From d07c621393fab6cf32f3add2aa65e4d5331d4a67 Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Wed, 19 Feb 2025 12:29:52 +0100 Subject: [PATCH] common : add llama.vim preset for Qwen2.5 Coder (#11945) This commit adds a preset for llama.vim to use the default Qwen 2.5 Coder models. The motivation for this change is to make it easier to start a server suitable to be used with the llama.vim plugin. For example, the server can be started with a command like the following: ```console $ llama.vim --fim-qwen-1.5b-default ``` Refs: https://github.com/ggml-org/llama.cpp/issues/10932 --- common/arg.cpp | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/common/arg.cpp b/common/arg.cpp index eb8beccac..3c169b5b5 100644 --- a/common/arg.cpp +++ b/common/arg.cpp @@ -2502,5 +2502,53 @@ common_params_context common_params_parser_init(common_params & params, llama_ex } ).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER})); + add_opt(common_arg( + {"--fim-qwen-1.5b-default"}, + string_format("use default Qwen 2.5 Coder 1.5B (note: can download weights from the internet)"), + [](common_params & params) { + params.hf_repo = "ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF"; + params.hf_file = "qwen2.5-coder-1.5b-q8_0.gguf"; + params.port = 8012; + params.n_gpu_layers = 99; + params.flash_attn = true; + params.n_ubatch = 1024; + params.n_batch = 1024; + params.n_ctx = 0; + params.n_cache_reuse = 256; + } + ).set_examples({LLAMA_EXAMPLE_SERVER})); + + add_opt(common_arg( + {"--fim-qwen-3b-default"}, + string_format("use default Qwen 2.5 Coder 3B (note: can download weights from the internet)"), + [](common_params & params) { + params.hf_repo = "ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF"; + params.hf_file = "qwen2.5-coder-3b-q8_0.gguf"; + params.port = 8012; + params.n_gpu_layers = 99; + params.flash_attn = true; + params.n_ubatch = 1024; + params.n_batch = 1024; + params.n_ctx = 0; + params.n_cache_reuse = 256; + } + ).set_examples({LLAMA_EXAMPLE_SERVER})); + + add_opt(common_arg( + {"--fim-qwen-7b-default"}, + string_format("use default Qwen 2.5 Coder 7B (note: can download weights from the internet)"), + [](common_params & params) { + params.hf_repo = "ggml-org/Qwen2.5-Coder-7B-Q8_0-GGUF"; + params.hf_file = "qwen2.5-coder-7b-q8_0.gguf"; + params.port = 8012; + params.n_gpu_layers = 99; + params.flash_attn = true; + params.n_ubatch = 1024; + params.n_batch = 1024; + params.n_ctx = 0; + params.n_cache_reuse = 256; + } + ).set_examples({LLAMA_EXAMPLE_SERVER})); + return ctx_arg; }