Add NOTICE
Browse files
NOTICE
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Mitsuba-ComfyUI-27B-GGUF
|
| 2 |
+
|
| 3 |
+
This model is a modified version of Qwen3.8-27B.
|
| 4 |
+
Qwen3.8-27B is Copyright 2026 Alibaba Cloud and is available under the Apache License 2.0:
|
| 5 |
+
https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/LICENSE
|
| 6 |
+
|
| 7 |
+
Modifications:
|
| 8 |
+
- The weights were ternarized (values -1 / 0 / +1 with one scale per 128 weights) and the scales were further trained.
|
| 9 |
+
- The weights are stored in Prism ML's PQ2_0 and PTQ1_0 GGUF formats.
|
| 10 |
+
|
| 11 |
+
The file mmproj-Q8_0.gguf is included unchanged from
|
| 12 |
+
https://huggingface.co/OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF (Apache License 2.0),
|
| 13 |
+
which is based on https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf (Apache License 2.0).
|
| 14 |
+
|
| 15 |
+
Ternary Bonsai is copyright 2026-present Prism ML, Inc. and is available under the Apache License 2.0.
|
| 16 |
+
The PQ2_0 / PTQ1_0 formats and the llama.cpp fork used to run this model are by Prism ML.
|
| 17 |
+
Created using Bonsai by Prism ML (formats and vision encoder).
|