CompactAI-O/Shard-1
Updated • 10
Lane Fiedler
CompactAI
AI & ML interests
Hey there! If your reading this, my profile has moved to https://huggingface.co/CompactAI-O
Recent Activity
new activity about 7 hours ago
google/gemma-4-31B-it-assistant:Fine tuning updated a model about 7 hours ago
CompactAI-O/Shard-1 updated a Space about 7 hours ago
CompactAI-O/HomepageOrganizations
Fine tuning
➕ 3
1
#4 opened 6 days ago
by 
gertrud
updated a
model about 7 hours ago
updated a
Space about 7 hours ago
updated a
collection about 19 hours ago
Would be a shame
1
#2 opened 3 days ago
by 
Enderchef
Uncensored Claude Opus version of Gemma 4 26B?
1
#6 opened 3 days ago
by 
aeronfx
Hey from Hugging Face 🤗
❤️ 1
5
#1 opened over 1 year ago
by 
reach-vb
liked a
model 5 days ago
updated a
Space 6 days ago
liked a
model 6 days ago
liked a
Space 6 days ago
Share onnx conversion script
3
#14 opened 8 days ago
by 
jalbrethsen-highflame
reacted to BlueNipples's post with 👀 6 days ago
Post
2914
Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.
- 1 reply
Def going to use this somewhere🔥
commented on Learning Maths for the Last Time 6 days ago
ikr :)
upvoted an article 7 days ago
Article
Learning Maths for the Last Time
Crownelius
• • 8 replied to BlueNipples's post 7 days ago
Seems like they could find a way to add backwards compatibility
replied to Crownelius's post 7 days ago
40k?
Easy, spend 15k in Anthropic highest subscription & the rest in API
The rest? Spend it on a H100 (27k), then dump the rest into hardware
reacted to Crownelius's post with 😎 7 days ago
Post
3989
Day 4-6 [05/05/2026]
Howdy,
Is anybody else willing to put a second mortgage on their house, just to spend 40k USD in compute credits? Just me? k...
I got dreams, man. The datasets I could build with 40k would be insane.
Somebody called me a genius the other day, they'd be shocked to find out, that I would put my house on the line for 30 days of runpod usage.
What would you do with it?
I would turn arxiv into a dataset. Turn each arxiv paper into a QnA.
Or... maybe if I got 40k USD in credit's Id end up like those 16 lost scientists.
Food for thought.
Anyways, I think I'm going to make a post once a week.
In the meantime you can find me building small llm's in discord here:
https://discord.gg/4DdwS9D8x9
Howdy,
Is anybody else willing to put a second mortgage on their house, just to spend 40k USD in compute credits? Just me? k...
I got dreams, man. The datasets I could build with 40k would be insane.
Somebody called me a genius the other day, they'd be shocked to find out, that I would put my house on the line for 30 days of runpod usage.
What would you do with it?
I would turn arxiv into a dataset. Turn each arxiv paper into a QnA.
Or... maybe if I got 40k USD in credit's Id end up like those 16 lost scientists.
Food for thought.
Anyways, I think I'm going to make a post once a week.
In the meantime you can find me building small llm's in discord here:
https://discord.gg/4DdwS9D8x9
- 6 replies
How do i run this?
2
#1 opened 7 days ago
by 
NukeNotNull