supervised-fine-tuning
DiRL
A post-training framework for diffusion language models with supervised fine-tuning and reinforcement learning
- 167
- Python
- Apache-2.0
- 8 mo ago
NanoJev
- 92
- 826
- 2 mo ago
AUGUstus
🚗 AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding. 🏋️ 512 H800 GPUs · ~2 days · 318K+ video hours · 513B+ training tokens. ⚡ 12 Hz on-vehicle deployment. SFT + GRPO + NAVSIM.
- 42
- Python
- Apache-2.0
- 5 wk ago
Vela
Vela: User Behavior as Supervision Sparks LLM Intelligence — official paper, task templates, and prompts from AllSpark at Xiaohongshu.
- 33
- 5 wk ago
RoSTE
[ICML 2025] Official code for the paper "RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models"
- 10
- Python
- 18 mo ago
llm-tool-call-sft
LoRA fine-tuning pipeline for tool-calling chat LLMs with config-driven datasets, deterministic prompts, and built-in tool-call evaluation.
- 11
- Python
- CC0-1.0
- 13 mo ago
RoSTE
[ICML 2025] Official code for the paper "RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models"
- 8
- Python
- 18 mo ago
cmu-agents
卡内基梅隆大学 11-768《AI Agents》课程中文详细讲义:覆盖工具使用、长上下文、记忆、规划、编码与计算机使用 Agent,以及 SFT/RL 训练与 Agent 安全
- 6
- JavaScript
- 4 wk ago
SRP-SFT
Selective margin preservation for supervised fine-tuning. Keeps selected non-target logit margins while improving math reasoning and code generation.
- 5
- Python
- 5 wk ago
ExpertCondenser
Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning (COLM 2026): ExpertCondenser: SFT for sparse MoE LLMs with gated condenser experts. Official code.
- 5
- Python
- Apache-2.0
- 2 mo ago
Financial-Intent-Understanding-with-LLMs
🎯 Fine-tuning LLMs using LlamaFactory for financial intent understanding | Evaluating open-source models on OpenFinData benchmark | Full implementation with multiple models (Qwen2.5/ChatGLM3/Baichuan2/Llama3)
- 5
- Jupyter Notebook
- 22 mo ago
Arete-27B-Unlocked-Uncensored-Heretic-i1-GGUF
- 3
- 5k
- apache-2.0
- 11 d ago
qwen-05b-min-sft
Least-data SFT on Qwen2.5-0.5B-Instruct: teach a ticket-card format with 8 examples. Colab T4 notebook + LoRA. Open weights.
- 3
- Python
- MIT
- 3 mo ago
LLaMA-Sum-Fine-Tuning
Fine-tuned Meta's LLaMA 3.2 1B for text summarization using QLoRA (4-bit quantization + LoRA), achieving 40%+ improvement in ROUGE-2 over the base model on CNN/DailyMail dataset.
- 3
- Python
- Apache-2.0
- 9 mo ago
nanoDiff
Minimal masked diffusion LM in PyTorch. Pretraining + SFT + a scaling family from 50M to 350M, LLaDA recipe.
- 1
- Python
- MIT
- 6 mo ago
TerminalHorizon-122B-A10B-i1-GGUF
- 1
- 2.8k
- apache-2.0
- 5 wk ago
LLM-Full-Finetuning-with-Code
A practical Large Language Model (LLM) full fine-tuning repository featuring end-to-end implementations of dataset preparation, tokenization, supervised fine-tuning (SFT), transformer model training, loss optimization, evaluation, and model checkpoint management using Python, PyTorch, and Hugging Face Transformers.
- 1
- Jupyter Notebook
- Apache-2.0
- 6 d ago
opencode-reasoning-reproduction
A reproducible LiveCodeBench evaluation scaffold for controlled studies of code-reasoning SFT on Qwen2.5-1.5B.
- 1
- Python
- 4 mo ago
cmu-11-768-ai-agents-fall2026
Unofficial homework and notes for CMU 11-768: AI Agents (Fall 2026).
- 0
- Python
- MIT
- 2 wk ago
yxwang1215
Yuxuan Wang (王宇轩): efficient multimodal LLMs, supervised fine-tuning, and KV-cache compression. Incoming Ph.D. at Peking University.
- 0
- 6 d ago










