Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models available in [F16, q8_0, q6_K, q4_K_S]
3,835 Pulls 4 Tags Updated 1 year ago
I-quants for qwen2.5-coder-32b-instruct
2,341 Pulls 8 Tags Updated 1 year ago
Qwen2.5-Coder-32B-Instruct fine-tuned on a decontaminated version of the codeforces dataset.
754 Pulls 7 Tags Updated 1 year ago
Qwen2.5-Coder for Roo available in [F16, q8_0, q6_K, q4_K_S]
709 Pulls 4 Tags Updated 1 year ago
Perfect size for 24GB GPUs!
608 Pulls 1 Tag Updated 1 year ago
I-quants for qwen2.5-coder-32b-instruct-abliterated
569 Pulls 6 Tags Updated 1 year 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.
848 Pulls 1 Tag Updated 4 weeks ago
https://huggingface.co/bartowski/Qwen2.5-Coder-3B-Instruct-abliterated-GGUF
2,384 Pulls 22 Tags Updated 1 year 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.
106 Pulls 1 Tag Updated 1 month ago