Thireus
commited on
Commit
·
6792bea
1
Parent(s):
f25905b
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,12 +38,12 @@ cd GGUF-Tool-Suite
|
|
| 38 |
rm -f download.conf # Make sure to copy the relevant download.conf for the model before running quant_assign.py
|
| 39 |
cp -f models/DeepSeek-R1-0528/download.conf . # Use the download.conf of the chosen model
|
| 40 |
mkdir -p kitchen && cd kitchen
|
| 41 |
-
../quant_downloader.sh ../recipe_examples/DeepSeek-R1-0528.THIREUS-1.9364bpw-4.3533ppl.151GB-GGUF_11GB-GPU_140GB-CPU.3c88ec6_9fd615d.recipe
|
| 42 |
|
| 43 |
# Other recipe examples can be found at https://github.com/Thireus/GGUF-Tool-Suite/tree/main/recipe_examples
|
| 44 |
|
| 45 |
# Launch ik_llama's llama-cli:
|
| 46 |
-
ulimit -n
|
| 47 |
~/ik_llama.cpp/build/bin/llama-cli \
|
| 48 |
-m DeepSeek-R1-0528-THIREUS-BF16-SPECIAL_TENSOR-00001-of-01148.gguf \
|
| 49 |
-mla 3 -fa -amb 512 -fmoe -ctk f16 -c 4096 -ngl 99 \
|
|
|
|
| 38 |
rm -f download.conf # Make sure to copy the relevant download.conf for the model before running quant_assign.py
|
| 39 |
cp -f models/DeepSeek-R1-0528/download.conf . # Use the download.conf of the chosen model
|
| 40 |
mkdir -p kitchen && cd kitchen
|
| 41 |
+
../quant_downloader.sh ../recipe_examples/ik_llama.cpp_recipes/DeepSeek-R1-0528.THIREUS-1.9364bpw-4.3533ppl.151GB-GGUF_11GB-GPU_140GB-CPU.3c88ec6_9fd615d.recipe
|
| 42 |
|
| 43 |
# Other recipe examples can be found at https://github.com/Thireus/GGUF-Tool-Suite/tree/main/recipe_examples
|
| 44 |
|
| 45 |
# Launch ik_llama's llama-cli:
|
| 46 |
+
ulimit -n 9999 # Lifts "too many open files" limitation on Linux
|
| 47 |
~/ik_llama.cpp/build/bin/llama-cli \
|
| 48 |
-m DeepSeek-R1-0528-THIREUS-BF16-SPECIAL_TENSOR-00001-of-01148.gguf \
|
| 49 |
-mla 3 -fa -amb 512 -fmoe -ctk f16 -c 4096 -ngl 99 \
|