Zyphra/ZAYA1-8B
9B ā¢ Updated ā¢ 66.1k ā¢ 399
Ujjwal Tyagi
Ujjwal-Tyagi
AI & ML interests
Chief Scientist at Shirova AI, focused on advancing open-source AI, Experienced in LLM fine-tuning, model architecture, and research, with a strong interest in building scalable and efficient models
Recent Activity
liked a model 1 day ago
Zyphra/ZAYA1-8B liked a dataset 1 day ago
1aurent/BACH liked a model 1 day ago
houyuanchen/UniVidXOrganizations
liked a
model 1 day ago
liked a
dataset 1 day ago
liked a
model 1 day ago
replied to DedeProGames's post 1 day ago
Oh wow, good
upvoted a paper 2 days ago
upvoted 2
collections 5 days ago
liked a
model 7 days ago
liked a
dataset 8 days ago
posted an update 8 days ago
Post
200
6 Open-Source Libraries to FineTune LLMs
1. Unsloth
GitHub: https://github.com/unslothai/unsloth
ā Fastest way to fine-tune LLMs locally
ā Optimized for low VRAM (even laptops)
ā Plug-and-play with Hugging Face models
2. Axolotl
GitHub: https://github.com/OpenAccess-AI-Collective/axolotl
ā Flexible LLM fine-tuning configs
ā Supports LoRA, QLoRA, multi-GPU
ā Great for custom training pipelines
3. TRL (Transformer Reinforcement Learning)
GitHub: https://github.com/huggingface/trl
ā RLHF, DPO, PPO for LLM alignment
ā Built on Hugging Face ecosystem
ā Essential for post-training optimization
4. DeepSpeed
GitHub: https://github.com/microsoft/DeepSpeed
ā Train massive models efficiently
ā Memory + speed optimization
ā Industry standard for scaling
5. LLaMA-Factory
GitHub: https://github.com/hiyouga/LLaMA-Factory
ā All-in-one fine-tuning UI + CLI
ā Supports multiple models (LLaMA, Qwen, etc.)
ā Beginner-friendly + powerful
6. PEFT
GitHub: https://github.com/huggingface/peft
ā Fine-tune with minimal compute
ā LoRA, adapters, prefix tuning
ā Best for cost-efficient training
1. Unsloth
GitHub: https://github.com/unslothai/unsloth
ā Fastest way to fine-tune LLMs locally
ā Optimized for low VRAM (even laptops)
ā Plug-and-play with Hugging Face models
2. Axolotl
GitHub: https://github.com/OpenAccess-AI-Collective/axolotl
ā Flexible LLM fine-tuning configs
ā Supports LoRA, QLoRA, multi-GPU
ā Great for custom training pipelines
3. TRL (Transformer Reinforcement Learning)
GitHub: https://github.com/huggingface/trl
ā RLHF, DPO, PPO for LLM alignment
ā Built on Hugging Face ecosystem
ā Essential for post-training optimization
4. DeepSpeed
GitHub: https://github.com/microsoft/DeepSpeed
ā Train massive models efficiently
ā Memory + speed optimization
ā Industry standard for scaling
5. LLaMA-Factory
GitHub: https://github.com/hiyouga/LLaMA-Factory
ā All-in-one fine-tuning UI + CLI
ā Supports multiple models (LLaMA, Qwen, etc.)
ā Beginner-friendly + powerful
6. PEFT
GitHub: https://github.com/huggingface/peft
ā Fine-tune with minimal compute
ā LoRA, adapters, prefix tuning
ā Best for cost-efficient training
- 1 reply
liked a
model 9 days ago
liked a
dataset 11 days ago
liked a
model 11 days ago
liked a
model 12 days ago
upvoted a paper 12 days ago
liked 2
models 12 days ago
liked a
dataset 13 days ago
upvoted a paper 13 days ago
commented a
paper 13 days ago