Repositories
31
Net stars gained, last 7 days
+5,285
Top-level Tag
Net stars gained each day, last 90 days
Peak days
- 1
Aug 31, 2026 +1,785 net stars (median day +624)
- jingyaogong/minimind+837 (47%)
- p-e-w/heretic+475 (27%)
- unslothai/unsloth+96 (5%)
- 2
Sep 1, 2026 +1,509 net stars (median day +624)
- jingyaogong/minimind+912 (60%)
- p-e-w/heretic+273 (18%)
- unslothai/unsloth+70 (5%)
- 3
Sep 21, 2026 +2,106 net stars (median day +624)
- jaredpalmer/kev+1,480 (70%)
Published kev-family on Sep 20, 2026 · Created on Sep 17, 2026
- jingyaogong/minimind+202 (10%)
- p-e-w/heretic+150 (7%)
- 4
Sep 22, 2026 +2,603 net stars (median day +624)
- jaredpalmer/kev+2,029 (78%)
Created on Sep 17, 2026
- jingyaogong/minimind+158 (6%)
- p-e-w/heretic+89 (3%)
- 5
Sep 23, 2026 +1,989 net stars (median day +624)
- jaredpalmer/kev+1,487 (75%)
Created on Sep 17, 2026
- jingyaogong/minimind+151 (8%)
- unslothai/unsloth+71 (4%)
A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.
Largest
Most stars in total now.
readme:
Train LLMs, diffusion, decision, TTS, and embedding models 2× faster with 70% less VRAM with no accuracy loss
readme:
Easily fine-tune 100+ large language models with zero-code CLI and Web UI
readme:
覆盖 Pretrain、SFT、LoRA、RLHF-DPO、RLAIF（PPO / GRPO / CISPO）、Tool Use、Agentic RL、自适应思考与模型蒸馏等完整训练流程。
description:
The simplest, fastest repository for training/finetuning medium-sized GPTs.
readme:
nanochat is the simplest experimental harness for training LLMs.
readme:
FastChat is an open platform for training, serving, and evaluating large language model based chatbots.
description:
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
readme:
The code for fine-tuning the model.
readme:
* Supervised Fine-Tuning `sft` * Group Relative Policy Optimization `grpo`
readme:
We also provide a doc on how to finetune LLaVA-1.5 on your own dataset with LoRA.
Newest Admissions
Entered the index by the rising rule, newest first.
readme:
The models use full-parameter supervised fine-tuning with a **32,768-token training sequence length**.
readme:
a post-training reinforcement learning framework for Large Language Models (LLMs)
readme:
A finetuning framework for MOSS-Image
readme:
the **HybridSFT** and **HybridRL** post-training stages, batch inference, and the **Interpretable Latent Mode** inspector.
readme:
Reflective Supervised Fine-Tuning (ReSFT)
- jaredpalmer/kev9.8K
readme:
Fine-tune on your own labelled examples. A coding-agent skill runs the whole loop on Modal, from finding your questions to serving the result.
- xzf-thu/VoiceMem2.9K
readme:
VoiceMem 提供完整的微调代码,可用于训练自己的 VoiceMem Model Family Adapter。
How a repository gets this Tag
An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.