Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 19, 2025
Merged

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

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 48 additions & 0 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
}
Loading