Mini-Coder-v2 is build on top of upscaled Qwen3.5-9B model with Continual Pretraining (CPT), we feed ~34k high-quality curated luau raw codes to improves the luau coding tasks capability.
This model present a upscaled of Qwen3.5-9B from only 32 layers to 56 layers for a deeper reasoning capability! This model parameters is 15.07B with Vision, 14.67B without Vision.
Uploaded finetuned model
Developed by:
khtsly
License:
apache-2.0
Finetuned from model :
khtsly/Mini-Coder-v2-noft
This qwen3_5 model was trained 2x faster with
Unsloth
and Huggingface's TRL library.
Runs of khtsly Mini-Coder-v2-noft on huggingface.co
175
Total runs
0
24-hour runs
0
3-day runs
-366
7-day runs
-347
30-day runs
More Information About Mini-Coder-v2-noft huggingface.co Model
Mini-Coder-v2-noft huggingface.co is an AI model on huggingface.co that provides Mini-Coder-v2-noft's model effect (), which can be used instantly with this khtsly Mini-Coder-v2-noft model. huggingface.co supports a free trial of the Mini-Coder-v2-noft model, and also provides paid use of the Mini-Coder-v2-noft. Support call Mini-Coder-v2-noft model through api, including Node.js, Python, http.
Mini-Coder-v2-noft huggingface.co is an online trial and call api platform, which integrates Mini-Coder-v2-noft's modeling effects, including api services, and provides a free online trial of Mini-Coder-v2-noft, you can try Mini-Coder-v2-noft online for free by clicking the link below.
khtsly Mini-Coder-v2-noft online free url in huggingface.co:
Mini-Coder-v2-noft is an open source model from GitHub that offers a free installation service, and any user can find Mini-Coder-v2-noft on GitHub to install. At the same time, huggingface.co provides the effect of Mini-Coder-v2-noft install, users can directly use Mini-Coder-v2-noft installed effect in huggingface.co for debugging and trial. It also supports api for free installation.