Update README.md

README.md

@@ -49,7 +49,7 @@ quantized_by: Second State Inc.
     {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
     ```
 
-- Context size: `4096`
+- Context size: `8192`
 
 - Run as LlamaEdge service
 
@@ -57,7 +57,7 @@ quantized_by: Second State Inc.
   wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3-8B-Instruct-Q5_K_M.gguf \
     llama-api-server.wasm \
     --prompt-template llama-3-chat \
-    --ctx-size 4096 \
+    --ctx-size 8192 \
     --model-name Llama-3-8b
   ```
 
@@ -67,7 +67,7 @@ quantized_by: Second State Inc.
   wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3-8B-Instruct-Q5_K_M.gguf \
     llama-chat.wasm \
     --prompt-template llama-3-chat \
-    --ctx-size 4096 \
+    --ctx-size 8192 \
   ```
 
 ## Quantized GGUF Models