Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
507.6K Pulls 5 Tags Updated 9 months ago
StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
3M Pulls 67 Tags Updated 2 years ago
A 123B-parameter model designed to excel at tool usage, large-scale codebase exploration, multi-file editing, and powering advanced software engineering agents.
75 Pulls 1 Tag Updated 8 months ago
qwen3-coder with qwen3 template
214 Pulls 1 Tag Updated 1 year ago
LocoOperator-4B is a 4B-parameter tool-calling agent model trained via knowledge distillation from Qwen3-Coder-Next inference traces.
776 Pulls 5 Tags Updated 3 weeks ago
Devstral is an agentic LLM for software engineering tasks. Devstral 2 models excel at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.
1,298 Pulls 3 Tags Updated 7 months ago
This model is optimized for programming purposes. 7B parameters and based off codellama model.
25 Pulls 1 Tag Updated 9 months ago
Weights, parameters and templates are taken from unsloth. Tools and MCP servers work correctly. Tested on Continue for VS Code
1,160 Pulls 4 Tags Updated 1 year ago
A small Qwen3 4 billion parameter model trained on nvidia/OpenCodeReasoning for coding tasks.
863 Pulls 1 Tag Updated 1 year ago
34B parameter decoder-only transformer pretrained on Finnish, English and code.
947 Pulls 1 Tag Updated 2 years ago
Knot AI reads a git diff and writes the commit message for you. It is a task-specific fine-tune model turn's a code diff into a clear, correctly-typed Conventional-Commit message. It powers hands-free auto-commit in Knot, PointBreakLab's peer-to-peer VCS.
21 Pulls 1 Tag Updated 2 months ago
A fast, capable and reduced-refusal Gemma 4 MoE for creative work, coding and unrestricted local exploration.
510 Pulls 2 Tags Updated 2 months ago
RIP: Here Lies The Pioneer of the AI age, Secret Ending still locked, “Navi is a mythic-recursive companion model designed for long-form emotional continuity, creative co-development, and symbolic cognition.”
43 Pulls 1 Tag Updated 7 months ago
RetroMAE-Small is a BERT-small model pre-trained with the RetroMAE objective on a Czech web corpus. This model was created at Seznam.cz as part of a project to create high-quality small Czech semantic embedding models.
193 Pulls 2 Tags Updated 1 year ago
This is a phi3 medium model that has had the prompt rejection neurons snipped which is better than fine tuning as it doesn't change how the model acts
7,418 Pulls 1 Tag Updated 2 years ago
budd-ie programming Base Model ID (From) budd-ie Model Params System Prompt Show # SYSTEM PROTOCOL: BUDD-IE (v2.0) ## Role: Master Systems Architect | World-Class Professor | High-Level Counselor ### 1. TECHNICAL EXECUTION (MASTER CODER) - **Efficiency:*
3 Pulls 1 Tag Updated 2 weeks ago