CodeGen provides open-source models for program synthesis and code generation.
Open source
24 alternativesdeepseek-ai/DeepSeek-Coder
DeepSeek Coder is a language model project for code generation and programming tasks.
About deepseek-ai/DeepSeek-Coder
DeepSeek Coder is a series of open-source language models for code generation, completion and infilling. Models are available in 1B, 5.7B, 6.7B and 33B sizes and were trained from scratch on 2T tokens containing 87% code and 13% English and Chinese text.
The models use a 16K window and fill-in-the-blank training to work with project-level context, and include Base versions and instruction-tuned Instruct versions. The repository documents data filtering, training steps, and evaluation on HumanEval, MBPP and DS-1000.
Key features
- Code generation and completion across multiple programming languages
- Project-level code completion with 16K context window
- Fill-in-the-blank code infilling task support
- Model sizes in 1B, 5.7B, 6.7B and 33B versions
- Base models and instruction-tuned Instruct variants
- Training corpus includes 87% code and 13% natural language
Best for: Researchers and developers working with open-source code generation and completion.
Good for
- Open source with model sizes from 1B to 33B
- 16K window supports project-level completion and infilling
- Training and evaluation methods documented in repository
deepseek-ai/DeepSeek-Coder at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
deepseek-ai/DeepSeek-Coder alternatives
Tools and sites you could use instead, ranked by how closely they match.
OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.
Open source
24 alternatives
This repository contains the DeepSeek-V3 language model project and related source files.
Open source
24 alternatives
This repository contains Google Research code for the Flan-T5 language model project.
Open source
24 alternatives
DeepSWE benchmarks coding agents on original, long-horizon software engineering tasks.
Open source
24 alternatives
Code and documentation to train Stanford's Alpaca models, and generate the data.
Open source
24 alternativesPopular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
deepseek-ai/DeepSeek-Coder FAQ
What model sizes are available?
1B, 5.7B, 6.7B and 33B versions, ranging from 1B to 33B.
What data were the models trained on?
2T tokens from scratch, with 87% code and 13% natural language in English and Chinese.
What is the difference between Base and Instruct models?
Base models are the pre-trained foundational models, while Instruct models result from instruction fine-tuning on 2B tokens of instruction data.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.