Andrew Canis
commited on
Commit
•
f5c0256
1
Parent(s):
01be733
Update with llama.cpp release
Browse files
README.md
CHANGED
@@ -12,17 +12,11 @@ license: cc-by-nc-4.0
|
|
12 |
This repo contains llama.cpp GGUF format model files for
|
13 |
[Command-R 35B v1.0](https://huggingface.co/CohereForAI/c4ai-command-r-v01).
|
14 |
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
mkdir build
|
21 |
-
cd build
|
22 |
-
cmake .. -DLLAMA_CUBLAS=ON
|
23 |
-
cmake --build . --config Release -- -j16
|
24 |
-
cd ..
|
25 |
-
```
|
26 |
|
27 |
## F16 files are split and require joining
|
28 |
|
|
|
12 |
This repo contains llama.cpp GGUF format model files for
|
13 |
[Command-R 35B v1.0](https://huggingface.co/CohereForAI/c4ai-command-r-v01).
|
14 |
|
15 |
+
<!-- compatibility_gguf start -->
|
16 |
+
## Compatibility
|
17 |
+
|
18 |
+
These quantised GGUF files are compatible with llama.cpp from Mar 16, 2024 onwards,
|
19 |
+
starting from release [b2440](https://github.com/ggerganov/llama.cpp/releases/tag/b2440)
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## F16 files are split and require joining
|
22 |
|