mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-19 01:05:09 +02:00
Merge commit '4ef9301e4de5ea8f5ebf20b107cf30de0070bf2a' into concedo_experimental
# Conflicts: # .github/labeler.yml # docs/multimodal.md # embd_res/ggml-vocab-gemma-4.gguf # embd_res/ggml-vocab-gemma-4.gguf.inp # embd_res/ggml-vocab-gemma-4.gguf.out # ggml/src/ggml-sycl/fattn-tile.cpp # ggml/src/ggml-sycl/fattn-tile.hpp # ggml/src/ggml-sycl/fattn-vec.hpp # ggml/src/ggml-sycl/fattn.cpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-f16-q8_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_0-q8_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q4_1-q8_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_0-q8_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q5_1-q8_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-f16.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q4_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_0.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q5_1.cpp # ggml/src/ggml-sycl/template-instances/fattn-vec-instance-q8_0-q8_0.cpp # tests/CMakeLists.txt # tests/test-jinja.cpp # tools/mtmd/CMakeLists.txt
This commit is contained in:
+11
-1
@@ -595,6 +595,10 @@ static hf_cache::hf_file find_best_model(const hf_cache::hf_files & files,
|
||||
for (const auto & f : files) {
|
||||
if (gguf_filename_is_model(f.path) &&
|
||||
std::regex_search(f.path, pattern)) {
|
||||
auto split = get_gguf_split_info(f.path);
|
||||
if (split.count > 1 && split.index != 1) {
|
||||
continue;
|
||||
}
|
||||
return f;
|
||||
}
|
||||
}
|
||||
@@ -604,6 +608,10 @@ static hf_cache::hf_file find_best_model(const hf_cache::hf_files & files,
|
||||
if (tag.empty()) {
|
||||
for (const auto & f : files) {
|
||||
if (gguf_filename_is_model(f.path)) {
|
||||
auto split = get_gguf_split_info(f.path);
|
||||
if (split.count > 1 && split.index != 1) {
|
||||
continue;
|
||||
}
|
||||
return f;
|
||||
}
|
||||
}
|
||||
@@ -622,6 +630,7 @@ static void list_available_gguf_files(const hf_cache::hf_files & files) {
|
||||
}
|
||||
|
||||
struct hf_plan {
|
||||
hf_cache::hf_file primary;
|
||||
hf_cache::hf_files model_files;
|
||||
hf_cache::hf_file mmproj;
|
||||
};
|
||||
@@ -667,6 +676,7 @@ static hf_plan get_hf_plan(const common_params_model & model,
|
||||
}
|
||||
}
|
||||
|
||||
plan.primary = primary;
|
||||
plan.model_files = get_split_files(all, primary);
|
||||
|
||||
if (opts.download_mmproj) {
|
||||
@@ -753,7 +763,7 @@ common_download_model_result common_download_model(const common_params_model
|
||||
for (const auto & f : hf.model_files) {
|
||||
hf_cache::finalize_file(f);
|
||||
}
|
||||
result.model_path = hf.model_files[0].final_path;
|
||||
result.model_path = hf.primary.final_path;
|
||||
|
||||
if (!hf.mmproj.path.empty()) {
|
||||
result.mmproj_path = hf_cache::finalize_file(hf.mmproj);
|
||||
|
||||
Reference in New Issue
Block a user