open-r1_OlympicCoder-7B-GGUFオープンソースコード生成モデル

ホーム

Open R1 OlympicCoder 7B GGUF

bartowskiによって開発

OlympicCoder-7Bはコード生成に特化した7Bパラメータの大規模言語モデルで、open-r1/OlympicCoder-7Bをllama.cppで量子化したものです。複数の量子化レベルを選択可能です。

大規模言語モデル英語オープンソースライセンス:Apache-2.0 #コード生成 #競技プログラミング #マルチレベル量子化

ダウンロード数 5,859

リリース時間 : 3/11/2025

モデル概要

これはプログラミングコンテストやコード生成タスクに最適化された7Bパラメータの言語モデルで、BF16からQ2_Kまでの様々な量子化バージョンを提供し、異なるハードウェア環境に対応しています。

モデル特徴

多様な量子化オプション

BF16からQ2_Kまで22種類の量子化バージョンを提供し、様々なハードウェア性能とストレージ要件に対応

コード生成最適化

Codeforces競技データセットでトレーニングされており、プログラミングコンテストの問題解決に優れている

クロスプラットフォーム対応

LM Studio、llama.cppなど複数の実行環境をサポートし、ARM/AVXアーキテクチャと互換性がある

インテリジェントな重み付け

一部の量子化バージョンでは、埋め込み層と出力層の重みに高精度のQ8_0量子化を適用

モデル能力

コード生成

プログラミング問題解答

アルゴリズム実装

テキスト補完

使用事例

プログラミング教育

プログラミングコンテストトレーニング

学生がCodeforcesのようなプログラミングコンテストの問題を理解・解決するのを支援

コンテスト要件に合致したコードソリューションを生成可能

開発支援

コード自動補完

IDEでインテリジェントなコード補完を提供

開発効率を向上させ、繰り返しコーディング作業を削減

quantized_by: bartowski pipeline_tag: text-generation language:

en license: apache-2.0 base_model: open-r1/OlympicCoder-7B datasets:
open-r1/codeforces-cots

Llamacpp imatrix Quantizations of OlympicCoder-7B by open-r1

Using llama.cpp release b4867 for quantization.

Original model: https://huggingface.co/open-r1/OlympicCoder-7B

All quants made using imatrix option with dataset from here

Run them in LM Studio

Run them directly with llama.cpp, or any other llama.cpp based project

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Split	Description
OlympicCoder-7B-bf16.gguf	bf16	15.24GB	false	Full BF16 weights.
OlympicCoder-7B-Q8_0.gguf	Q8_0	8.10GB	false	Extremely high quality, generally unneeded but max available quant.
OlympicCoder-7B-Q6_K_L.gguf	Q6_K_L	6.52GB	false	Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
OlympicCoder-7B-Q6_K.gguf	Q6_K	6.25GB	false	Very high quality, near perfect, recommended.
OlympicCoder-7B-Q5_K_L.gguf	Q5_K_L	5.78GB	false	Uses Q8_0 for embed and output weights. High quality, recommended.
OlympicCoder-7B-Q5_K_M.gguf	Q5_K_M	5.44GB	false	High quality, recommended.
OlympicCoder-7B-Q5_K_S.gguf	Q5_K_S	5.32GB	false	High quality, recommended.
OlympicCoder-7B-Q4_K_L.gguf	Q4_K_L	5.09GB	false	Uses Q8_0 for embed and output weights. Good quality, recommended.
OlympicCoder-7B-Q4_1.gguf	Q4_1	4.87GB	false	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
OlympicCoder-7B-Q4_K_M.gguf	Q4_K_M	4.68GB	false	Good quality, default size for most use cases, recommended.
OlympicCoder-7B-Q3_K_XL.gguf	Q3_K_XL	4.57GB	false	Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
OlympicCoder-7B-Q4_K_S.gguf	Q4_K_S	4.46GB	false	Slightly lower quality with more space savings, recommended.
OlympicCoder-7B-Q4_0.gguf	Q4_0	4.44GB	false	Legacy format, offers online repacking for ARM and AVX CPU inference.
OlympicCoder-7B-IQ4_NL.gguf	IQ4_NL	4.44GB	false	Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference.
OlympicCoder-7B-IQ4_XS.gguf	IQ4_XS	4.22GB	false	Decent quality, smaller than Q4_K_S with similar performance, recommended.
OlympicCoder-7B-Q3_K_L.gguf	Q3_K_L	4.09GB	false	Lower quality but usable, good for low RAM availability.
OlympicCoder-7B-Q3_K_M.gguf	Q3_K_M	3.81GB	false	Low quality.
OlympicCoder-7B-IQ3_M.gguf	IQ3_M	3.57GB	false	Medium-low quality, new method with decent performance comparable to Q3_K_M.
OlympicCoder-7B-Q2_K_L.gguf	Q2_K_L	3.55GB	false	Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
OlympicCoder-7B-Q3_K_S.gguf	Q3_K_S	3.49GB	false	Low quality, not recommended.
OlympicCoder-7B-IQ3_XS.gguf	IQ3_XS	3.35GB	false	Lower quality, new method with decent performance, slightly better than Q3_K_S.
OlympicCoder-7B-IQ3_XXS.gguf	IQ3_XXS	3.11GB	false	Lower quality, new method with decent performance, comparable to Q3 quants.
OlympicCoder-7B-Q2_K.gguf	Q2_K	3.02GB	false	Very low quality but surprisingly usable.
OlympicCoder-7B-IQ2_M.gguf	IQ2_M	2.78GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/open-r1_OlympicCoder-7B-GGUF --include "open-r1_OlympicCoder-7B-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/open-r1_OlympicCoder-7B-GGUF --include "open-r1_OlympicCoder-7B-Q8_0/*" --local-dir ./

You can either specify a new local-dir (open-r1_OlympicCoder-7B-Q8_0) or download them all in place (./)

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Click to view Q4_0_X_X information (deprecated

I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.

Click to view benchmarks on an AVX2 system (EPYC7702)

model	size	params	backend	threads	test	t/s	% (vs Q4_0)
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	pp512	204.03 ± 1.03	100%
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	pp1024	282.92 ± 0.19	100%
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	pp2048	259.49 ± 0.44	100%
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	tg128	39.12 ± 0.27	100%
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	tg256	39.31 ± 0.69	100%
qwen2 3B Q4_0	1.70 GiB	3.09 B	CPU	64	tg512	40.52 ± 0.03	100%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	pp512	301.02 ± 1.74	147%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	pp1024	287.23 ± 0.20	101%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	pp2048	262.77 ± 1.81	101%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	tg128	18.80 ± 0.99	48%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	tg256	24.46 ± 3.04	83%
qwen2 3B Q4_K_M	1.79 GiB	3.09 B	CPU	64	tg512	36.32 ± 3.59	90%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	pp512	271.71 ± 3.53	133%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	pp1024	279.86 ± 45.63	100%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	pp2048	320.77 ± 5.00	124%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	tg128	43.51 ± 0.05	111%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	tg256	43.35 ± 0.09	110%
qwen2 3B Q4_0_8_8	1.69 GiB	3.09 B	CPU	64	tg512	42.60 ± 0.31	105%

Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation

Which file should I choose?

Click here for details

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.