maxwelhelp commited on
Commit ·
81e58a0
1
Parent(s): 7c97475
Add model card YAML metadata
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# llama.cpp DFlash2 P40 (Pascal) optimization
|
| 2 |
|
| 3 |
Speculative decoding (DFlash2 block-diffusion drafter) tuned specifically for
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- ru
|
| 5 |
+
tags:
|
| 6 |
+
- dflash2
|
| 7 |
+
- speculative-decoding
|
| 8 |
+
- llama.cpp
|
| 9 |
+
- tesla-p40
|
| 10 |
+
- pascal
|
| 11 |
+
- gguf
|
| 12 |
+
license: apache-2.0
|
| 13 |
+
library_name: gguf
|
| 14 |
+
base_model: Qwen/Qwen3.8-27B-UD
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
# llama.cpp DFlash2 P40 (Pascal) optimization
|
| 18 |
|
| 19 |
Speculative decoding (DFlash2 block-diffusion drafter) tuned specifically for
|