Daniel Han-Chen's picture

Daniel Han-Chen

danielhanchen

·

https://unsloth.ai/

danielhanchen

AI & ML interests

None yet

Recent Activity

new activity about 20 hours ago

microsoft/phi-4:Suggested tokenizer changes by Unsloth.ai

posted an update 1 day ago

We fixed many bugs in Phi-4 & uploaded fixed GGUF + 4-bit versions! ✨ Our fixed versions are even higher on the Open LLM Leaderboard than Microsoft's! GGUFs: https://huggingface.co/unsloth/phi-4-GGUF Dynamic 4-bit: https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit You can also now finetune Phi-4 for free on Colab: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb Read our blogpost for more details on bug fixes etc: https://unsloth.ai/blog/phi4

new activity 2 days ago

unsloth/DeepSeek-V3-GGUF:Getting error with Q3-K-M

View all activity

Articles

Faster fine-tuning using TRL & Unsloth

Organizations

danielhanchen's activity

upvoted a collection 3 days ago

Phi-4 (All Versions)

Microsoft's new Phi-4 model in all formats. Includes GGUF, 4-bit bnb and original versions. Includes Unsloth's bug fixes. • 4 items • Updated 3 days ago • 22

upvoted 2 collections about 1 month ago

Unsloth 4-bit Dynamic Quants

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 8 items • Updated 3 days ago • 22

Llama 3.3 (All Versions)

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. • 3 items • Updated 3 days ago • 29

upvoted a collection 2 months ago

Qwen 2.5 Coder

Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats. • 35 items • Updated 3 days ago • 21

upvoted an article 3 months ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 47

upvoted 2 collections 3 months ago

4bit Instruct Models

18 items • Updated 3 days ago • 26

Load 4bit models 4x faster

Native bitsandbytes 4bit pre quantized models • 25 items • Updated 3 days ago • 51

upvoted a collection 4 months ago

Llama 3.2

Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. • 23 items • Updated 3 days ago • 46

upvoted an article 6 months ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29, 2024

• 262

upvoted a collection 10 months ago

Navarasa 2.0 Models

Collection of models Navarasa 2.0 Models finetuned with Gemma on 15 Indian languages • 5 items • Updated Mar 18, 2024 • 18

upvoted a collection 11 months ago

OpenCodeInterpreter

18 items • Updated Mar 3, 2024 • 83

upvoted a paper about 1 year ago

LLaMA Pro: Progressive LLaMA with Block Expansion

Paper • 2401.02415 • Published Jan 4, 2024 • 53

upvoted a collection about 1 year ago

Awesome feedback datasets

A curated list of datasets with human or AI feedback. Useful for training reward models or applying techniques like DPO. • 19 items • Updated Apr 12, 2024 • 67