Update README.md

README.md

@@ -43,7 +43,7 @@ license: apache-2.0
 
   - Reverse prompt: `<|im_end|>`
 
-- Context size: `4096`
+- Context size: `128000`
 
 - Run as LlamaEdge service
 
@@ -52,7 +52,7 @@ license: apache-2.0
     llama-api-server.wasm \
     --prompt-template chatml \
     --reverse-prompt "<|im_end|>" \
-    --ctx-size 4096 \
+    --ctx-size 128000 \
     --model-name Yi-Coder-1.5B-Chat
   ```
 
@@ -63,7 +63,7 @@ license: apache-2.0
     llama-chat.wasm \
     --prompt-template chatml \
     --reverse-prompt "<|im_end|>" \
-    --ctx-size 4096
+    --ctx-size 128000
   ```
 
 ## Quantized GGUF Models
@@ -84,4 +84,4 @@ license: apache-2.0
 | [Yi-Coder-1.5B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q8_0.gguf)     | Q8_0   | 8 | 1.57 GB| very large, extremely low quality loss - not recommended |
 | [Yi-Coder-1.5B-Chat-f16.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-f16.gguf)       | f16   | 16 | 2.95 GB| |
 
-*Quantized with llama.cpp b3613*
+*Quantized with llama.cpp b3664*