Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
- Qwen3-8B-Esper3.f16.gguf +3 -0
- Qwen3-8B-Esper3.q5_k.gguf +3 -0
- Qwen3-8B-Esper3.q6_k.gguf +3 -0
- Qwen3-8B-Esper3.q8_0.gguf +3 -0
- Qwen3-8B-Esper3.q8_p.gguf +3 -0
- Qwen3-8B-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 |
+
Qwen3-8B-Esper3.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen3-8B-Esper3.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen3-8B-Esper3.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen3-8B-Esper3.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen3-8B-Esper3.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen3-8B-Esper3.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3-8B-Esper3.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cff1622e27a536bf7aa636c070e4472f649cc23e10ef7735c8f33ccb5fa9b21
|
3 |
+
size 16388045184
|
Qwen3-8B-Esper3.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a0a83c622a4da1672bcfed6bd64c898be7ad562492cd7742e2bfc8eb53cb872
|
3 |
+
size 7402076544
|
Qwen3-8B-Esper3.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5920d9657e2fb39c22f14d4cc2bc6124af67a9b7f7384adc064cb30c98bf3d3d
|
3 |
+
size 8194210176
|
Qwen3-8B-Esper3.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b2c922dbcd9c932f07d4c625c3be4ac19861edc09e13c0d32cd41e571eeda38
|
3 |
+
size 9876388224
|
Qwen3-8B-Esper3.q8_p.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8360931ba9cb9663e3069bc983fd9fda10a2eb05b2f231686c945a15d1d1603
|
3 |
+
size 8709519744
|
Qwen3-8B-Esper3.q8q4.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5522fa52cf29d0c6bf3de46a5a45b6620531179b6d192d02b2d35292ab0e0403
|
3 |
+
size 5489670528
|
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, 12:42:08
|