Update llama.cpp.rst (#739)

* Update llama.cpp.rst

Llama.cpp just updated their program names, I've updated the article to use the new name.

quantize -> llama-quantize
main -> llama-cli
simple -> llama-simple

[Check out the PR](ggml-org/llama.cpp#7809)

* Updated llama.cpp.rst ( removed -cml )

* Update llama.cpp.rst

---------

Co-authored-by: Ren Xuancheng <[email protected]>

Author: Mohammed Noumaan Ahamed

docs/source/run_locally/llama.cpp.rst

@@ -55,14 +55,18 @@ Then you can run the model with the following command:
 
 .. code:: bash
 
-   ./main -m qwen2-7b-instruct-q5_k_m.gguf -n 512 --color -i -cml -f prompts/chat-with-qwen.txt
+   ./llama-cli -m qwen2-7b-instruct-q5_k_m.gguf \
+  -n 512 -co -i -if -f prompts/chat-with-qwen.txt \
+  --in-prefix "<|im_start|>user\n" \
+  --in-suffix "<|im_end|>\n<|im_start|>assistant\n" \
+  -ngl 80 -fa
 
 where ``-n`` refers to the maximum number of tokens to generate. There
 are other hyperparameters for you to choose and you can run
 
 .. code:: bash
 
-   ./main -h
+   ./llama-cli -h
 
 to figure them out.
 
@@ -92,7 +96,7 @@ Then you can run the test with the following command:
 
 .. code:: bash
 
-   ./perplexity -m models/7B/ggml-model-q4_0.gguf -f wiki.test.raw
+   ./llama-perplexity -m <gguf_path> -f wiki.test.raw
 
 where the output is like