Disable --max-model-len option in the Bielik‑11B‑v2.3‑Instruct vLLM quick‑start script.

Paweł Kędzia · Paweł Kędzia · commit 49dc01914dec · 2025-12-01T02:52:49.000+01:00
diff --git a/examples/quickstart/speakleash-bielik-11b-v2_3-Instruct/run-bielik-11b-v2_3-vllm.sh b/examples/quickstart/speakleash-bielik-11b-v2_3-Instruct/run-bielik-11b-v2_3-vllm.sh
@@ -10,5 +10,7 @@ vllm serve \
         --host 0.0.0.0 \
         --quantization bitsandbytes \
         --load-format bitsandbytes \
-        --max-model-len=56000 \
         --gpu-memory-utilization=0.80
+
+
+#         --max-model-len=56000 \
