Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,10 @@ tags:
|
|
| 4 |
- moe
|
| 5 |
- merge
|
| 6 |
---
|
| 7 |
-
# Experimental model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- moe
|
| 5 |
- merge
|
| 6 |
---
|
| 7 |
+
# Experimental model
|
| 8 |
+
A Experimental MoE Model that custom for all-rounded Roleplay. Well understand Character Card and high logic.
|
| 9 |
+
# It's ridiculous that I can run this original version in 4bit, but can't run in GGUF version. I hope someone could help me fix the GGUF version.
|
| 10 |
+
This is the following error line that I got when try loading GGUF version of this model:
|
| 11 |
+
``GGML_ASSERT: /home/runner/work/llama-cpp-python-cuBLAS-wheels/llama-cpp-python-cuBLAS-wheels/vendor/llama.cpp/ggml-cuda.cu:8431: (ncols & (ncols - 1)) == 0``
|
| 12 |
+
Have try from Q2 to fp16, no hope. 😥
|
| 13 |
+
# Is this model good? Want more dicussion? Let's me know in community tab! ヾ(≧▽≦*)o
|