still not really working right

This commit is contained in:
LostRuins Concedo
2025-11-09 01:57:48 +08:00
48 changed files with 3193 additions and 2705 deletions
+7 -1018
View File
File diff suppressed because it is too large Load Diff
+2 -2
View File
@@ -59,8 +59,8 @@ struct common_arg {
common_arg & set_sparam();
bool in_example(enum llama_example ex);
bool is_exclude(enum llama_example ex);
bool get_value_from_env(std::string & output);
bool has_value_from_env();
bool get_value_from_env(std::string & output) const;
bool has_value_from_env() const;
std::string to_string();
};
+4
View File
@@ -503,6 +503,10 @@ struct common_params {
// return false from callback to abort model loading or true to continue
llama_progress_callback load_progress_callback = NULL;
void * load_progress_callback_user_data = NULL;
bool has_speculative() const {
return !speculative.model.path.empty() || !speculative.model.hf_repo.empty();
}
};
// call once at the start of a program if it uses libcommon
+1036
View File
File diff suppressed because it is too large Load Diff
+41
View File
@@ -0,0 +1,41 @@
#pragma once
#include <string>
struct common_params_model;
//
// download functionalities
//
struct common_hf_file_res {
std::string repo; // repo name with ":tag" removed
std::string ggufFile;
std::string mmprojFile;
};
// resolve and download model from Docker registry
// return local path to downloaded model file
std::string common_docker_resolve_model(const std::string & docker);
/**
* Allow getting the HF file from the HF repo with tag (like ollama), for example:
* - bartowski/Llama-3.2-3B-Instruct-GGUF:q4
* - bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M
* - bartowski/Llama-3.2-3B-Instruct-GGUF:q5_k_s
* Tag is optional, default to "latest" (meaning it checks for Q4_K_M first, then Q4, then if not found, return the first GGUF file in repo)
*
* Return pair of <repo, file> (with "repo" already having tag removed)
*
* Note: we use the Ollama-compatible HF API, but not using the blobId. Instead, we use the special "ggufFile" field which returns the value for "hf_file". This is done to be backward-compatible with existing cache files.
*/
common_hf_file_res common_get_hf_file(
const std::string & hf_repo_with_tag,
const std::string & bearer_token,
bool offline);
// returns true if download succeeded
bool common_download_model(
const common_params_model & model,
const std::string & bearer_token,
bool offline);