Workflow · saas · workflow
Meta releases Code Llama: an open large language model for code generation, completion, and debugging
Developer workflows needed tools to become faster and more efficient, the barrier to entry for people learning to code needed to be lowered, and open-source code-specific LLMs lagged behind proprietary alternatives.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Developer submits text prompt
A user provides a text or code prompt to request code generation.
Tools used
Code LlamaLlama 2PyTorchHumanEvalMBPP
Outcome
Code Llama 34B scored 53.7% on HumanEval and 56.2% on MBPP, outperforming other open-source code-specific LLMs and performing on par with ChatGPT, while supporting contexts up to 100,000 tokens.
Results
Volume53.7%
Running sinceJan 29, 2024 (70B model release)
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
code generationknowledge basemetric backedproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedsoftwareaccuracy improvementemployee productivitytechnical build writeup