Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
- Qwen3-4B-Esper3.f16.gguf +3 -0
- Qwen3-4B-Esper3.q5_k.gguf +3 -0
- Qwen3-4B-Esper3.q6_k.gguf +3 -0
- Qwen3-4B-Esper3.q8_0.gguf +3 -0
- Qwen3-4B-Esper3.q8_p.gguf +3 -0
- Qwen3-4B-Esper3.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 |
+
Qwen3-4B-Esper3.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen3-4B-Esper3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen3-4B-Esper3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen3-4B-Esper3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen3-4B-Esper3.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen3-4B-Esper3.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3-4B-Esper3.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d1ae119d51422048a7648d90a145d907378da1ad4e8c5bb096d477704ab6429
|
3 |
+
size 8051286336
|
Qwen3-4B-Esper3.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93a2e432faa0f9639fdb99eae1515306a3f0d1fe4380d80c116b75db7cfe09a9
|
3 |
+
size 3348361536
|
Qwen3-4B-Esper3.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d481cae57f6a0126d55f72261d90218833642c01f84e0e1e860719d21cf3e4db
|
3 |
+
size 3765109056
|
Qwen3-4B-Esper3.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb39a407fca1974de6188b24d6a56a71a9123ea91a872f13dd45a315aeae5745
|
3 |
+
size 4645052736
|
Qwen3-4B-Esper3.q8_p.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557b28cf292699d22e2d920a4aa82bc606942a824a7ca72df1b44288a2337385
|
3 |
+
size 4280406336
|
Qwen3-4B-Esper3.q8q4.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7217932fa5aa60091d520967e355d00e08e894c3e51b08f8bf53749aa958f1f8
|
3 |
+
size 2591482176
|
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: Wed May 07, 09:53:08
|