14 models
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.
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
Decensored Qwen2.5-Coder-3B-Instruct with 3/100 refusals and near-zero KL divergence via Heretic abliteration.
https://huggingface.co/bartowski/Qwen2.5-Coder-3B-Instruct-abliterated-GGUF
Adapted for Cline tool / Roo Code use in VS Code fused model , hybrid of DeepSeekR1 and Qwen2.5 coder, from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models available in [F16, q8_0, q6_K, q4_K_S]
Qwen2.5-Coder for Roo available in [F16, q8_0, q6_K, q4_K_S]
Qwen2.5-Coder-32B-Instruct fine-tuned on a decontaminated version of the codeforces dataset.
Qwen2.5 Coder 32B with the corrected 128k context
This repo contains the instruction-tuned 3B Qwen2.5-Coder model in the GGUF Format: https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF/tree/main
Perfect size for 24GB GPUs!
Quantized version of Qwen2.5-32B optimized for tool usage with Cline / Roo Code and complex problem solving.