common : streamline the formatting of help (#4890)

* common : streamline the formatting of help

- Separate alternative parameters by a comma

- Do not indent `--version` differently

* Update common/common.cpp

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

common/common.cpp

@@ -818,7 +818,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("\n");
     printf("options:\n");
     printf("  -h, --help            show this help message and exit\n");
-    printf("      --version         show version and build info\n");
+    printf("  --version             show version and build info\n");
     printf("  -i, --interactive     run in interactive mode\n");
     printf("  --interactive-first   run in interactive mode and wait for input right away\n");
     printf("  -ins, --instruct      run in instruction mode (use with Alpaca models)\n");
@@ -915,7 +915,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("                        number of layers to store in VRAM\n");
     printf("  -ngld N, --n-gpu-layers-draft N\n");
     printf("                        number of layers to store in VRAM for the draft model\n");
-    printf("  -ts SPLIT --tensor-split SPLIT\n");
+    printf("  -ts SPLIT, --tensor-split SPLIT\n");
     printf("                        how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
     printf("  -mg i, --main-gpu i   the GPU to use for scratch and small tensors\n");
 #ifdef GGML_USE_CUBLAS
@@ -950,7 +950,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  --override-kv KEY=TYPE:VALUE\n");
     printf("                        advanced option to override model metadata by key. may be specified multiple times.\n");
     printf("                        types: int, float, bool. example: --override-kv tokenizer.ggml.add_bos_token=bool:false\n");
-    printf("  -stc N --print-token-count N\n");
+    printf("  -ptc N, --print-token-count N\n");
     printf("                        print token count every N tokens (default: %d)\n", params.n_print);
     printf("\n");
 #ifndef LOG_DISABLE_LOGS

convert-hf-to-gguf.py

@@ -825,7 +825,7 @@ class PersimmonModel(Model):
         # NOTE: not sure about this change - why does the model not have a rope dimension count when it is smaller
         #       than the head size?
         #       ref: https://github.com/ggerganov/llama.cpp/pull/4889
-        #self.gguf_writer.add_rope_dimension_count(hidden_size // head_count)
+        # self.gguf_writer.add_rope_dimension_count(hidden_size // head_count)
         self.gguf_writer.add_rope_dimension_count(hidden_size // head_count // 2)
 
         self.gguf_writer.add_head_count(head_count)