Add GGUF and Q4 version of the model for llama.cpp
Browse files- .gitattributes +1 -0
- added_tokens.json +0 -3
- ggml-model-f16.gguf +3 -0
- ggml-model-q4_0.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ 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 |
+
ggml-model-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
CHANGED
|
@@ -1,6 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"</s>": 2,
|
| 3 |
-
"<s>": 1,
|
| 4 |
-
"<unk>": 0,
|
| 5 |
"[PAD]": 32000
|
| 6 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"[PAD]": 32000
|
| 3 |
}
|
ggml-model-f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2990323139c845727dae835865fd5b81b4d2b72521dda2fded2d0c4dcb731092
|
| 3 |
+
size 26033323872
|
ggml-model-q4_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f2cb609b0d4d3f819180d98d8254b5ebdaafedfa0f84410492325b333ef664d
|
| 3 |
+
size 7365841760
|