AI & ML interests

None defined yet.

AtAndDevΒ 
posted an update about 9 hours ago
view post
Post
352
SPECK 2 IS ALREADY OUT: specklabs/Speck2-140M

Pretrained on 4x more tokens than the previous releases (20b vs 5b).
Instruct tuned versions are coming soon.
Very interesting models are coming soon too (hint: moe).

Thanks for everyone supporting!
  • 1 reply
Β·
AtAndDevΒ 
posted an update 3 days ago
view post
Post
127
SPECK1.5 IS COMING SOON!
Same 5B token budget but much better corpus quality.

Also getting a ton of downloads, thanks for everyone downloading and liking <3

specklabs
AtAndDevΒ 
posted an update 6 days ago
view post
Post
135
NEW SPECK UPDATES:

Just hit #14 and #15 with out FIRST models on Open SLM Leaderboard. The models were trained on 5B tokens, while competing with similarly sized models trained on more than 6-20x the data.

A new base model Speck1.5-140M being trained right now on a higher quality corpus and will be released soon.
SpeckChat3 is coming very soon with 1 million samples, specifically designed to post train small base models.

Also, just to clarify stuff, we will NOT release anything that is NOT MIT licensed EVER. Openness is needed in small language research.

Thanks to everyone supporting the project, and stay tuned for new releases!
AtAndDevΒ 
posted an update 7 days ago
view post
Post
1874
SPECK UPDATES:
1 New instruct model tuned on top of Speck1-140M: specklabs/Speck1-140M-Instruct
2 Instruction tuning datasets
2 GGUFs

Much more coming soon:
Speck1.1-140M-Instruct that is post trained on SpeckChat2 will be coming very soon
New base model Speck1.5-140M is coming with a much higher quality corpus

Thanks to everyone who is already supporting the project, and stay tuned for new releases!
  • 3 replies
Β·
AtAndDevΒ 
posted an update 8 days ago
view post
Post
2112
FIRST SPECK MODEL RELEASED:
specklabs/Speck1-140M

new models coming very soon (both instruct and much better models), with much much higher training scale as i am getting marenostrum5 access soon!
we will be looking at 100b-2t token budgets :)
  • 4 replies
Β·
mahwizzzzΒ 
posted an update 19 days ago
NymboΒ 
posted an update 22 days ago
view post
Post
2079
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 β€” issues and PRs welcome.
NymboΒ 
posted an update about 1 month ago
view post
Post
5825
Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3.

CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0.

See it for yourselves:
owensong/Inflect-Micro-v2
owensong/Inflect-Nano-v2

Try the Demos:
Nymbo/Inflect-TTS (unlimited CPU usage)
owensong/Inflect-v2 (ultra-fast ZeroGPU usage)
  • 6 replies
Β·
eienmojikiΒ 
posted an update 2 months ago
KingNishΒ 
posted an update 3 months ago
view post
Post
4794
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos

Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.

Trained on: H100s from Modal

The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.

Everything is open:
πŸ€– Demo β†’ build-small-hackathon/OpenMythos
🧠 Model β†’ build-small-hackathon/OpenMythos
πŸ“¦ CVE Dataset β†’ build-small-hackathon/CVE_Vulnerailities_Detailed
πŸ“„ ArXiv Dataset β†’ himanshu17HF/ArvixImport-Filtered-Final

Try it out and let us know where it breaks πŸ™
  • 2 replies
Β·
AbhaykoulΒ 
posted an update 3 months ago
view post
Post
406
Shipped v0.1.2 of vtx β€” a minimalist coding agent for the terminal.

Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.

Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono β€” same principles, pure Python, no transpiled runtime.

What ships out of the box:

β†’ Textual TUI + headless CLI (vtx -p "fix the failing test")
β†’ 49 LLM provider gateways, all declared in a single provider.yaml
β†’ 5 core tools (read / edit / write / bash / find) plus web search and fetch
β†’ Session tree with compaction, handoff, and resume
β†’ AGENTS.md / CLAUDE.md auto-discovery
β†’ Skills system β€” drop SKILL.md files in .agents/skills/ and they become slash commands
β†’ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
β†’ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist

This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.

Apache 2.0. uv tool install vtx-coding-agent and you're running.

GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent

Built in the open. Feedback, extensions, and PRs welcome.
mahwizzzzΒ 
posted an update 3 months ago
view post
Post
395
Released lafzyn , built over Qwen, an Urdu language model that converts Urdu text into IPA phonetic transcription, with GGUF builds for local inference.

Release contents:
- mahwizzzz/lafzyn: full weights
- mahwizzzz/lafzyn-gguf: quantized builds

Try it out πŸ€—
Demo: https://huggingface.co/spaces/mahwizzzz/Lafzyn
NymboΒ 
posted an update 6 months ago
view post
Post
7941
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
  • 3 replies
Β·
NymboΒ 
posted an update 8 months ago
view post
Post
3717
Genuine recommendation: You should really use this AutoHotKey macro. Save the file as macros.ahk and run it. Before sending a prompt to your coding agent, press Ctrl + Alt + 1 and paste your prompt to any regular chatbot. Then send the output to the agent. This is the actual, boring, real way to "10x your prompting". Use the other number keys to avoid repeating yourself over and over again. I use this macro prolly 100-200 times per day. AutoHotKey isn't as new or hype as a lot of other workflows, but there's a reason it's still widely used after 17 years. Don't overcomplicate it.

; Requires AutoHotkey v1.1+

; All macros are `Ctrl + Alt + <variable>`

^!1::
    Send, Please help me more clearly articulate what I mean with this message (write the message in a code block):
return

^!2::
    Send, Please make the following changes:
return

^!3::
    Send, It seems you got cut off by the maximum response limit. Please continue by picking up where you left off.
return


In my experience the past few months, Ctrl + Alt + 1 works best with Instruct models (non-thinking). Reasoning causes some models to ramble and miss the point. I've just been using GPT-5.x for this.
NymboΒ 
posted an update 9 months ago
view post
Post
2858
🚨 New tool for the Nymbo/Tools MCP server: The new Agent_Skills tool provides full support for Agent Skills (Claude Skills but open-source).

How it works: The tool exposes the standard discover/info/resources/validate actions. Skills live in /Skills under the same File_System root, and any bundled scripts run through Shell_Command, no new infrastructure required.

Agent_Skills(action="discover")  # List all available skills
Agent_Skills(action="info", skill_name="music-downloader")  # Full SKILL.md
Agent_Skills(action="resources", skill_name="music-downloader")  # Scripts, refs, assets


I've included a music-downloader skill as a working demo, it wraps yt-dlp for YouTube/SoundCloud audio extraction.

Caveat: On HF Spaces, Shell_Command works for most tasks, but some operations (like YouTube downloads) are restricted due to the container environment. For full functionality, run the server locally on your machine.

Try it out ~ https://www.nymbo.net/nymbot
KingNishΒ 
posted an update 9 months ago
view post
Post
3848
Muon vs MuonClip vs Muon+Adamw

Muon has gone from an experiment to a mainstream optimizer, but does it hold up for fine‑tuning? We ran head‑to‑head tests on Qwen3‑4B (10k+ high‑quality instruction rows) to find out.

Short story: Pure Muon converged fastest at the start, but its gradient‑norm spikes made training unstable. MuonClip (Kimi K2’s clipping) stabilizes long pretraining runs, yet in our small‑scale fine‑tune it underperformed, lower token accuracy and slower convergence. The winner was the hybrid: Muon for 2D layers + AdamW for 1D layers. It delivered the best balance of stability and final performance and even beat vanilla AdamW.

Takeaway: for small-scale fine-tuning, hybrid = practical and reliable.

Next Step: scale to larger models/datasets to see if Muon’s spikes become catastrophic or if clipping wins out.

Full Blog Link: https://huggingface.co/blog/KingNish/optimizer-part1
KingNishΒ 
posted an update 9 months ago
NymboΒ 
posted an update 9 months ago
view post
Post
5314
πŸš€ I've just shipped a major update to the Nymbo/Tools MCP server: the Agent_Terminal, a single "master tool" that cuts token usage by over 90%!

Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.

# The Problem

Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window β€” a 10,000-row spreadsheet? That's all going into context just to sum a column.

# The Solution: One Tool to Rule Them All

Agent_Terminal wraps all 12 tools (Web_Search, Web_Fetch, File_System, Generate_Image, Generate_Speech, Generate_Video, Deep_Research, Memory_Manager, Obsidian_Vault, Shell_Command, Code_Interpreter) into a single Python code execution gateway.

Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:

# Search for Bitcoin price
result = Web_Search("current price of bitcoin", max_results=3)
print(result)


Don't know what tools are available? The agent can discover them at runtime:

print(search_tools('image'))  # Find tools by keyword
print(usage('Generate_Image'))  # Get full docs for a specific tool


The individual direct tool calls are all still there, but they can be disabled if using the Agent_Terminal. Try it now - https://www.nymbo.net/nymbot
  • 1 reply
Β·
adamm-hfΒ 
posted an update 10 months ago
adamm-hfΒ 
posted an update 10 months ago
view post
Post
898
The new King πŸ‘‘has arrived!

Moonshot AI now the top model on Hugging Face πŸ”₯
moonshotai/Kimi-K2-Thinking