Update README.md

README.md

@@ -38,10 +38,10 @@ cd GGUF-Tool-Suite
 rm -f download.conf # Make sure to copy the relevant download.conf for the model before running quant_assign.py
 cp -f models/DeepSeek-TNG-R1T2-Chimera/download.conf . # Use the download.conf of the chosen model
 mkdir -p kitchen && cd kitchen
-../quant_downloader.sh ../recipe_examples/DeepSeek-TNG-R1T2-Chimera.ROOT-3.0624bpw-3.3657ppl.238GB-GGUF_11GB-GPU_227GB-CPU.13549e6_1ac857a.recipe
+../quant_downloader.sh ../recipe_examples/ik_llama.cpp_recipes/DeepSeek-TNG-R1T2-Chimera.ROOT-3.0624bpw-3.3657ppl.238GB-GGUF_11GB-GPU_227GB-CPU.13549e6_1ac857a.recipe
 
 # Launch ik_llama's llama-cli:
-ulimit -n 99999 # Lifts "too many open files" limitation on Linux
+ulimit -n 9999 # Lifts "too many open files" limitation on Linux
 ~/ik_llama.cpp/build/bin/llama-cli \
   -m DeepSeek-TNG-R1T2-Chimera-THIREUS-BF16-SPECIAL_TENSOR-00001-of-01148.gguf \
   -mla 3 -fa -amb 512 -fmoe -ctk f16 -c 4096 -ngl 99 \
@@ -74,6 +74,8 @@ Here’s how DeepSeek-R1-0528 quantized with **Thireus’ GGUF Tool Suite** stac
 
 More perplexity/bpw graphs for other supported models: https://github.com/Thireus/GGUF-Tool-Suite/tree/main/ppl_graphs  
 
+*All PPL values are computed with the parameters `-ctk f16 -c 512 -b 4096 -ub 4096`. Changing any of these parameters will alter the PPL. In particular, reducing `-b 4096 -ub 4096` increases the PPL, while increasing them decreases the PPL.*
+
 ---
 
 ## 🚀 How do I get started?