vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Improve usability of --model-url & related flags (#6930)

Browse source 
* args: default --model to models/ + filename from --model-url or --hf-file (or else legacy models/7B/ggml-model-f16.gguf)

* args: main & server now call gpt_params_handle_model_default

* args: define DEFAULT_MODEL_PATH + update cli docs

* curl: check url of previous download (.json metadata w/ url, etag & lastModified)

* args: fix update to quantize-stats.cpp

* curl: support legacy .etag / .lastModified companion files

* curl: rm legacy .etag file support

* curl: reuse regex across headers callback calls

* curl: unique_ptr to manage lifecycle of curl & outfile

* curl: nit: no need for multiline regex flag

* curl: update failed test (model file collision) + gitignore *.gguf.json
This commit is contained in:
Olivier Chafik 2024-04-30 00:52:50 +01:00 • committed by GitHub
parent b8c1476e44
commit 8843a98c2b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 143 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

6
common/common.h
View file

@ -31,6 +31,8 @@
fprintf(stderr, "%s: built with %s for %s\n", __func__, LLAMA_COMPILER, LLAMA_BUILD_TARGET); \
} while(0)
#define DEFAULT_MODEL_PATH "models/7B/ggml-model-f16.gguf"
// build info
extern int LLAMA_BUILD_NUMBER;
extern char const *LLAMA_COMMIT;
@ -92,7 +94,7 @@ struct gpt_params {
// // sampling parameters
struct llama_sampling_params sparams;
std::string model = "models/7B/ggml-model-f16.gguf"; // model path
std::string model = ""; // model path
std::string model_draft = ""; // draft model for speculative decoding
std::string model_alias = "unknown"; // model alias
std::string model_url = ""; // model url to download
@ -171,6 +173,8 @@ struct gpt_params {
std::vector<std::string> image; // path to image file(s)
};
void gpt_params_handle_model_default(gpt_params & params);
bool parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides);
bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params);