Anybody like?
OpenEngineer
Monster-Code
AI & ML interests
Training AI models!
Recent Activity
commentedon an article 1 day ago
So, let’s make our own dataset upvoted an article 1 day ago
So, let’s make our own dataset repliedto their post 1 day ago
Introducing Audiyo 🎶 — Run Stable Audio Open on 8GB of RAM
https://github.com/TeamAudiyo/Audiyo. Organizations
replied to their post 1 day ago
reacted to their post with 👍 1 day ago
Post
2434
- 5 replies
reacted to Banaxi-Tech's post with 👍❤️ 1 day ago
Post
5544
AGI has arrived.
Just gotta wait for the GLM distill.
Just gotta wait for the GLM distill.
- 29 replies
reacted to tegridydev's post with 🔥 1 day ago
Post
3406
Been playing around with Astra the last few days and gave it my usual dumb Minecraft test lol
Started with a super vague oneshot prompt in Work on Astra Max, got a surprisingly complete voxel game back, then pushed the same project through one more Max revision and finally into Codex CLI with Astra xHigh for
Whole run was about 145 mins from first prompt to the final top-down sim version, and the overall dev experience was noticeably smoother than my similar Sol 5.6 runs.
Wrote up the process, timings, screenshots and linked the original one-shot Wildblock source here:
https://huggingface.co/blog/tegridydev/minecraft-time-with-astra-tegridydev
Source / oneshot:
https://github.com/tegridydev/tegridy/blob/main/blog/agents/minecraft-time-with-astra/wildblock.html
[td] tegridydev
Started with a super vague oneshot prompt in Work on Astra Max, got a surprisingly complete voxel game back, then pushed the same project through one more Max revision and finally into Codex CLI with Astra xHigh for
/plan + Astra Low for /goal.Whole run was about 145 mins from first prompt to the final top-down sim version, and the overall dev experience was noticeably smoother than my similar Sol 5.6 runs.
Wrote up the process, timings, screenshots and linked the original one-shot Wildblock source here:
https://huggingface.co/blog/tegridydev/minecraft-time-with-astra-tegridydev
Source / oneshot:
https://github.com/tegridydev/tegridy/blob/main/blog/agents/minecraft-time-with-astra/wildblock.html
[td] tegridydev
- 2 replies
reacted to sergiopaniego's post with 👀 1 day ago
Post
2315
while preparing the last class of the Training Agents live series during the summer, i spent some time reading the post-training sections of many frontier model reports, to learn how they use RL environments to improve their models, and wrote a blog about it
if you use any kind of coding harness, or you saw the Blender scenes that went viral recently, this might be interesting to you
Blog: https://huggingface.co/blog/sergiopaniego/rl-environments-2026
if you use any kind of coding harness, or you saw the Blender scenes that went viral recently, this might be interesting to you
Blog: https://huggingface.co/blog/sergiopaniego/rl-environments-2026
replied to their post 1 day ago
https://huggingface.co/TeamAudiyo/MM3-GGUF
Adding Minimax Music 3 support right now to GH and HF and PyPi 🫠
Native GGUF support is also being added soon for more architectures!
reacted to DedeProGames's post with 👍 1 day ago
Post
83
🚀 Introducing the GRM-3.2 Family
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
OrionLLM
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
- 2 replies
reacted to DavidAU's post with 🚀❤️ 1 day ago
Post
5884
Qwen 3.8 27B - TWIN TURBO, Fable Fusion (10 modes of operation)
Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit AND THIS is instruct mode - thinking/reasoning is higher.
This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants.
BUT WE WENT FURTHER:
Now with 5 reasoning modes (2 new - UltraXhigh / Einstein), and 5 instruct modes (2 new - UltraXhigh / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level).
GGUFS:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit AND THIS is instruct mode - thinking/reasoning is higher.
This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants.
BUT WE WENT FURTHER:
Now with 5 reasoning modes (2 new - UltraXhigh / Einstein), and 5 instruct modes (2 new - UltraXhigh / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level).
GGUFS:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF
SOURCE:
DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
reacted to DedeProGames's post with 🚀 1 day ago
Post
83
🚀 Introducing the GRM-3.2 Family
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
OrionLLM
The GRM-3.2 family is a new generation of reasoning-focused models from OrionLLM, purpose-built for long-horizon agentic tasks, extremely difficult reasoning problems, advanced coding, and local AI workflows across a wide range of hardware constraints.
GRM-3.2-Sky is the flagship model in the family: a 35B-A3B Mixture-of-Experts model built on the Ornith-1.0-35B architecture, designed for elite structured reasoning, complex multi-file coding, advanced mathematics, and sustained coherence across extended agentic workflows. It represents a substantial leap in long-horizon task capability over its predecessor, GRM-2.6-Plus.
GRM-3.2-Cliff is the mid-sized workhorse: a 9B-parameter model optimized for long-horizon agentic tasks and difficult reasoning in low-to-mid GPU environments. It delivers strong multi-step planning, debugging, and terminal-agent performance without demanding flagship-level hardware.
GRM-3.2-Turf is the lightweight edge model: a 1.2B-parameter model based on the LiquidAI/LFM2.5-1.2B-Thinking architecture, engineered for efficient on-device execution, high-fidelity instruction following, and robust tool use on mobile, embedded, and other resource-constrained hardware.
All three models are designed for users who need dependable reasoning engines that can maintain goal-directed behavior, planning quality, and task fidelity across many steps—whether on a server, a local workstation, or an edge device.
Models:
GRM-3.2-Sky: OrionLLM/GRM-3.2-Sky
GRM-3.2-Cliff: OrionLLM/GRM-3.2-Cliff
GRM-3.2-Turf: OrionLLM/GRM-3.2-Turf
Organization:
- 2 replies
reacted to ProCreations's post with 🚀🔥😎🤗👍 1 day ago
Post
93
Grug 27b gguf got around 400,000 downloads. Grug v1.1 gguf got around 1000. Do you guys want new grugs?
reacted to mrs83's post with ➕ 1 day ago
Post
79
Currently HF Papers only ingests arXiv IDs. While arXiv is standard, it imposes endorsement requirements and legacy moderation bottlenecks that exclude a growing segment of independent researchers, decentralized collectives, and open-source practitioners who publish peer-traceable preprints through CERN/Zenodo, OpenAIRE or OSF.
Zenodo records provide immutable DOIs, versioned artifact linking, and standardized metadata via open APIs.
Integrating Zenodo/DOI ingestion alongside arXiv would drastically broaden paper discovery for the open-source community.
If the engineering bandwidth on the HF team is focused on other roadmaps, I’d be glad to collaborate, help spec the ingestion pipeline, or contribute to an initial integration PR to map Zenodo metadata into the Papers schema cleanly.
Is extending support to external DOI providers currently on the radar, or open to community contributions?
Forum discussion: https://discuss.huggingface.co/t/feature-request-question-non-arxiv-preprints-zenodo-on-hf-papers/179555
Zenodo records provide immutable DOIs, versioned artifact linking, and standardized metadata via open APIs.
Integrating Zenodo/DOI ingestion alongside arXiv would drastically broaden paper discovery for the open-source community.
If the engineering bandwidth on the HF team is focused on other roadmaps, I’d be glad to collaborate, help spec the ingestion pipeline, or contribute to an initial integration PR to map Zenodo metadata into the Papers schema cleanly.
Is extending support to external DOI providers currently on the radar, or open to community contributions?
Forum discussion: https://discuss.huggingface.co/t/feature-request-question-non-arxiv-preprints-zenodo-on-hf-papers/179555
reacted to Harley-ml's post with 🚀👍 1 day ago
Post
72
Zero-v1.0-144M is currently training. So far, it has completed 26% of its training run, with about 98 billion tokens to go.
Current Val PPL: 13.705
Zero-v1.0 uses a custom architecture consisting of RMSNorm, RoPe, SwiGLU, Engram Conditional Memory, mHC, and XSA GQA.
Current Val PPL: 13.705
Zero-v1.0 uses a custom architecture consisting of RMSNorm, RoPe, SwiGLU, Engram Conditional Memory, mHC, and XSA GQA.
reacted to SoulInPsyAbstract's post with 😎 1 day ago
Post
71
Built the part of a voice agent that's allowed to refuse you.
For a hackathon we needed the piece nobody demos first: what happens between "the model understood the request" and "the model did it." A deterministic gate classifies every action before it runs — reversible? moves money? destroys data? — and works out the consequence chain in plain language, not after the fact.
Ask it to check a balance: it just answers. Ask it to send $50: it speaks the consequence chain out loud and holds until you say an actual "yes." Ask it to wire $5,000: it refuses outright — that one's a hard invariant, and your "yes" doesn't unlock it. The gate doesn't trust your intent, and it doesn't trust its own read of the situation either.
Every path writes into an append-only, hash-chained receipt log. Not "the agent says it did X" — a record a stranger can verify without trusting the agent at all. Alter one entry and the chain breaks visibly.
21 tests, zero API keys to run the core loop.
Not a bigger model in the voice agent. A stricter loop around whatever model does the talking.
Repo: github.com/soulinpsyabstract/sipa-voice-gate (Apache 2.0)
Team sipaos — AssemblyAI Voice Agent Hackathon, submission Sep 30
For a hackathon we needed the piece nobody demos first: what happens between "the model understood the request" and "the model did it." A deterministic gate classifies every action before it runs — reversible? moves money? destroys data? — and works out the consequence chain in plain language, not after the fact.
Ask it to check a balance: it just answers. Ask it to send $50: it speaks the consequence chain out loud and holds until you say an actual "yes." Ask it to wire $5,000: it refuses outright — that one's a hard invariant, and your "yes" doesn't unlock it. The gate doesn't trust your intent, and it doesn't trust its own read of the situation either.
Every path writes into an append-only, hash-chained receipt log. Not "the agent says it did X" — a record a stranger can verify without trusting the agent at all. Alter one entry and the chain breaks visibly.
21 tests, zero API keys to run the core loop.
Not a bigger model in the voice agent. A stricter loop around whatever model does the talking.
Repo: github.com/soulinpsyabstract/sipa-voice-gate (Apache 2.0)
Team sipaos — AssemblyAI Voice Agent Hackathon, submission Sep 30