Michael Han's picture

Michael Han

shimmyshimmer

·

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

new activity 6 days ago

unsloth/ERNIE-4.5-21B-A3B-PT-GGUF:update the gguf

new activity 9 days ago

unsloth/Qwen3-VL-30B-A3B-Thinking-GGUF:k6 k xl ud is bugged

new activity 9 days ago

unsloth/Qwen3-VL-30B-A3B-Instruct-GGUF:Q6_K_XL seems corrupted

View all activity

Organizations

upvoted a collection 20 days ago

Qwen3-VL

Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. • 56 items • Updated 18 days ago • 12

upvoted a collection about 2 months ago

DeepSeek-V3.2

2 items • Updated Sep 29 • 448

upvoted a collection 2 months ago

MMLU Pro benchmark for GGUFs (1 shot)

"Not all quantized model perform good", serving framework ollama uses NVIDIA gpu, llama.cpp uses CPU with AVX & AMX • 13 items • Updated Aug 15 • 10

upvoted a collection 4 months ago

gpt-oss

OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. • 18 items • Updated 19 days ago • 34

upvoted a collection 7 months ago

Qwen3

84 items • Updated Aug 6 • 1.43k

upvoted 2 collections 8 months ago

Llama 4

Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth! • 15 items • Updated 20 days ago • 52

Gemma 3

All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 55 items • Updated 20 days ago • 93

upvoted 2 articles 10 months ago

Article

How to deploy and fine-tune DeepSeek models on AWS

Jan 30

•

55

Article

Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL

Jan 10, 2024

•

74

upvoted a collection 10 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 20 days ago • 260

upvoted 3 collections 11 months ago

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 20 days ago • 75

Deepseek V3 (All Versions)

Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. • 7 items • Updated 20 days ago • 38

Eule

A series of English/Russian reasoning models. • 2 items • Updated Dec 12, 2024 • 2

upvoted 2 collections 12 months ago

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 20 days ago • 37

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 20 days ago • 90

upvoted an article 12 months ago

Article

Unleashing the Power of Unsloth and QLora:Redefining Language Model Fine-Tuning

Jan 19, 2024

•

18

upvoted a collection 12 months ago

Vision/multimodal Models

Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more! • 25 items • Updated 20 days ago • 17

upvoted 2 collections about 1 year ago

Llama 3.2 Vision

Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions. • 8 items • Updated 20 days ago • 7

Qwen 2.5 Coder

Complete collection of Code-specific model series for Qwen2.5 in bnb 4bit, 16bit and GGUF formats. • 35 items • Updated 20 days ago • 35

upvoted an article about 1 year ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

•

63