CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : add llama.vim preset for Qwen2.5 Coder (#11945)

Browse Source 
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
This commit is contained in:
Daniel Bevenius
2025-02-19 12:29:52 +01:00
committed by GitHub
parent abd4d0bc4f
commit d07c621393
1 changed files with 48 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
common/arg.cpp
View File

@@ -2502,5 +2502,53 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
} }
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_SERVER})); ).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; return ctx_arg;
} }