• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

• There are 24 files with 19,943 lines of code.
• 3 very long files (16,352 lines of code)
• 2 long files (1,062 lines of code)
• 4 medium size files (1,482 lines of codeclsfd_ftr_w_mp_ins)
• 5 small files (721 lines of code)
• 10 very small files (326 lines of code)

There are 14 files with lines longer than 120 characters. In total, there are 114 long lines.

File	# lines	# units	# long lines
prompt_guard.ipynb in llama_guard	371	-	18
inference-api.ipynb in api_inference	174	-	17
llama_guard_3_1B.ipynb in llama_guard	7349	-	17
llama_guard_4.ipynb in root	501	-	12
llama-guard-4.ipynb in llama_guard	435	-	10
chatbot_demo.ipynb in gradio_demos	1316	-	9
Llama-Vision FT.ipynb in fine_tune	323	-	8
llama_rag_pipeline.ipynb in llama_rag	7687	-	7
assisted_decoding_70B_3B.ipynb in assisted_decoding	353	-	5
awq.ipynb in local_inference	561	-	4
fp8-405B.ipynb in local_inference	149	-	3
torch_compile_with_torchao.ipynb in performance_optimization	152	-	2
quantized_cache.py in performance_optimization	24	-	1
prompt_reuse.py in performance_optimization	23	-	1