Update README.md

README.md

@@ -13,7 +13,7 @@ pipeline_tag: translation
 
 # Marco-MT-Algharb
 
-This repository contains the system description paper for Algharb, the submission from the Marco Translation Team of Alibaba International Digital Commerce (AIDC) to the WMT 2025 General Machine Translation Shared Task.
+This repository contains the system for Algharb, the submission from the Marco Translation Team of Alibaba International Digital Commerce (AIDC) to the WMT 2025 General Machine Translation Shared Task.
 
 ## Introduction
 
@@ -37,7 +37,7 @@ The core of the process involves formatting the input text into a specific promp
 The prompt template is:
 
 ```python
-f"Human: Please translate the following text into {target_language}: \n{source_text}<|im_end|>\nAssistant:"
+"Human: Please translate the following text into {target_language}: \n{source_text}<|im_end|>\nAssistant:"
 ```
 
 Here is a complete Python example:
@@ -81,7 +81,7 @@ prompts_to_generate = [prompt]
 print("Formatted Prompt:\n", prompt)
 
 sampling_params = SamplingParams(
-    n=1,
+    n=100,
     temperature=1.0,
     top_p=1.0,
     max_tokens=512
@@ -100,4 +100,10 @@ for output in outputs:
     for i, candidate in enumerate(output.outputs):
         generated_text = candidate.text.strip()
         print(f"Candidate {i+1}: {generated_text}")
-```
+```
+
+### 3. Apply MBR decoding
+```bash
+comet-mbr -s src.txt -t mbr_sample_100.txt -o mbr_trans.txt --num_samples 100 --gpus 1 --qe_model Unbabel/wmt22-cometkiwi-da
+```
+Note: Word alignment for MBR reranking will be available soon.