NILKNARFGonzo/modded-llama.cpp-convert_hf_to_gguf_update.py
Updated
💩 cat box
Nilky
NILKNARFGonzo
AI & ML interests
i want small fun!
im making a model that fits on 4 floppy disks... which is gonna take multiple months!!!
all of my stuff is made in the eastern us
Recent Activity
new activity about 22 hours ago
mradermacher/model_requests:Request quantization for HuTaoDeDog/furina-qwen3.6-27b-merged-2.0 (ModelScope) new activity about 23 hours ago
mradermacher/model_requests:Quants for https://huggingface.co/artindnr/strawberry-1Organizations
Request quantization for HuTaoDeDog/furina-qwen3.6-27b-merged-2.0 (ModelScope)
11
#2738 opened 15 days ago
by 
XingChina
Request to make quants of my teensy models - https://huggingface.co/NILKNARFGonzo/single-floppy-346k-merged and https://huggingface.co/NILKNARFGonzo/floppyx3-MEGAmodel-merged
22
#2756 opened 10 days ago
by NILKNARFGonzo
Quants for https://huggingface.co/artindnr/strawberry-1
7
#2766 opened 6 days ago
by 
artindnr
updated a
model about 23 hours ago
published a
model about 23 hours ago
Muse Glimmer Styletune
2
#2793 opened 1 day ago
by 
repla73
updated a
model 1 day ago
upvoted a collection 1 day ago
lol all of the open source models are in china
good for them lmao (i use deepseek tbh)
reacted to Jiaqi-hkust's post with 🚀 2 days ago
Post
2381
🧠 Remember-R1: Our fix for MLLMs forgetting the image during long reasoning
We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.
So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.
We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.
Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.
No extra cost at inference, just cleaner supervision where it counts.
📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1
Happy to answer any questions and receive feedback!
#MultimodalAI #RL #MLLM #CoT #VisualReasoning
We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.
So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.
We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.
Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.
No extra cost at inference, just cleaner supervision where it counts.
📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1
Happy to answer any questions and receive feedback!
#MultimodalAI #RL #MLLM #CoT #VisualReasoning
updated a
model 2 days ago
replied to Banaxi-Tech's post 2 days ago
if you follow random people they might follow u back
replied to Banaxi-Tech's post 2 days ago
im gonna put ads for people 2 follow u
reacted to Nymbo's post with 🔥 2 days ago
Post
1824
Anthropic gave me six months of Claude Max 20x through the Claude for Open Source program, granted based on my Hugging Face work. Thank you 
Anthropic for supporting open source.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap — issues and PRs welcome.
So far I've been pointing it at Markdown Minimap, an Obsidian plugin that adds a scrollable IDE-style minimap to your notes. This week I've been clearing a backlog of user-reported issues on it, with Claude often handling them end to end.
https://github.com/Nymbo/Markdown-Minimap — issues and PRs welcome.
updated a
model 2 days ago
reacted to Banaxi-Tech's post with ➕❤️😎👍🤗 2 days ago
Post
1945
We're exited to announce BananaMind OS, our OS specically for running BananaMind models!
Its able to run BananaMind 2 Nano at 4 bit on only 7-8MB of ram, the 2 bit on 6MB of ram and the 8 bit version on 14MB of RAM!
It runs on a 486 or newer!
Check out this video and image running BananaMind 2 Nano 4 Bit on 9
MB of RAM and a emulated 486 in QEMU at ~1TPS!
We asked it: "What is the first letter of the alphabet?"
The response is:
"The first letter of the alphabet is:
- A.
"
And if you're asking because of the video, yes I am a arch btw.
Comment and like this post for a GitHub link and comment for adding other models!
Its able to run BananaMind 2 Nano at 4 bit on only 7-8MB of ram, the 2 bit on 6MB of ram and the 8 bit version on 14MB of RAM!
It runs on a 486 or newer!
Check out this video and image running BananaMind 2 Nano 4 Bit on 9
MB of RAM and a emulated 486 in QEMU at ~1TPS!
We asked it: "What is the first letter of the alphabet?"
The response is:
"The first letter of the alphabet is:
- A.
"
And if you're asking because of the video, yes I am a arch btw.
Comment and like this post for a GitHub link and comment for adding other models!
- 25 replies