BananaMind-2.1-NanoCoder I'm just realizing this now but, did you do SFT on these models, I only see base training data in the readme. If you do, could you tell me which model to try of yours that does?
🔄 Aniimage model coming soon
Jackson Yeskie
8BitStudio
AI & ML interests
Text to image, Language models
Recent Activity
repliedto Banaxi-Tech's post about 1 hour ago
Should I even continue making models?Organizations
None yet
replied to Banaxi-Tech's post about 1 hour ago
replied to wayneworkman2012's post about 13 hours ago
Wonder if they would raise the prices if this is actually added
reacted to wayneworkman2012's post with 🚀 about 21 hours ago
Post
1,792
To all the inference providers behind the HuggingFace router - if you want me to use your services you will have to serve native-precision models. I'm not paying for FP8 when I can run in bf16 locally.
- 4 replies
replied to Banaxi-Tech's post about 21 hours ago
Yeah, and I think spending more time on one model would be better than releasing a bunch of almost unusable ones at once like they've been doing. I just tried their coding model and it cant do anything at all, not even making a script to reverse a string in python or any sort of SUPER basic debugging
replied to mithulaartigala's post 3 days ago
Hey, we still got at least a year or two..
reacted to mithulaartigala's post with 🤗 4 days ago
Post
4,544
I am LOVING HuggingFace Pro <3
- 7 replies
liked 2
models 5 days ago
updated a
dataset 7 days ago
liked a
Space 7 days ago
upvoted a changelog 9 days ago
Hugging Face Changelog
P(doom) on user profiles
• 353
WAKE UP
11
#5 opened 10 days ago
by 
GGUFGuy
Thats cool! If you can say, how big is the model, im curious
Hugging Science is DEAD???
➕ 2
38
#2 opened 19 days ago
by 
XBFDI
Message board idea
👍 5
7
#3 opened 14 days ago
by 
el4
updated a
model 13 days ago
Line count
10
#2 opened about 2 months ago
by 
Sterling-Ai
reacted to harshitkgupta's post with 🚀 17 days ago
Post
8,745
Fine-tuned Qwen 2.5 (0.5B → 3B) on real coding-agent traces, 10 controlled runs, one 16GB Mac. Compared PyTorch MPS vs. Apple MLX for local LoRA SFT — and the honest answer is "it depends on what you're optimizing for":
• PyTorch MPS: 2.2x–5.7x faster raw throughput, but hits a hard memory wall — can't load a 3B model in FP16 on 16GB.
• Apple MLX: 4-bit QLoRA fits 3B+ models with almost flat memory scaling as context grows (+109 MB going from 1k→4k tokens).
• 4-bit quantization doesn't cost you convergence — eval loss tracks closely across backends.
• The bigger surprise: most of MLX's slowdown isn't the 4-bit dequant tax. Two of the 10 runs went unquantized to isolate it — dequant only explains 1.07x–1.4x of the gap. A ~4.1–4.6x framework-level gap remains either way.
All 10 LoRA adapters + Trackio logs are public so the numbers are checkable, not just claimed.
Full writeup: https://huggingface.co/blog/harshitkgupta/fine-tuning-coding-agents-on-mac-pytorch-mps-mlx
• PyTorch MPS: 2.2x–5.7x faster raw throughput, but hits a hard memory wall — can't load a 3B model in FP16 on 16GB.
• Apple MLX: 4-bit QLoRA fits 3B+ models with almost flat memory scaling as context grows (+109 MB going from 1k→4k tokens).
• 4-bit quantization doesn't cost you convergence — eval loss tracks closely across backends.
• The bigger surprise: most of MLX's slowdown isn't the 4-bit dequant tax. Two of the 10 runs went unquantized to isolate it — dequant only explains 1.07x–1.4x of the gap. A ~4.1–4.6x framework-level gap remains either way.
All 10 LoRA adapters + Trackio logs are public so the numbers are checkable, not just claimed.
Full writeup: https://huggingface.co/blog/harshitkgupta/fine-tuning-coding-agents-on-mac-pytorch-mps-mlx
- 7 replies
replied to Banaxi-Tech's post 19 days ago
does BananaMind have a website? Would love to easily test these on it if so
liked a
model 19 days ago
