The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
16.2M Pulls 199 Tags Updated 1 year ago
A custom model of Qwen2.5-coder:7B-Instruct with the Qwen2.5-coder:3B-instruct used as a speculative fill model to speed up inference. Primarily made for TabbyML Usage.
391 Pulls 1 Tag Updated 3 weeks ago
A Custom Qwen2.5-coder:14B-instruct model using a Qwen2.5-coder:3B-instruct model for Speculative Fill. Primary usage is for TabbyML.
229 Pulls 1 Tag Updated 3 weeks ago
A Custom Model using Qwen2.5-coder:7B-instruct as a base, and adding my custom Qwen2.5-coder-3b-instuct-spec model which is a Qwen2.5-coder:3b-instruct model using qwen2.5-coder:1.5b model as speculative fill. VERY WIP...
90 Pulls 1 Tag Updated 3 weeks ago
FROM ./Qwen2.5-Coder-3B-Instruct-Q4_K_M.gguf TEMPLATE """{{ .Prompt }}""" PARAMETER temperature 0.4 PARAMETER top_p 0.9 PARAMETER top_k 40 PARAMETER repeat_penalty 1.15 PARAMETER mirostat 2 PARAMETER mirostat_eta 0.2 PARAMETER mirostat_tau 5.0 PARAMETER
60 Pulls 1 Tag Updated 1 week ago
A Custom Qwen2.5-coder:3b-instruct using a Qwen2.5-coder:1.5b model as speculative fill. Primary usage for this model is TabbyML.
66 Pulls 1 Tag Updated 3 weeks ago
This model has been finetuned with data from Agentic Signal (a visual AI agent workflow automation platform with local LLM integration).
34 Pulls 1 Tag Updated 2 weeks ago
A concise, root-cause-first coding assistant built on Qwen2.5-Coder 7B. Debug and generate code with zero filler — runs entirely locally via Ollama.
20 Pulls 1 Tag Updated 1 week ago
Fully decensored Qwen2.5-Coder-3B-Instruct processed with Heretic abliteration. Achieves 3/100 refusals with an exceptionally low KL divergence of 0.0163 — near-zero model degradation on a consumer RTX 4060.
742 Pulls 1 Tag Updated 1 week ago
qwen2.5-auditor is a local Ollama model wrapper built from qwen2.5-coder and tuned for security-focused code review and static analysis; it adopts a strict “Astra” system persona to act like a security engineer/bug-bounty auditor.
595 Pulls 1 Tag Updated 3 months ago
551 Pulls 1 Tag Updated 3 months ago
The model fine-tunes Qwen2.5-Coder-14B for Rust-specific programming tasks using a 191K-example synthetic dataset built via multi-model generation and peer-reviewed validation.
512 Pulls 3 Tags Updated 3 months ago
It's pretty good for rapid code prediction and correction.
456 Pulls 5 Tags Updated 4 months ago
Fine-tuned manim model using Qwen2.5-Coder-14B-Instruct trained on 3blue1brown-manim dataset with 2,407 examples.
401 Pulls 3 Tags Updated 3 months ago
Quantized coding assistant for use on edge devices (Raspberry Pi 5 tested)
386 Pulls 1 Tag Updated 5 months ago
183 Pulls 1 Tag Updated 2 months ago
Lumen writes code, runs shell commands, uses git/GitHub, and fixes bugs autonomously. Fine-tuned on Qwen2.5-Coder-7B-Instruct with LoRA for tool-use and agentic workflows.
179 Pulls 1 Tag Updated 2 months ago
Omini-pyauto-1.5b is a fine-tuned Python automation code generation model built on top of Qwen2.5-Coder-1.5B-Instruct. It specializes in generating production-ready automation scripts for three major frameworks: Playwright, SeleniumBase, and Selenium.
108 Pulls 1 Tag Updated 2 months ago
95 Pulls 3 Tags Updated 2 months ago
92 Pulls 1 Tag Updated 2 months ago