Michael Han
shimmyshimmer
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 hour ago
Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
updated
a model
about 8 hours ago
unsloth/DeepSeek-V3-0324-BF16
updated
a collection
about 8 hours ago
Deepseek V3 (All Versions)
Organizations
shimmyshimmer's activity
Model issue with 64GB ram
5
#4 opened 10 days ago
by
llama-anon

Does not work at all
8
#1 opened 22 days ago
by
zokica
What tool/framework to test gguf models?
1
#14 opened 5 days ago
by
bobchenyx
Which quantized version can run on a Mac computer with 32GB of memory?
4
#2 opened 5 days ago
by
jimpunk
Please make a heavily quantized version like you did with R1
1
#1 opened 7 days ago
by
Blazgo

Does not support multimodal input
4
#5 opened 12 days ago
by
RamboRogers

GGuf Version
1
#5 opened 8 days ago
by
apcameron
Vision Model?
1
#4 opened 8 days ago
by
philbanjo

What's the difference between a model with a name 'unsloth' and a model without it?
1
#3 opened 7 days ago
by
1sn0treal

PLEASE make one like this for Maverick (LLaMA 4)
4
#50 opened 7 days ago
by
Blazgo

text only?
1
#1 opened 7 days ago
by
csabakecskemeti

What are the system requirements to train this
3
#1 opened 9 days ago
by
Blazgo

Update README.md
1
#1 opened 8 days ago
by
JackCloudman

how i use this version model in vllm serve
4
#1 opened 28 days ago
by
couldn
Missing params.json
2
#2 opened 19 days ago
by
bingw5
Something is wrong with the 4bit uploads, 57.9B params???
2
#2 opened 10 days ago
by
fsaudm
OOM on 2xH100
7
#3 opened 9 days ago
by
Maverick17

What is the mininmum VRAM required to deploy this model?
6
#6 opened 9 days ago
by
GradAscend
