Paper-Replications-and-Experiments

From-scratch PyTorch replications of classic and SOTA AI/ML papers: transformers, attention, GANs, diffusion, CLIP, LoRA, MoE, plus SFT/GRPO post-training experiments.

YuvrajSingh-mist/Paper-Replications-and-Experiments

View on GitHub ↗

From-scratch PyTorch replications of classic and SOTA AI/ML papers: transformers, attention, GANs, diffusion, CLIP, LoRA, MoE, plus SFT/GRPO post-training experiments.

Paper-Replications-and-Experiments ranks 47th of 113 in Pretraining & Training, last commit 17 days ago.

Star trajectory

16 days tracked
2026-11-06431 stars today2026-11-22
Momentum

- in 30d, below the Pretraining & Training median of +0.3%.

Maintenance

Last commit 17 days ago, fresher than the median of 103d.

How it compares in Pretraining & Training

Paper-Replications-and-Experiments
431
stars
- 30d
commit 17 days ago
Pretraining & Training median
342
stars
+0.3% 30d
commit ~103d ago
Leader · maxtext
2.5k
stars
+1.0% 30d
commit today

Ranked 47th of 113 by stars.

Ranked by shared tags, then keywords, then stars
  1. Halo is an open-source framework built by White Circle for training large language and multimodal models

    +34 (+4.1%) in 30d · Committed today · Python · Other license

    Shares Pretraining & Training, Training Toolkits, Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF

  2. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Training Toolkits, Pretraining & Training, Fine-Tuning (LoRA / PEFT), Reinforcement Learning / RLHF

  3. Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed…

    +3 (+1.2%) in 30d · Committed 88d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits, Fine-Tuning (LoRA / PEFT)

  4. Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction…

    +1 (+0.5%) in 30d · Committed 30d ago · Python

    Shares Pretraining & Training, Training Toolkits, Reinforcement Learning / RLHF

  5. An algorithm-focused interface for common llm training, continual learning, and reinforcement learning…

    +3 (+2.9%) in 30d · Committed 9d ago · Python · Apache-2.0

    Shares Fine-Tuning (LoRA / PEFT), Training Toolkits, Reinforcement Learning / RLHF

  6. An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end…

    +0 (+0.0%) in 30d · Committed 90d ago · Python · Apache-2.0

    Shares Pretraining & Training, Training Toolkits, Fine-Tuning (LoRA / PEFT)

  7. A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun…

    Committed yesterday · Python · Apache-2.0

    Shares Training Toolkits, Pretraining & Training, Fine-Tuning (LoRA / PEFT)

  8. An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and…

    +0 (+0.0%) in 30d · Committed 619d ago · Python · Apache-2.0

    Shares Pretraining & Training, Training Toolkits, Fine-Tuning (LoRA / PEFT)

  9. LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)

    +0 (+0.0%) in 30d · Committed 1,137d ago · Python

    Shares Training Toolkits, Reinforcement Learning / RLHF, Fine-Tuning (LoRA / PEFT)

  10. LLM-And-More is a professional, plug-and-play, llm trainer and application builder that guides you through the…

    +6 (+1.6%) in 30d · Committed 870d ago · Go

    Shares Fine-Tuning (LoRA / PEFT), Pretraining & Training, Training Toolkits

Language
Jupyter Notebook
License
Apache License 2.0
Contributors
3
Forks
43
Watchers
9
Open issues
1
Releases
2
Created
2024-06-14
Stars this week
+1

You've seen where Paper-Replications-and-Experiments stands today.

Get the moves before everyone else: the 5 Pretraining & Training repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain Paper-Replications-and-Experiments?

Claim this page to add your own call-to-action.

Claim this page