Code Model Training Transformer Models

There are 16 code model training models tracked. The highest-rated is oripress/AlgoTune at 49/100 with 95 stars.

Get all 16 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=code-model-training&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	oripress/AlgoTune AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and...	49	Emerging	95	Python
2	xjywhu/Awesome-Multimodal-LLM-for-Code Multimodal Large Language Models for Code Generation under Multimodal Scenarios	40	Emerging	221	—
3	jie-jw-wu/human-eval-comm HumanEvalComm: Evaluating Communication Skill of Code LLM and LLM Agent	38	Emerging	11	Python
4	juyongjiang/CodeUp CodeUp: A Multilingual Code Generation Llama-X Model with...	37	Emerging	127	Python
5	JHansiduYapa/Fine-Tuning-a-Small-Language-Model-for-Cypher-Query-Generation This project fine-tunes Unsloth's Gemma-3 4B IT (4-bit) model to translate...	36	Emerging	6	Jupyter Notebook
6	Gen-Verse/ReasonFlux [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux,...	34	Emerging	524	Python
7	martin-wey/cl-code-apis Replication package of the paper "On the Usage of Continual Learning for...	33	Emerging	5	Python
8	skpig/MPSC [ACL 2024] Enhancing Large Language Models in Coding Through...	30	Emerging	6	Python
9	xlang-ai/text2reward [ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for...	29	Experimental	201	Jupyter Notebook
10	amazon-science/llm-code-preference Training and Benchmarking LLMs for Code Preference.	29	Experimental	38	Python
11	sanskar9999/CodeEvolveLLM A framework for using local LLMs (Qwen2.5-coder 7B) that are fine-tuned...	28	Experimental	8	Python
12	TingjiaInFuture/pixrep Let LLMs see your codebase just like you do.	26	Experimental	9	Python
13	carlos-life/OpenEvolve Evolve algorithms with LLMs. Open-source AlphaEvolve alternative. Uses...	22	Experimental	—	Python
14	PAN001/LeToRr LeToRr: Learning to Re-rank with Application in Code Generation	21	Experimental	1	—
15	Training-Datasmith/olmo3-code-150m-pretrain Pre-training a ~150M parameter code-specialized language model using OLMo 3...	19	Experimental	—	Jupyter Notebook
16	dakshjain-1616/nemotron3-super-vs-gpt5.4-nano Head-to-head benchmark comparing Nemotron and GPT-5.4-nano on code generation tasks	14	Experimental	—	Python