Text Generation
GGUF
English
Chinese
MOE
Qwen 2.5 MOE
Mixture of Experts
6X1.5B
deepseek
reasoning
thinking
creative
128k context
general usage
problem solving
brainstorming
solve riddles
story generation
plot generation
storytelling
fiction story
story
writing
fiction
Qwen 2.5
mergekit
Inference Endpoints
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,7 +57,7 @@ In Lmstudio the "Jinja Template" should load by default.
|
|
| 57 |
|
| 58 |
In other apps - use the Deepseek Tokenizer.
|
| 59 |
|
| 60 |
-
Sometimes this model will output Chinese Characters/Symbols - regen to clear.
|
| 61 |
|
| 62 |
Sometimes it will work great, other times it will give "so/so" answers and then sometimes it will bat it out of the park, and past the "state line."
|
| 63 |
|
|
|
|
| 57 |
|
| 58 |
In other apps - use the Deepseek Tokenizer.
|
| 59 |
|
| 60 |
+
Sometimes this model will output Chinese Characters/Symbols (with an English prompt) - regen to clear.
|
| 61 |
|
| 62 |
Sometimes it will work great, other times it will give "so/so" answers and then sometimes it will bat it out of the park, and past the "state line."
|
| 63 |
|