Search:
Match:
2 results
Research#llm👥 CommunityAnalyzed: Jan 3, 2026 06:20

Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context

Published:Oct 31, 2023 17:40
1 min read
Hacker News

Analysis

The article announces a new Phind model that outperforms GPT-4 in coding tasks while being significantly faster. It highlights the model's performance on HumanEval and emphasizes its real-world helpfulness based on user feedback. The speed advantage is attributed to the use of NVIDIA's TensorRT-LLM library on H100s. The article also mentions the model's foundation on open-source CodeLlama-34B fine-tunes.
Reference

“The current 7th-generation Phind Model is built on top of our open-source CodeLlama-34B fine-tunes that were the first models to beat GPT-4’s score on HumanEval and are still the best open source coding models overall by a wide margin.”

PermalinkHacker News
Research#AI Code Generation👥 CommunityAnalyzed: Jan 3, 2026 06:20

Fine-tuned CodeLlama-34B Beats GPT-4 on HumanEval

Published:Aug 25, 2023 22:08
1 min read
Hacker News

Analysis

The article reports on fine-tuning CodeLlama-34B and CodeLlama-34B-Python on a proprietary dataset to achieve higher pass@1 scores on HumanEval compared to GPT-4. The authors emphasize the use of instruction-answer pairs in their dataset, native fine-tuning, and the application of OpenAI's decontamination methodology to ensure result validity. The training process involved DeepSpeed ZeRO 3, Flash Attention 2, and 32 A100-80GB GPUs, completing in three hours. The article highlights a significant achievement in code generation capabilities.
Reference

“We have fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieved 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieved 67%.”

PermalinkHacker News