
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
---
|
7 |
+
|
8 |
+
My own (ZeroWw) quantizations.
|
9 |
+
output and embed tensors quantized to f16.
|
10 |
+
all other tensors quantized to q5_k or q6_k.
|
11 |
+
|
12 |
+
Result:
|
13 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
14 |
+
and they perform as well as the pure f16.
|
15 |
+
|
16 |
+
Updated on: Fri Jul 19, 18:50:44
|