Add repetition_penalty and frequency_penalty suggestion

README.md

@@ -141,11 +141,16 @@ You have 2 reasoning parsers;
 
 The reason why `minimax_m2_append_think` was introduced was Interleaved Thinking and having the model build upon it's previous thinking (usually frontends discard the thinking trace)
 
+> [!TIP]  
+> 💡With the recommended parameters the model tends to get stuck in repetition loops.\
+> It seems like repetition_penalty: 1.10, frequency_penalty: 0.40 avoids that
+
 ```bash
 # Model configuration (Mandatory)
 MODEL="mratsim/MiniMax-M2.1-FP8-INT4-AWQ"
 MODELNAME="MiniMax-M2.1-FP8"
 GPU_UTIL=0.93
+SAMPLER_OVERRIDE='{"temperature": 1, "top_p": 0.95, "top_k": 40, "repetition_penalty": 1.1, "frequency_penalty": 0.40}'
 
 # Prevent memory fragmentation
 export PYTORCH_ALLOC_CONF=expandable_segments:True,max_split_size_mb:512
@@ -158,9 +163,10 @@ vllm serve "${MODEL}" \
   --trust-remote-code \
   --gpu-memory-utilization ${GPU_UTIL} \
   --tp 2 \
+  --override-generation-config "${SAMPLER_OVERRIDE}" \
   --enable-auto-tool-choice \
   --tool-call-parser minimax_m2 \
-  --reasoning-parser minimax_m2
+  --reasoning-parser minimax_m2 \
   # --reasoning-parser minimax_m2_append_think
 ```