Update README.md

README.md

@@ -17,13 +17,15 @@ tags:
 ### Instructions to run this model in llama.cpp:
 Or you can view more detailed instructions here: [unsloth.ai/blog/deepseek-r1](https://unsloth.ai/blog/deepseek-r1)
 1. Do not forget about `<｜User｜>` and `<｜Assistant｜>` tokens! - Or use a chat template formatter
-2. Example with Q5_0 K quantized cache (V quantized cache doesn't work):
+2. Example with K & V quantized cache **Notice -no-cnv disables auto conversation mode**
    ```bash
-   ./llama.cpp/llama-cli
-   --model unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q2_K_XS/DeepSeek-R1-Distill-Llama-8B-Q2_K_XS-00001-of-00005.gguf
-   --cache-type-k q5_0
-   --threads 16 
-   --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
+   ./llama.cpp/llama-cli \
+       --model unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q2_K_L.gguf \
+       --cache-type-k q8_0 \
+       --cache-type-v q8_0 \
+       --threads 16 \
+       --prompt '<｜User｜>What is 1+1?<｜Assistant｜>' \
+       -no-cnv
    ```
    Example output:
    ```txt
@@ -35,13 +37,15 @@ Or you can view more detailed instructions here: [unsloth.ai/blog/deepseek-r1](h
 
     So, **1 + 1 = 2**. [end of text]
     ```
-3. If you have a GPU (RTX 4090 for example) with 24GB, you can offload 5 layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
+4. If you have a GPU (RTX 4090 for example) with 24GB, you can offload multiple layers to the GPU for faster processing. If you have multiple GPUs, you can probably offload more layers.
    ```bash
-    /llama.cpp/llama-cli \
-    --model DeepSeek-R1-Distill-Llama-8B-F16.gguf\
-    --cache-type-k q8_0 \
-    --prompt '<｜User｜>What is 1+1?<｜Assistant｜>' \
-    --threads 32 \
+   ./llama.cpp/llama-cli \
+   --model unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF/DeepSeek-R1-Distill-Llama-8B-Q2_K_L.gguf
+   --cache-type-k q8_0 
+   --cache-type-v q8_0 
+   --threads 16 
+   --prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
+   --n-gpu-layers 20 \
     -no-cnv
    ```