Add files using upload-large-folder tool
Browse files- .gitattributes +5 -0
- Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf +3 -0
- Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf +3 -0
- Qwopus3.5-9B-Coder-MTP-Q6_K.gguf +3 -0
- Qwopus3.5-9B-Coder-MTP-Q8_0.gguf +3 -0
- README.md +17 -0
- imatrix-code_micro.gguf +3 -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 |
+
imatrix-code_micro.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
Qwopus3.5-9B-Coder-MTP-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
Qwopus3.5-9B-Coder-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwopus3.5-9B-Coder-MTP-IQ4_XS.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a9ea62d65af07dda0a873f1940b0f3cf1142f19f20927a05d45b11a124486f
|
| 3 |
+
size 6026814016
|
Qwopus3.5-9B-Coder-MTP-Q4_K_XL.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92859bc5b0f10f5f819c7983155207700ba39613c0b85d5cbf7a7a630e50474a
|
| 3 |
+
size 6238806592
|
Qwopus3.5-9B-Coder-MTP-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a855aa24c5882ae918f328e4fe9a2cc0543e6f071cdfbc0e6fc01738107b3e5
|
| 3 |
+
size 7617815104
|
Qwopus3.5-9B-Coder-MTP-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e639ca81579757e4f929da62fb0b4817d6b686600083537746417fefffbb65a5
|
| 3 |
+
size 9786057312
|
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-text-to-text
|
| 3 |
+
base_model:
|
| 4 |
+
- Jackrong/Qwopus3.5-9B-Coder
|
| 5 |
+
tags:
|
| 6 |
+
- qwen
|
| 7 |
+
- qwen3_5_moe
|
| 8 |
+
- MTP
|
| 9 |
+
---
|
| 10 |
+
These are quantizations of the model [Jackrong / Qwopus3.5-9B-Coder](https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder)
|
| 11 |
+
I've added the MTP layer on it.
|
| 12 |
+
My personal speed improvement on my 7900XTX with the vulkan backend has been from ~80 tps to around ~120 tps.
|
| 13 |
+
An imatrix has been calulated for coding tasks, as such it is specialized for coding.
|
| 14 |
+
|
| 15 |
+
## Quick Start
|
| 16 |
+
1. Download the latest release of **llama.cpp**.
|
| 17 |
+
2. Download your preferred model variant from below.
|
imatrix-code_micro.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4076274f6bee37af8437f8fc9539d34a6206e2dec622ffcf16787f40f0fb2304
|
| 3 |
+
size 5150176
|