Commit
•
dbef861
1
Parent(s):
782e28b
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,11 @@ tags:
|
|
| 27 |
- 2bit
|
| 28 |
---
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
# glm-4-9b-chat-1m-GGUF
|
| 31 |
_Llama.cpp static quantization of THUDM/glm-4-9b-chat-1m_
|
| 32 |
|
|
|
|
| 27 |
- 2bit
|
| 28 |
---
|
| 29 |
|
| 30 |
+
> [!WARNING]
|
| 31 |
+
> **Caution!**
|
| 32 |
+
> This model is not properly supported yet in llama.cpp and will not work.
|
| 33 |
+
> See discussion here: https://github.com/ggerganov/llama.cpp/pull/8031#issuecomment-2213635819
|
| 34 |
+
|
| 35 |
# glm-4-9b-chat-1m-GGUF
|
| 36 |
_Llama.cpp static quantization of THUDM/glm-4-9b-chat-1m_
|
| 37 |
|