Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Phind-CodeLlama-34B-v1

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

100K tokens

Max output length

No data

Model type

编程大模型

Release date

2023-08-26

Model file size

70GB

MoE architecture

Total params / Active params

340.0B / N/A

Knowledge cutoff

No data

Phind-CodeLlama-34B-v1

Open source & experience

Code license

Llama 2 Community License Agreement

Weights license

Llama 2 Community License Agreement- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/Phind/Phind-CodeLlama-34B-Python-v1

Live demo

No live demo

Phind-CodeLlama-34B-v1

Official resources

Paper

Beating GPT-4 on HumanEval with a Fine-Tuned CodeLlama-34B

DataLearnerAI blog

No blog post yet

Phind-CodeLlama-34B-v1

API details

API speed

No data

No public API pricing yet.

Phind-CodeLlama-34B-v1

Benchmark Results

No benchmark data to show.

Phind-CodeLlama-34B-v1

Publisher

Phind

View publisher details

Phind-CodeLlama-34B-v1

Model Overview

Phind-CodeLlama-34B-v1是由Phind开源的基于CodeLlama-34B微调的编程大模型。

Phind-CodeLlama-34B-v1是基于8万个高质量编程数据集进行微调的。该数据集是Phind内部数据集，没有公开。包含了指令和回答结果，而不是代码补全的例子。

在HumanEval的Pass@1的评测上，该模型得分67.6%，超过了其基础模型CodeLlama-34B-Python的48.8%。

关于它的具体排名参考DataLearner编程大模型排行榜： https://www.datalearner.com/ai-models/llm-coding-evaluation

Foundation model

CodeLLaMA

View details

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送