Michael Han's picture

Michael Han

shimmyshimmer

·

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

new activity about 21 hours ago

unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit:run with "vllm serve" comes to an error: KeyError: 'layers.0.mlp.down_proj.weight.absmax'

updated a model 1 day ago

unsloth/Llama-4-Scout-17B-16E-unsloth-bnb-8bit

updated a model 1 day ago

unsloth/Llama-4-Scout-17B-16E-Instruct

View all activity

Organizations

shimmyshimmer's activity

upvoted a collection 17 days 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 about 8 hours ago • 43

upvoted a collection about 1 month ago

Gemma 3

All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated about 8 hours ago • 53

upvoted 2 articles 3 months ago

Article

How to deploy and fine-tune DeepSeek models on AWS

Jan 30

• 52

Article

Faster fine-tuning using TRL & Unsloth

Jan 10, 2024

• 57

upvoted a collection 3 months ago

DeepSeek R1 (All Versions)

DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated about 8 hours ago • 219

upvoted 3 collections 4 months ago

Phi-4 (All Versions)

Microsoft's new Phi-4 models including mini in all formats. Includes GGUF, 4-bit bnb and original versions. Includes Unsloth's bug fixes. • 8 items • Updated about 8 hours ago • 51

Deepseek V3 (All Versions)

Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions. • 6 items • Updated about 8 hours ago • 35

Eule

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

upvoted 5 collections 5 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 about 8 hours 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 about 8 hours ago • 76

Vision/multimodal Models

Collection of the most popular vision models including Llama 3.2, LlaVa, Qwen2 VL, Pixtral, PaliGemma and more! • 25 items • Updated about 8 hours ago • 9

Llama 3.2 Vision

Meta's Llama 3.2 vision models 11B and 90B. Include 4-bit bnb and original versions. • 8 items • Updated about 8 hours 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 about 8 hours ago • 27

upvoted an article 6 months ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 53

upvoted 2 collections 7 months ago

Qwen 2.5

32 items • Updated about 8 hours ago • 12

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 about 8 hours ago • 62

upvoted an article about 1 year ago

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18, 2024

• 287