From 5372f9bdb0cbd7bc529897db92b98d1bc9d4bd16 Mon Sep 17 00:00:00 2001
From: Amir <amir_zia@outlook.com>
Date: Fri, 17 May 2024 22:23:10 +0000
Subject: [PATCH] examples: cache hf model when --model not provided

---
 common/common.cpp       | 9 ++++++---
 examples/main/README.md | 2 ++
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/common/common.cpp b/common/common.cpp
index ab3d739a0..23ec4de64 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1354,7 +1354,12 @@ void gpt_params_handle_model_default(gpt_params & params) {
             }
             params.hf_file = params.model;
         } else if (params.model.empty()) {
-            params.model = get_cache_directory() + string_split(params.hf_file, '/').back();
+            std::string cache_directory = get_cache_directory();
+            const bool success = create_directory_with_parents(cache_directory);
+            if (!success) {
+                throw std::runtime_error("failed to create cache directory: " + cache_directory);
+            }
+            params.model = cache_directory + string_split(params.hf_file, '/').back();
         }
     } else if (!params.model_url.empty()) {
         if (params.model.empty()) {
@@ -2549,12 +2554,10 @@ std::string get_cache_directory() {
         cache_directory += "llama.cpp";
         cache_directory += DIRECTORY_SEPARATOR;
     }
-
     const bool success = create_directory_with_parents(cache_directory);
     if (!success) {
         throw std::runtime_error("failed to create cache directory: " + cache_directory);
     }
-
     return cache_directory;
 }
 
diff --git a/examples/main/README.md b/examples/main/README.md
index 97e2ae4c2..ee930f4e7 100644
--- a/examples/main/README.md
+++ b/examples/main/README.md
@@ -325,3 +325,5 @@ These options provide extra functionality and customization when running the LLa
 -   `-ts SPLIT, --tensor-split SPLIT`: When using multiple GPUs this option controls how large tensors should be split across all GPUs. `SPLIT` is a comma-separated list of non-negative values that assigns the proportion of data that each GPU should get in order. For example, "3,2" will assign 60% of the data to GPU 0 and 40% to GPU 1. By default the data is split in proportion to VRAM but this may not be optimal for performance.
 -   `--lora FNAME`: Apply a LoRA (Low-Rank Adaptation) adapter to the model (implies --no-mmap). This allows you to adapt the pretrained model to specific tasks or domains.
 -   `--lora-base FNAME`: Optional model to use as a base for the layers modified by the LoRA adapter. This flag is used in conjunction with the `--lora` flag, and specifies the base model for the adaptation.
+
+-   `-hfr URL --hf-repo URL`: The url to the Hugging Face model repository. Used in conjunction with `--hf-file` or `-hff`. The model is downloaded and stored in the file provided by `-m` or `--model`. If `-m` is not provided, the model is auto-stored in the path specified by the `LLAMA_CACHE` environment variable  or in an OS-specific local cache.