From b7f7d05a7e5b3f5da9d571e43703180390a30068 Mon Sep 17 00:00:00 2001 From: Ruonan Wang Date: Thu, 9 May 2024 16:44:12 +0800 Subject: [PATCH] update llama.cpp usage of llama3 (#10975) * update llama.cpp usage of llama3 * fix --- .../doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/readthedocs/source/doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.md b/docs/readthedocs/source/doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.md index cedb256f..98f7b529 100644 --- a/docs/readthedocs/source/doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.md +++ b/docs/readthedocs/source/doc/LLM/Quickstart/llama3_llamacpp_ollama_quickstart.md @@ -79,7 +79,7 @@ Under your current directory, exceuting below command to do inference with Llama .. code-block:: bash - main -ngl 33 -m /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 /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 /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 /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 /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 /Meta-Llama-3-8B-Instruct-Q4_K_M.gguf ``` Below is a sample output on Intel Arc GPU: