Update README.md
Browse files
README.md
CHANGED
@@ -12,8 +12,9 @@ tags:
|
|
12 |
|
13 |
# TriLM - llamafile
|
14 |
|
15 |
-
This is a ternary LLM whose weights consist of {-1, 0, +1}.
|
16 |
-
optimized for CPU performance, thanks to the [`Q2_K_S`
|
|
|
17 |
format](https://github.com/Mozilla-Ocho/llamafile/pull/552).
|
18 |
|
19 |
- Model creator: [SpectraSuite](https://huggingface.co/SpectraSuite)
|
|
|
12 |
|
13 |
# TriLM - llamafile
|
14 |
|
15 |
+
This is a 1.58 bit ternary LLM whose weights consist of {-1, 0, +1}.
|
16 |
+
It's highly optimized for CPU performance, thanks to the [`Q2_K_S`
|
17 |
+
quantization
|
18 |
format](https://github.com/Mozilla-Ocho/llamafile/pull/552).
|
19 |
|
20 |
- Model creator: [SpectraSuite](https://huggingface.co/SpectraSuite)
|