keitokei1994
commited on
Commit
•
c45ee6a
1
Parent(s):
7f20af8
Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ language:
|
|
19 |
```
|
20 |
2. 以下のようなコマンドでFlashAttentionを有効化して実行します:
|
21 |
```
|
22 |
-
./server -m ./models/shisa-v1-qwen2-7b.Q8_0.gguf -ngl 99 --port 8888 -fa
|
23 |
```
|
24 |
|
25 |
# shisa-v1-qwen2-7b-gguf
|
@@ -35,5 +35,5 @@ This is a gguf format conversion of [shisa-v1-qwen2-7b](https://huggingface.co/s
|
|
35 |
```
|
36 |
2. Run with Flash Attention enabled using a command like this:
|
37 |
```
|
38 |
-
./server -m ./models/shisa-v1-qwen2-7b.Q8_0.gguf -ngl 99 --port 8888 -fa
|
39 |
```
|
|
|
19 |
```
|
20 |
2. 以下のようなコマンドでFlashAttentionを有効化して実行します:
|
21 |
```
|
22 |
+
./llama-server -m ./models/shisa-v1-qwen2-7b.Q8_0.gguf -ngl 99 --port 8888 -fa
|
23 |
```
|
24 |
|
25 |
# shisa-v1-qwen2-7b-gguf
|
|
|
35 |
```
|
36 |
2. Run with Flash Attention enabled using a command like this:
|
37 |
```
|
38 |
+
./llama-server -m ./models/shisa-v1-qwen2-7b.Q8_0.gguf -ngl 99 --port 8888 -fa
|
39 |
```
|