174 19 208

Michael Han

shimmyshimmer

https://unsloth.ai

AI & ML interests

None yet

Recent Activity

new activity about 15 hours ago

unsloth/DeepSeek-R1-GGUF:RTX 5090 with 600GB of RAM what models？

new activity about 15 hours ago

unsloth/Qwen2.5-VL-7B-Instruct:Trouble with running the model

new activity about 15 hours ago

unsloth/Phi-4-mini-instruct:Phi-4 mini does not work inside of unsloth.

View all activity

Organizations

shimmyshimmer's activity

New activity in unsloth/DeepSeek-R1-GGUF about 15 hours ago

RTX 5090 with 600GB of RAM what models？

#40 opened 1 day ago by

frank-mx

New activity in unsloth/Qwen2.5-VL-7B-Instruct about 15 hours ago

Trouble with running the model

#2 opened 1 day ago by

ShaunShuster

New activity in unsloth/Phi-4-mini-instruct about 15 hours ago

Phi-4 mini does not work inside of unsloth.

#1 opened 1 day ago by

Pinkstack

Phi 4 mini multimodal

#2 opened about 20 hours ago by

Root56

New activity in unsloth/DeepSeek-R1-GGUF 2 days ago

Q2_K_XL model is the best? IQ2_XXS is better than Q2_K_XL in mmlu-pro benchmark

#36 opened 6 days ago by

albertchow

New activity in unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit 9 days ago

Is it possible to add this or any other Dynamic Quants model to ollama?

#2 opened 9 days ago by

Crandel

New activity in unsloth/Qwen2.5-VL-72B-Instruct-bnb-4bit 9 days ago

Update preprocessor_config.json

#3 opened 10 days ago by

TahirC

New activity in unsloth/DeepSeek-R1-GGUF 11 days ago

is it uncensored?

#33 opened 11 days ago by

Morrigan-Ship

New activity in unsloth/Qwen2.5-32B-bnb-4bit 13 days ago

Dynamic quantization

#1 opened 13 days ago by

woctordho

New activity in unsloth/README 15 days ago

I can't run any of the bnb-4bit quants with TextGenerationInference

#6 opened 18 days ago by

v3ss0n

New activity in unsloth/DeepSeek-R1-GGUF 15 days ago

8bits quantization

#20 opened 22 days ago by

ramkumarkoppu

New activity in unsloth/DeepSeek-V3-GGUF 15 days ago

Is it worth hosting a quantized DeepSeek V3? Cost & performance insights?

#15 opened 20 days ago by

Techw

New activity in unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF 15 days ago

hey how about refine-tuning the model

#7 opened 19 days ago by

OqbaN

New activity in unsloth/phi-4 15 days ago

About the phi-4 training Hyperparameters

#1 opened 20 days ago by

zj2023vegetable

New activity in unsloth/DeepSeek-R1-GGUF 15 days ago

I tested dynamic 1.58bit and 2.22bit, All thoughts are empty?

#24 opened 19 days ago by

SongXiaoMao

IQ1_S模型合并后部署于ollama上，推理生成效果差

#26 opened 18 days ago by

gaozj

when using with ollama, does it support kv_cache_type=q4_0 and flash_attention=1?

#28 opened 17 days ago by

leonzy04

New activity in unsloth/llava-1.5-7b-hf-bnb-4bit 15 days ago

Update processor_config.json

#1 opened 17 days ago by

RaushanTurganbay

New activity in unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit 15 days ago

Update processor_config.json

#1 opened 17 days ago by

baraujo22

New activity in unsloth/Llama-3.2-11B-Vision-unsloth-bnb-4bit 15 days ago

Saving to q5_k_m GGUF

#1 opened 16 days ago by

sasha1234567