Added more quants
Browse files- README.md +3 -2
- kukulemon-7B.Q4_K_M.gguf +3 -0
- kukulemon-7B.Q5_K_M.gguf +3 -0
- kukulemon-7B.Q6_K.gguf +3 -0
README.md
CHANGED
|
@@ -7,10 +7,11 @@ tags:
|
|
| 7 |
- mergekit
|
| 8 |
- merge
|
| 9 |
license: cc-by-nc-4.0
|
|
|
|
| 10 |
---
|
| 11 |
# kukulemon-7B-GGUF
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
A merger of two similar Kunoichi models with strong reasoning, hopefully resulting in "dense" encoding of said reasoning, was merged with a model targeting roleplay.
|
| 16 |
|
|
@@ -57,4 +58,4 @@ parameters:
|
|
| 57 |
- value: 0.5 # fallback for rest of tensors
|
| 58 |
dtype: float16
|
| 59 |
|
| 60 |
-
```
|
|
|
|
| 7 |
- mergekit
|
| 8 |
- merge
|
| 9 |
license: cc-by-nc-4.0
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
---
|
| 12 |
# kukulemon-7B-GGUF
|
| 13 |
|
| 14 |
+
The files are GGUF quants of (kukulemon-7B)[https://huggingface.co/grimjim/kukulemon-7B].
|
| 15 |
|
| 16 |
A merger of two similar Kunoichi models with strong reasoning, hopefully resulting in "dense" encoding of said reasoning, was merged with a model targeting roleplay.
|
| 17 |
|
|
|
|
| 58 |
- value: 0.5 # fallback for rest of tensors
|
| 59 |
dtype: float16
|
| 60 |
|
| 61 |
+
```
|
kukulemon-7B.Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9b8d647dc76c8578a1bfc5d3a0d22b358627f5ab8603c00adb1543545b3e270
|
| 3 |
+
size 4368439040
|
kukulemon-7B.Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:199032a4568489f12af47b4c48c463764f24a133910624b7542a7ce7eb3e4b70
|
| 3 |
+
size 5131409152
|
kukulemon-7B.Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2e14d9f6cc7bfcaa19ef357ea46de470bf49a840296358144b2d00b6d194168
|
| 3 |
+
size 5942064896
|