minor : fix trailing whitespace (#5538)

This is a follup of Commit fc0c8d286a
("llava : update surgery script to not remove tensors") but this time
the change is to the BakLLaVA specific part of the surgery script.

I've been able to test this using SkunkworksAI/BakLLaVA-1 and it works
as expected using the instructions in README.md.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

examples/llava/llava-surgery.py

@@ -25,9 +25,6 @@ if len(clip_tensors) > 0:
     clip = {name.replace("vision_tower.vision_tower.", ""): checkpoint[name].float() for name in clip_tensors}
     torch.save(clip, f"{args.model}/llava.clip")
 
-    # remove these tensors
-    for name in clip_tensors:
-        del checkpoint[name]
 
     # added tokens should be removed to be able to convert Mistral models
     if os.path.exists(f"{args.model}/added_tokens.json"):
@@ -35,7 +32,6 @@ if len(clip_tensors) > 0:
             f.write("{}\n")
 
 
-    torch.save(checkpoint, path)
 
 print("Done!")
 print(f"Now you can convert {args.model} to a regular LLaMA GGUF file.")

llama.cpp

@@ -12525,7 +12525,7 @@ static std::string trim(const std::string & str) {
 // This function uses heuristic checks to determine commonly used template. It is not a jinja parser.
 static int32_t llama_chat_apply_template_internal(
     const std::string & tmpl,
-    const std::vector<const llama_chat_message *> & chat, 
+    const std::vector<const llama_chat_message *> & chat,
     std::string & dest, bool add_ass) {
     // Taken from the research: https://github.com/ggerganov/llama.cpp/issues/5527
     std::stringstream ss;