juntaoyuan
commited on
Commit
•
74cf9e2
1
Parent(s):
f5a2c14
Update context size
Browse files
README.md
CHANGED
@@ -50,7 +50,7 @@ tags:
|
|
50 |
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
51 |
```
|
52 |
|
53 |
-
- Context size: `
|
54 |
|
55 |
- Run as LlamaEdge service
|
56 |
|
@@ -58,7 +58,7 @@ tags:
|
|
58 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
|
59 |
llama-api-server.wasm \
|
60 |
--prompt-template llama-3-chat \
|
61 |
-
--ctx-size
|
62 |
--model-name llama-3-8B-instruct-262k
|
63 |
```
|
64 |
|
@@ -68,7 +68,7 @@ tags:
|
|
68 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
|
69 |
llama-chat.wasm \
|
70 |
--prompt-template llama-3-chat \
|
71 |
-
--ctx-size
|
72 |
```
|
73 |
|
74 |
## Quantized GGUF Models
|
|
|
50 |
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
51 |
```
|
52 |
|
53 |
+
- Context size: `262144`
|
54 |
|
55 |
- Run as LlamaEdge service
|
56 |
|
|
|
58 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
|
59 |
llama-api-server.wasm \
|
60 |
--prompt-template llama-3-chat \
|
61 |
+
--ctx-size 262144 \
|
62 |
--model-name llama-3-8B-instruct-262k
|
63 |
```
|
64 |
|
|
|
68 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
|
69 |
llama-chat.wasm \
|
70 |
--prompt-template llama-3-chat \
|
71 |
+
--ctx-size 262144
|
72 |
```
|
73 |
|
74 |
## Quantized GGUF Models
|