Update README.md
Browse files
README.md
CHANGED
@@ -65,13 +65,25 @@ tags:
|
|
65 |
|
66 |
- Run as LlamaEdge service
|
67 |
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
--
|
72 |
-
|
73 |
-
|
74 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
- Run as LlamaEdge command app
|
77 |
|
@@ -79,7 +91,7 @@ tags:
|
|
79 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
|
80 |
llama-chat.wasm \
|
81 |
--prompt-template llama-3-chat \
|
82 |
-
--ctx-size 128000
|
83 |
```
|
84 |
|
85 |
## Quantized GGUF Models
|
|
|
65 |
|
66 |
- Run as LlamaEdge service
|
67 |
|
68 |
+
- Chat
|
69 |
+
|
70 |
+
```bash
|
71 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
|
72 |
+
llama-api-server.wasm \
|
73 |
+
--prompt-template llama-3-chat \
|
74 |
+
--ctx-size 128000 \
|
75 |
+
--model-name Llama-3.1-8b
|
76 |
+
```
|
77 |
+
|
78 |
+
- Tool use
|
79 |
+
|
80 |
+
```bash
|
81 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
|
82 |
+
llama-api-server.wasm \
|
83 |
+
--prompt-template llama-3-tool \
|
84 |
+
--ctx-size 128000 \
|
85 |
+
--model-name Llama-3.1-8b
|
86 |
+
```
|
87 |
|
88 |
- Run as LlamaEdge command app
|
89 |
|
|
|
91 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \
|
92 |
llama-chat.wasm \
|
93 |
--prompt-template llama-3-chat \
|
94 |
+
--ctx-size 128000
|
95 |
```
|
96 |
|
97 |
## Quantized GGUF Models
|