Daniel Han-Chen's picture

Daniel Han-Chen PRO

danielhanchen

·

https://unsloth.ai/

AI & ML interests

None yet

Recent Activity

updated a model about 5 hours ago

unsloth/DeepSeek-R1-0528-GGUF

updated a model about 17 hours ago

unsloth/DeepSeek-R1-0528-BF16

updated a model about 18 hours ago

unsloth/DeepSeek-R1-0528

View all activity

Organizations

danielhanchen's activity

upvoted a paper 15 days ago

Speechless: Speech Instruction Training Without Speech for Low Resource Languages

Paper • 2505.17417 • Published 18 days ago • 11

upvoted 2 collections about 1 month ago

TorchAO Quantized Phi-4-mini-instruct

TorchAO quantized Phi-4-mini-instruct models from PyTorch team, runnable in A100, H100 through vLLM and in mobile devices through ExecuTorch • 3 items • Updated 27 days ago • 3

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & outperforms all leading quantization methods. • 32 items • Updated 11 days ago • 116

upvoted an article 2 months ago

Article

Comparing sub 50GB Llama 4 Scout quants (KLD/Top P)

By

•

Apr 9

• 40

upvoted a collection 3 months ago

Qwen2.5-VL (All Versions)

All versions of Qwen2.5-VL including the new 32B version and 4-bit, 16-bit and more! • 16 items • Updated 5 days ago • 16

upvoted 2 collections 5 months ago

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 11 days ago • 238

Phi-4 (All Versions)

Microsoft's Phi-4 models including Reasoning + Reasoning Plus & mini. Includes Dynamic 2.0 GGUF, 4-bit & 16-bit versions. Includes Unsloth's bug fixes • 20 items • Updated 11 days ago • 70

upvoted 2 collections 6 months 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 • 28 items • Updated 11 days ago • 81

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 11 days ago • 37

upvoted a collection 7 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 11 days ago • 31

upvoted an article 8 months ago

Article

Fixing Gradient Accumulation

By

and 5 others •

Oct 16, 2024

• 53

upvoted 2 collections 8 months ago

4bit Instruct Models

18 items • Updated 11 days ago • 30

Load 4bit models 4x faster

Native bitsandbytes 4bit pre quantized models • 25 items • Updated 11 days ago • 57

upvoted a collection 9 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. • 27 items • Updated 11 days ago • 63

upvoted an article 11 months ago

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29, 2024

• 330

upvoted a collection about 1 year 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 • 20

upvoted a collection over 1 year ago

OpenCodeInterpreter

18 items • Updated Mar 3, 2024 • 84

upvoted a paper over 1 year ago

LLaMA Pro: Progressive LLaMA with Block Expansion

Paper • 2401.02415 • Published Jan 4, 2024 • 54

upvoted a collection over 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 • 68