whatmodel.sh / Yehia 7B Reasoning (preview)

Yehia 7B Reasoning (preview)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Yehia 7B Reasoning (preview) is an open-weights language model from JasperV13, released April 2025. Its published size is 7B parameters. Licence: apache-2.0.

Catalogue identity notes

Community GRPO fine-tune JasperV13/Yehia-7B-Reasoning-preview @f761e88 (created 2025-04-20, apache-2.0; card: 'Finetuned from model: Navid-AI/Yehia-7B-preview', itself built on ALLaM-AI/ALLaM-7B-Instruct-preview; Llama architecture, 4,096-token max_position_embeddings in config.json). 'preview' is part of the repo name. Added in pass 12 for its AraGen-v3 run (held in pass 9 as a single-source model with two precision runs).

Model information sources

Release date ↗ · Weights licence ↗

7,000,559,616 parameters (BF16) in the HF safetensors metadata.

55.7±4.4#301 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Yehia 7B Reasoning (preview), out of 1132 with a score.

#modelscorewhereRAMreleased
397K2-Think MBZUAI IFM (LLM360)56±4local~21GB2025-09
398FuseChat-Llama-3.2-3B-Instruct FuseAI56±2local~3.4GB2024-12
399Yehia 7B Reasoning (preview) JasperV1356±4local~16GB2025-04
400Magistral Medium 1.0 (2506) Mistral56±1comparison only2025-06
401Llama3-Instruct-8B-WPO-HB-v2 wzhouad (WPO)56±2local~35GB2024-07

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 91% of its score
testresultvs the others in its rundifficultycountswhy
AraGen-v3 3C3H score (Inception, Claude Sonnet 4 judge)45.0% ✎▁▁·▁▂▂▄█▄▅▄▄ beats 38/66hard · avg 31%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~14 GB · from huggingface.co/JasperV13 (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='JasperV13/Yehia-7B-Reasoning-preview', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/JasperV13 ↗

$ how the score was worked out · Inception Arabic/Hindi leader… 91%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%Apache-2.0
prior · pull toward the middle▇▇▇ 9%
weighted average= 55.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json