BlackCubeBanditos/NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF-bucket
12.4 GB
AI & ML interests
None defined yet.
Recent Activity
View all activity
fuzzy-mittenz
updated a
bucket 1 day ago
fuzzy-mittenz
published a
bucket 1 day ago
fuzzy-mittenz
updated a
bucket 2 days ago
fuzzy-mittenz
published a
bucket 2 days ago
World Model Requirements for the Field environment.
1
#2 opened 5 days ago
by 
fuzzy-mittenz
fuzzy-mittenz
updated a
collection 2 days ago
fuzzy-mittenz
updated a
collection 3 days ago
shootstuff
updated a
collection 4 days ago
fuzzy-mittenz
updated a
collection 4 days ago
fuzzy-mittenz
updated a
collection 6 days ago
Parveshiiii
posted an update 7 days ago
Post
168
Give your LLM a window to the web 🔎
I built Seekify, a Python tool that turns web search into clean, LLM-ready input for free.
Collecting sources for an LLM workflow usually means juggling search APIs, scraping pages, and cleaning up messy text. Seekify handles that in one place:
- No search API key needed
- Structured results with titles, URLs, and snippets
- Optional page text extraction so your model gets real content, not just links
Search the web, collect sources, and feed them straight into your pipeline, so you spend less time gathering data and more time building.
It's open source, and I'd love your feedback, ideas, and contributions.
👉 https://github.com/Parveshiiii/Seekify
If it's useful, a ⭐ on GitHub helps a lot!
I built Seekify, a Python tool that turns web search into clean, LLM-ready input for free.
Collecting sources for an LLM workflow usually means juggling search APIs, scraping pages, and cleaning up messy text. Seekify handles that in one place:
- No search API key needed
- Structured results with titles, URLs, and snippets
- Optional page text extraction so your model gets real content, not just links
Search the web, collect sources, and feed them straight into your pipeline, so you spend less time gathering data and more time building.
It's open source, and I'd love your feedback, ideas, and contributions.
👉 https://github.com/Parveshiiii/Seekify
If it's useful, a ⭐ on GitHub helps a lot!
fuzzy-mittenz
updated a
collection 9 days ago
SeaWolf-AI
posted an update 11 days ago
Post
2,770
🚀 We pretrained a language model from scratch on an inference-only NPU, with real backpropagation.
🤗 Model: FINAL-Bench/VKORE-46M-NPU 📝 Technical write-up: https://huggingface.co/blog/FINAL-Bench/backpropagation-on-an-inference-only-npu-pretraini
"NPUs are inference-only, you can't train on them." We built a counterexample: VKORE-46M-NPU, trained from scratch on a first-gen (2025) inference NPU, 32 chips, no pretrained weights. A 46M decoder-only model (RoPE · SwiGLU · RMSNorm · GQA), char-level, TinyStories.
📏 Why trust it: a falling-loss curve proves nothing. So we trained the same model under identical init, data, and schedule on the NPU and on a GPU reference. · Loss trajectories correlate at 0.99 · Throughput converged to a comparable level The NPU backward pass and optimizer updates do numerically the same work as the GPU, not an approximation that merely trends down.
🧩 One accelerator now covers pretraining · LoRA · inference · quantization. We call this layer VKORE: "CUDA for NPUs."
⚖️ Public: weights, model card, NPU-vs-GPU comparison. Private (patent-pending, paper to follow): the core training technique. 46M char-level is toy scale on purpose: it proves the training path, not model quality. Larger models and real data are next.
Feedback from folks working on custom autograd backends and low-precision training kernels on non-GPU accelerators is very welcome. 🙌
🤗 Model: FINAL-Bench/VKORE-46M-NPU 📝 Technical write-up: https://huggingface.co/blog/FINAL-Bench/backpropagation-on-an-inference-only-npu-pretraini
"NPUs are inference-only, you can't train on them." We built a counterexample: VKORE-46M-NPU, trained from scratch on a first-gen (2025) inference NPU, 32 chips, no pretrained weights. A 46M decoder-only model (RoPE · SwiGLU · RMSNorm · GQA), char-level, TinyStories.
📏 Why trust it: a falling-loss curve proves nothing. So we trained the same model under identical init, data, and schedule on the NPU and on a GPU reference. · Loss trajectories correlate at 0.99 · Throughput converged to a comparable level The NPU backward pass and optimizer updates do numerically the same work as the GPU, not an approximation that merely trends down.
🧩 One accelerator now covers pretraining · LoRA · inference · quantization. We call this layer VKORE: "CUDA for NPUs."
⚖️ Public: weights, model card, NPU-vs-GPU comparison. Private (patent-pending, paper to follow): the core training technique. 46M char-level is toy scale on purpose: it proves the training path, not model quality. Larger models and real data are next.
Feedback from folks working on custom autograd backends and low-precision training kernels on non-GPU accelerators is very welcome. 🙌
- 10 replies
fuzzy-mittenz
updated a
collection 11 days ago
Project Solo
👍 1
32
#1 opened about 2 months ago
by fuzzy-mittenz
fuzzy-mittenz
updated a
collection 13 days ago
fuzzy-mittenz
updated a
Space 14 days ago
SeaWolf-AI
posted an update 14 days ago
Post
4,649
⚛️ The Open Quantum Challenge is live. Both seasons open today.
Quantum computers are expensive, queued, and reachable by only a few. So we removed the barrier. With a single GPU and a public harness, anyone can contribute to core quantum-computing problems with no quantum hardware at all. That is the point of this challenge: to move quantum research from a handful of labs to everyone.
• Season 1, Quantum simulation: reproduce a target quantum system on a GPU.
• Season 2, QEC decoder: correct errors on coded quantum states.
Answers are held privately and every submission is auto-scored against a frozen ground truth, so the ranking is reproducible and hardware-independent.
🏆 Prize: 2,000 USD total (1,000 USD per season, 🥇600 / 🥈300 / 🥉100)
Getting started takes one step: copy the participation guide from the Space and paste it into Codex or Claude Code, then submit against the harness.
📄 Read the article: https://huggingface.co/blog/FINAL-Bench/the-open-quantum-challenge-quantum-simulation-and
👉 Challenge: FINAL-Bench/open-quantum-challenge
Quantum computers are expensive, queued, and reachable by only a few. So we removed the barrier. With a single GPU and a public harness, anyone can contribute to core quantum-computing problems with no quantum hardware at all. That is the point of this challenge: to move quantum research from a handful of labs to everyone.
• Season 1, Quantum simulation: reproduce a target quantum system on a GPU.
• Season 2, QEC decoder: correct errors on coded quantum states.
Answers are held privately and every submission is auto-scored against a frozen ground truth, so the ranking is reproducible and hardware-independent.
🏆 Prize: 2,000 USD total (1,000 USD per season, 🥇600 / 🥈300 / 🥉100)
Getting started takes one step: copy the participation guide from the Space and paste it into Codex or Claude Code, then submit against the harness.
📄 Read the article: https://huggingface.co/blog/FINAL-Bench/the-open-quantum-challenge-quantum-simulation-and
👉 Challenge: FINAL-Bench/open-quantum-challenge
Project Solo
👍 1
32
#1 opened about 2 months ago
by fuzzy-mittenz
Project Solo
👍 1
32
#1 opened about 2 months ago
by fuzzy-mittenz