apepkuss79
commited on
Commit
•
1f3eada
1
Parent(s):
8204c7c
Update README.md
Browse files
README.md
CHANGED
@@ -29,11 +29,11 @@ language:
|
|
29 |
|
30 |
- LlamaEdge version: coming soon
|
31 |
|
32 |
-
<!-- - LlamaEdge version: [v0.14.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.0) and above
|
33 |
|
34 |
- Prompt template
|
35 |
|
36 |
-
- Prompt type: `
|
37 |
|
38 |
- Prompt string
|
39 |
|
@@ -50,19 +50,9 @@ language:
|
|
50 |
```bash
|
51 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Breeze-7B-Instruct-v1_0-Q5_K_M.gguf \
|
52 |
llama-api-server.wasm \
|
53 |
-
--prompt-template
|
54 |
-
--ctx-size
|
55 |
-
--model-name
|
56 |
-
```
|
57 |
-
|
58 |
-
- Tool use
|
59 |
-
|
60 |
-
```bash
|
61 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Breeze-7B-Instruct-v1_0-Q5_K_M.gguf \
|
62 |
-
llama-api-server.wasm \
|
63 |
-
--prompt-template llama-3-tool \
|
64 |
-
--ctx-size 128000 \
|
65 |
-
--model-name Llama-3.1-8b
|
66 |
```
|
67 |
|
68 |
- Run as LlamaEdge command app
|
@@ -70,9 +60,9 @@ language:
|
|
70 |
```bash
|
71 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Breeze-7B-Instruct-v1_0-Q5_K_M.gguf \
|
72 |
llama-chat.wasm \
|
73 |
-
--prompt-template
|
74 |
-
--ctx-size
|
75 |
-
```
|
76 |
|
77 |
## Quantized GGUF Models
|
78 |
|
|
|
29 |
|
30 |
- LlamaEdge version: coming soon
|
31 |
|
32 |
+
<!-- - LlamaEdge version: [v0.14.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.0) and above -->
|
33 |
|
34 |
- Prompt template
|
35 |
|
36 |
+
- Prompt type: `mediatek-breeze`
|
37 |
|
38 |
- Prompt string
|
39 |
|
|
|
50 |
```bash
|
51 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Breeze-7B-Instruct-v1_0-Q5_K_M.gguf \
|
52 |
llama-api-server.wasm \
|
53 |
+
--prompt-template mediatek-breeze \
|
54 |
+
--ctx-size 8000 \
|
55 |
+
--model-name breeze-7b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
```
|
57 |
|
58 |
- Run as LlamaEdge command app
|
|
|
60 |
```bash
|
61 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Breeze-7B-Instruct-v1_0-Q5_K_M.gguf \
|
62 |
llama-chat.wasm \
|
63 |
+
--prompt-template mediatek-breeze \
|
64 |
+
--ctx-size 8000
|
65 |
+
```
|
66 |
|
67 |
## Quantized GGUF Models
|
68 |
|