apepkuss79 commited on
Commit
8a94122
·
verified ·
1 Parent(s): 9860732

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -49,7 +49,7 @@ language:
49
  <|im_start|>assistant
50
  ```
51
 
52
- - Context size: `128000`
53
 
54
  - Run as LlamaEdge service
55
 
@@ -58,7 +58,7 @@ language:
58
  llama-api-server.wasm \
59
  --model-name Qwen2.5-Coder-0.5B-Instruct \
60
  --prompt-template chatml \
61
- --ctx-size 128000
62
  ```
63
 
64
  - Run as LlamaEdge command app
@@ -67,7 +67,7 @@ language:
67
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf \
68
  llama-chat.wasm \
69
  --prompt-template chatml \
70
- --ctx-size 128000
71
  ```
72
 
73
  ## Quantized GGUF Models
 
49
  <|im_start|>assistant
50
  ```
51
 
52
+ - Context size: `32000`
53
 
54
  - Run as LlamaEdge service
55
 
 
58
  llama-api-server.wasm \
59
  --model-name Qwen2.5-Coder-0.5B-Instruct \
60
  --prompt-template chatml \
61
+ --ctx-size 32000
62
  ```
63
 
64
  - Run as LlamaEdge command app
 
67
  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-Coder-0.5B-Instruct-Q5_K_M.gguf \
68
  llama-chat.wasm \
69
  --prompt-template chatml \
70
+ --ctx-size 32000
71
  ```
72
 
73
  ## Quantized GGUF Models