Text Generation
GGUF
English
Chinese
MOE
Qwen 2.5 MOE
Mixture of Experts
Uncensored
2X7B
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
|
@@ -116,6 +116,12 @@ SOFTWARE patch (by me) for Silly Tavern (front end to connect to multiple AI app
|
|
| 116 |
|
| 117 |
IQ4XS Quant, Temp 1.5, rep pen 1.06, topp: .95, minp: .05, topk: 40
|
| 118 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
---
|
| 120 |
|
| 121 |
EXAMPLE #1:
|
|
|
|
| 116 |
|
| 117 |
IQ4XS Quant, Temp 1.5, rep pen 1.06, topp: .95, minp: .05, topk: 40
|
| 118 |
|
| 119 |
+
Below are the least creative outputs, prompt is in BOLD.
|
| 120 |
+
|
| 121 |
+
IMPORTANT:
|
| 122 |
+
|
| 123 |
+
Higher quants / imatrix quants will have much stronger generation - words, sentences, ideas, dialog and general quality.
|
| 124 |
+
|
| 125 |
---
|
| 126 |
|
| 127 |
EXAMPLE #1:
|