Update README.md
Browse files
README.md
CHANGED
@@ -6,13 +6,13 @@ license: apache-2.0
|
|
6 |
|
7 |
**Goal is to have the best performing MoE < 10gb**
|
8 |
|
9 |
-
|
10 |
|
11 |
-
|
12 |
|
13 |
8.4gb custom 2bit quant works ok up until 512 token length then starts looping.
|
14 |
|
15 |
-
Install llama.cpp from github and run it:
|
16 |
|
17 |
|
18 |
```bash
|
|
|
6 |
|
7 |
**Goal is to have the best performing MoE < 10gb**
|
8 |
|
9 |
+
Experimental q8 and q4 files for training/finetuning too.
|
10 |
|
11 |
+
***No sparsity tricks yet.***
|
12 |
|
13 |
8.4gb custom 2bit quant works ok up until 512 token length then starts looping.
|
14 |
|
15 |
+
- Install llama.cpp from github and run it:
|
16 |
|
17 |
|
18 |
```bash
|