Skip to content

llama-run: add support for downloading models from ModelScope #13370

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
May 9, 2025
Merged

llama-run: add support for downloading models from ModelScope #13370

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions tools/run/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,8 @@ Examples:
llama-run ollama://smollm:135m
llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
llama-run huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
llama-run ms://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
llama-run modelscope://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
llama-run https://example.com/some-file1.gguf
llama-run some-file2.gguf
llama-run file://some-file3.gguf
Expand Down
22 changes: 18 additions & 4 deletions tools/run/run.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,7 @@ class Opt {
"Commands:\n"
" model\n"
" Model is a string with an optional prefix of \n"
" huggingface:// (hf://), ollama://, https:// or file://.\n"
" huggingface:// (hf://), modelscope:// (ms://), ollama://, https:// or file://.\n"
" If no protocol is specified and a file exists in the specified\n"
" path, file:// is assumed, otherwise if a file does not exist in\n"
" the specified path, ollama:// is assumed. Models that are being\n"
Expand All @@ -282,6 +282,9 @@ class Opt {
" llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf\n"
" llama-run "
"huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf\n"
" llama-run ms://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf\n"
" llama-run "
"modelscope://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf\n"
" llama-run https://example.com/some-file1.gguf\n"
" llama-run some-file2.gguf\n"
" llama-run file://some-file3.gguf\n"
Expand Down Expand Up @@ -689,16 +692,14 @@ class LlamaData {
return 0;
}

int huggingface_dl(std::string & model, const std::string & bn) {
int dl_from_endpoint(std::string & model_endpoint, std::string & model, const std::string & bn) {
// Find the second occurrence of '/' after protocol string
size_t pos = model.find('/');
pos = model.find('/', pos + 1);
std::string hfr, hff;
std::vector<std::string> headers = { "User-Agent: llama-cpp", "Accept: application/json" };
std::string url;

std::string model_endpoint = get_model_endpoint();

if (pos == std::string::npos) {
auto [model_name, manifest_url] = extract_model_and_tag(model, model_endpoint + "v2/");
hfr = model_name;
Expand All @@ -720,6 +721,16 @@ class LlamaData {
return download(url, bn, true, headers);
}

int modelscope_dl(std::string & model, const std::string & bn) {
std::string model_endpoint = "https://modelscope.cn/models/";
return dl_from_endpoint(model_endpoint, model, bn);
}

int huggingface_dl(std::string & model, const std::string & bn) {
std::string model_endpoint = get_model_endpoint();
return dl_from_endpoint(model_endpoint, model, bn);
}

int ollama_dl(std::string & model, const std::string & bn) {
const std::vector<std::string> headers = { "Accept: application/vnd.docker.distribution.manifest.v2+json" };
if (model.find('/') == std::string::npos) {
Expand Down Expand Up @@ -837,6 +848,9 @@ class LlamaData {
rm_until_substring(model_, "hf.co/");
rm_until_substring(model_, "://");
ret = huggingface_dl(model_, bn);
} else if (string_starts_with(model_, "ms://") || string_starts_with(model_, "modelscope://")) {
rm_until_substring(model_, "://");
ret = modelscope_dl(model_, bn);
} else if ((string_starts_with(model_, "https://") || string_starts_with(model_, "http://")) &&
!string_starts_with(model_, "https://ollama.com/library/")) {
ret = download(model_, bn, true);
Expand Down
Loading