Discover and read the best of Twitter Threads about #ReplitDevDay
Most recents (1)
At #ReplitDevDay, we announced we’ve trained and are open-sourcing our first Complete Code model.
Introducing replit-code-v1-3b:
- 2.7B params
- 20 languages
- 525B tokens
- 40% better than comparable models
- Trained in 10 days
Take a look at the benchmarks yourself 🧵
Introducing replit-code-v1-3b:
- 2.7B params
- 20 languages
- 525B tokens
- 40% better than comparable models
- Trained in 10 days
Take a look at the benchmarks yourself 🧵
Replit-code-v1-3b & replit-finetuned-v1-3b were trained entirely on code and were meant for single-line code completion.
We didn’t expect either to perform so well on HumanEval, but they did.
replit-finetuned-v1-3b outperformed all OSS code models, even those 5x its size.
We didn’t expect either to perform so well on HumanEval, but they did.
replit-finetuned-v1-3b outperformed all OSS code models, even those 5x its size.
Both models also benchmark impressively well against commercial models.
replit-finetuned-v1-3b is by far the smallest model on the table and it outperformed Codex and LLaMA.
PaLM-Coder is 200x larger and we’re closing in on their performance with much better latency.
replit-finetuned-v1-3b is by far the smallest model on the table and it outperformed Codex and LLaMA.
PaLM-Coder is 200x larger and we’re closing in on their performance with much better latency.
