Update README.md

README.md

@@ -43,6 +43,8 @@ quantized_by: Second State Inc.
     <|im_start|>assistant
     ```
 
+  - Reverse prompt: `<|im_end|>`
+
 - Context size: `16384`
 
 - Run as LlamaEdge service
@@ -51,6 +53,7 @@ quantized_by: Second State Inc.
   wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
     llama-api-server.wasm \
     --prompt-template chatml \
+    --reverse-prompt "<|im_end|>" \
     --ctx-size 16384 \
     --model-name Yi-1.5-34B-Chat-16K
   ```
@@ -61,6 +64,7 @@ quantized_by: Second State Inc.
   wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-34B-Chat-16K-Q5_K_M.gguf \
     llama-chat.wasm \
     --prompt-template chatml \
+    --reverse-prompt "<|im_end|>" \
     --ctx-size 16384
   ```
 
@@ -84,4 +88,4 @@ quantized_by: Second State Inc.
 | [Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00002-of-00003.gguf)     | f16   | 16 | 32.1 GB| |
 | [Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf](https://huggingface.co/second-state/Yi-1.5-34B-Chat-16K-GGUF/blob/main/Yi-1.5-34B-Chat-16K-f16-00003-of-00003.gguf)     | f16   | 16 | 4.48 GB| |
 
-*Quantized with llama.cpp b2824*
+*Quantized with llama.cpp b3135*