Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,8 @@ The idea here was simple: find out whether a small reasoning model can roleplay
|
|
| 29 |
|
| 30 |
...Or so the theory goes!
|
| 31 |
|
|
|
|
|
|
|
| 32 |
## Model details
|
| 33 |
|
| 34 |
Base model is [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) - MoEs are neat little things, and this one is actually (finally!) remarkably easy to train with Axolotl. Worth noting: thinking traces are noticeably more concise post-training. Qwen3.6 loves to spiral, and apparently feeding it stories helped.
|
|
|
|
| 29 |
|
| 30 |
...Or so the theory goes!
|
| 31 |
|
| 32 |
+
GGUF quants [are available here](https://huggingface.co/bartowski/Gryphe_WorldSim-Opus-3.6-35B-A3B-GGUF).
|
| 33 |
+
|
| 34 |
## Model details
|
| 35 |
|
| 36 |
Base model is [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) - MoEs are neat little things, and this one is actually (finally!) remarkably easy to train with Axolotl. Worth noting: thinking traces are noticeably more concise post-training. Qwen3.6 loves to spiral, and apparently feeding it stories helped.
|