fine-tuned model on Linux Command Library (https://linuxcommandlibrary.com/basic/oneliners)
357 Pulls 1 Tag Updated 1 year ago
A fine-tuned Dolphin3 model (unrestricted version of Llama) from https://ollama.com/library/dolphin3 (dolphin3:latest) that has been trained on the OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B dataset from huggingface.
384 Pulls 1 Tag Updated 3 months ago
This model is not the official phi4 model. For the official model please refer to https://ollama.com/library/phi4
809 Pulls 1 Tag Updated 6 months ago
Islamic bot, if you want for authenticity, its best to feed it your own data, library and command it to explain it through that
79 Pulls 1 Tag Updated 1 year ago
3 Pulls 1 Tag Updated 10 months ago
This model was trained 2x faster with Unsloth and Huggingface's TRL library. This is an experiment on fixing models with incorrect behaviors.
40 Pulls 1 Tag Updated 1 year ago
OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.
27 Pulls 1 Tag Updated 2 years ago
2 Pulls 1 Tag Updated 1 year ago
26 Tags Updated yesterday
1 Tag Updated 1 year ago
AI Brand Manager for any industry & Business.
77 Pulls 1 Tag Updated 1 year ago
Light-R1-14B-DS is the State-Of-The-Art 14B math model with AIME24 & 25 scores 74.0 & 60.2, outperforming many 32B models.
324 Pulls 1 Tag Updated 1 year ago
Emre tarafından geliştirilen bu model, Türkçe çok aşamalı akıl yürütme verisiyle 4-bit formatta eğitilmiş olup, TARA v1 değerlendirmesinde %84.73 başarı oranı ile öne çıkan en güçlü Türkçe Gemma3 modellerinden biridir.
61 Pulls 1 Tag Updated 10 months ago
Latest and final roleplay/reasoning model by Nitral-AI (Huggingface).
277 Pulls 5 Tags Updated 4 months ago