BigCode

StarCoder2 7B

Name: StarCoder2 7B
Rating: 49 (193 reviews)
Author: BigCode

現行

HuggingFace

9.7Kダウンロード215いいねFeb 2024公開日16K トークンコンテキストBigCode OpenRAIL-Mライセンス2 入門品質

StarCoder2 7B (7B parameters) requires approximately 6.3 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 8 GB of VRAM.

はじめに

— コピー&ペーストでローカル実行

Copy-paste commands to run StarCoder2 7B on your machine.

Run

lms load starcoder2-7b && lms server start

Quick specs

Parameters7B

Architecturedense

Context16K tokens

Modalitycode

Min RAM2.7 GB

Rec. RAM4.3 GB (Q4_K_M)

LicenseBigCode OpenRAIL-M

FamilyStarCoder2

✓ Code

About this model

- Project Website: bigcode-project.org - Paper: Link - Point of Contact: [email protected] - Languages: 17 Programming languages

•Model Summary
•Limitations
•Training
•License
•Citation

StarCoder2 7Bのおすすめ

このモデルを実行

StarCoder2 7B on RTX 3080 10GB StarCoder2 7B on RTX 3080 Ti 12GB StarCoder2 7B on RTX 3080 12GB

量子化オプション

量子化レベル別VRAM推定値

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	2.7 GB	Low	—
Q3_K_S	3	3.4 GB	Low	—
NVFP4	4	3.9 GB	Medium	—
Q4_K_M	4	4.3 GB	Medium	—
Q5_K_M	5	5.0 GB	High	—
Q6_K	6	5.7 GB	High	—
Q8_0	8	7.5 GB	Very High	—
F16	16	14.3 GB	Maximum	—

Quality benchmarks

StarCoder2 7B benchmark scores

Benchmark verified

Coding

SWE-bench Verified—

HumanEval+35.4%

Aider Polyglot—

LiveCodeBench—

Reasoning

MMLU-Pro7.1%

GPQA Diamond0.2%

MATH-5003.1%

ARC Challenge—

General

Chatbot Arena—

IFEval22.1%

Source: official · 2024-02-28

ハードウェア互換性

全ハードウェアの適合度推定

カリキュレーターを開く

Computing compatibility...

メモリ内訳

Reference: RTX 2060 6GB

Weights4.3 GB

KV Cache0.5 GB

Runtime0.9 GB

Headroom0.6 GB

よくある質問