add codellama 13b python
Browse files
.gitignore
CHANGED
@@ -1 +1,4 @@
|
|
1 |
bak/
|
|
|
|
|
|
|
|
1 |
bak/
|
2 |
+
**/*-13b-*.gguf
|
3 |
+
**/*-q5*.gguf
|
4 |
+
**/*-q5*.gguf.*
|
README.md
CHANGED
@@ -4,4 +4,12 @@ license: llama2
|
|
4 |
|
5 |
# Llama Models
|
6 |
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
5 |
# Llama Models
|
6 |
|
7 |
+
## Notes
|
8 |
+
|
9 |
+
### Partitioned Files
|
10 |
+
|
11 |
+
Partitioned model like `*.gguf.0*`, please combine them into a single `gguf` file, for example:
|
12 |
+
|
13 |
+
```bash
|
14 |
+
cat codellama-13b-python-q4_0.gguf.* > codellama-13b-python-q4_0.gguf
|
15 |
+
```
|
codellama/codellama-13b-python-q4_0.gguf.00
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a96574fda23cd8bf8c40ebffe3eaeb115b817817dcf2b5da7c9443093c24c5
|
3 |
+
size 3221225472
|
codellama/codellama-13b-python-q4_0.gguf.01
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82ffb7faf957b9836cb5f3bf339222fb7abbfef69d56b1f4359fc42d4316abb0
|
3 |
+
size 3221225472
|
codellama/codellama-13b-python-q4_0.gguf.02
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff746e455ad2947706a9201f390d4c8c7b2e7f899b59bba922de85bf23cbc20f
|
3 |
+
size 923283808
|