update llama.cpp usage of llama3 (#10975)

* update llama.cpp usage of llama3

* fix
This commit is contained in:
Ruonan Wang 2024-05-09 16:44:12 +08:00 committed by GitHub
parent 697ca79eca
commit b7f7d05a7e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -79,7 +79,7 @@ Under your current directory, exceuting below command to do inference with Llama
.. code-block:: bash
main -ngl 33 -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf -n 32 --prompt "Once upon a time, there existed a little girl who liked to have adventures. She wanted to go to places and meet new people, and have fun doing something" -e -ngl 33 --color --no-mmap
main -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf -n 32 --prompt "Once upon a time, there existed a little girl who liked to have adventures. She wanted to go to places and meet new people, and have fun doing something" -e -ngl 33 --color --no-mmap
```
Under your current directory, you can also execute below command to have interactive chat with Llama3:
@ -90,7 +90,7 @@ Under your current directory, you can also execute below command to have interac
.. code-block:: bash
./main -ngl 33 -c 0 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf
./main -ngl 33 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf
.. tab:: Windows
@ -98,7 +98,7 @@ Under your current directory, you can also execute below command to have interac
.. code-block:: bash
main -ngl 33 -c 0 --interactive-first --color -e --in-prefix '<|start_header_id|>user<|end_header_id|>\n\n' --in-suffix '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' -r '<|eot_id|>' -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf
main -ngl 33 --interactive-first --color -e --in-prefix "<|start_header_id|>user<|end_header_id|>\n\n" --in-suffix "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" -r "<|eot_id|>" -m <model_dir>/Meta-Llama-3-8B-Instruct-Q4_K_M.gguf
```
Below is a sample output on Intel Arc GPU: