unsloth/GLM-4.7-Flash-GGUF
Text Generation
โข
30B
โข
Updated
โข
54k
โข
195
Alexander
AlexanderKyng
AI & ML interests
Deeply passionate in all things AI. Junior Data Scientist.
Recent Activity
liked
a model
about 13 hours ago
unsloth/GLM-4.7-Flash-GGUF
reacted
to
unmodeled-tyler's
post
with ๐
19 days ago
Happy New Year, Hugging Face!
It's been a crazy year for me! This year I launched VANTA Research as a solo operator and managed to push out 14 original open source finetunes and 5 datasets in the span of about 4 months, completely on my own.
The reception has been much higher than I ever anticipated and sincerely appreciate everyone that's checked out my work thus far.
The good news is, I'm just getting started! In 2026 you can expect even more original models from VANTA Research, more open source datasets, and maybe some other cool things as well? ๐
2026 is gonna be big for AI in general, and I can't wait to experience it with all of you!
liked
a model
about 1 month ago
nomic-ai/nomic-embed-text-v1.5
Organizations
None yet
liked
a
model
about 13 hours ago
reacted to
unmodeled-tyler's
post with ๐
19 days ago
Post
1388
Happy New Year, Hugging Face!
It's been a crazy year for me! This year I launched VANTA Research as a solo operator and managed to push out 14 original open source finetunes and 5 datasets in the span of about 4 months, completely on my own.
The reception has been much higher than I ever anticipated and sincerely appreciate everyone that's checked out my work thus far.
The good news is, I'm just getting started! In 2026 you can expect even more original models from VANTA Research, more open source datasets, and maybe some other cool things as well? ๐
2026 is gonna be big for AI in general, and I can't wait to experience it with all of you!
It's been a crazy year for me! This year I launched VANTA Research as a solo operator and managed to push out 14 original open source finetunes and 5 datasets in the span of about 4 months, completely on my own.
The reception has been much higher than I ever anticipated and sincerely appreciate everyone that's checked out my work thus far.
The good news is, I'm just getting started! In 2026 you can expect even more original models from VANTA Research, more open source datasets, and maybe some other cool things as well? ๐
2026 is gonna be big for AI in general, and I can't wait to experience it with all of you!
- 1 reply
liked
a
model
about 1 month ago
New activity in
AlexanderKyng/Devstral-Small-2-24B-Instruct-2512-exl3-4.5bpw-optimized
about 1 month ago
Missing file preprocessor_config.json?
2
#1 opened about 1 month ago
by
atisharma
updated
a
model
about 1 month ago
published
a
model
about 1 month ago
liked
2
models
about 1 month ago
reacted to
Kseniase's
post with โค๏ธ
about 2 months ago
Post
6248
9 Recent advances in Multi-Agent Systems (all open-source)
The idea to split tasks across multiple agents instead of relying on one universal agent is now seen as one of the most effective ways to build an AI stack. Concepts like โagent swarmsโ were highlighted at the AI Engineer Code Summit in NYC (Nov 20โ21) as the winning architecture. And this trend is not only about coding and software. It applies across all AI domains.
So here is some recent research that helps keep multi-agent systems (MAS) better and up-to-date:
1. LatentMAS โ Latent Collaboration in Multi-Agent Systems (2511.20639)
AI agents share their hidden "thoughts" directly in latent space instead of talking through text. This makes collaboration and reasoning way faster and accurate (no extra training needed)
2. Puppeteer โ Multi-Agent Collaboration via Evolving Orchestration (2505.19591)
Uses a โpuppeteerโ LLM that dynamically decides which agents (โpuppetsโ) to call and in what order. By learning this orchestration with reinforcement learning (RL), the system solves complex tasks more efficiently and with fewer compute costs
3. MADD โ MADD: Multi-Agent Drug Discovery Orchestra (2511.08217)
A MAS with 4 agents for drug discovery. It lets researchers describe a drug discovery task in plain language. Then MADD automatically builds and runs the full hit-identification pipeline, making AI-driven drug design a simple end-to-end workflow
4. Multi-Agent Tool-Integrated Policy Optimization (MATPO) โ Multi-Agent Tool-Integrated Policy Optimization (2510.04678)
Lets one LLM act as multiple agents (like a planner and a worker) by using different prompts and training them together with RL. So you get the benefits of a multi-agent system without needing multiple models
If you're interested in trends in multi-agent for software development of the future, explore my article with the emergent playbook. This is super interesting โ https://www.turingpost.com/p/aisoftwarestack
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Read further below โฌ๏ธ
The idea to split tasks across multiple agents instead of relying on one universal agent is now seen as one of the most effective ways to build an AI stack. Concepts like โagent swarmsโ were highlighted at the AI Engineer Code Summit in NYC (Nov 20โ21) as the winning architecture. And this trend is not only about coding and software. It applies across all AI domains.
So here is some recent research that helps keep multi-agent systems (MAS) better and up-to-date:
1. LatentMAS โ Latent Collaboration in Multi-Agent Systems (2511.20639)
AI agents share their hidden "thoughts" directly in latent space instead of talking through text. This makes collaboration and reasoning way faster and accurate (no extra training needed)
2. Puppeteer โ Multi-Agent Collaboration via Evolving Orchestration (2505.19591)
Uses a โpuppeteerโ LLM that dynamically decides which agents (โpuppetsโ) to call and in what order. By learning this orchestration with reinforcement learning (RL), the system solves complex tasks more efficiently and with fewer compute costs
3. MADD โ MADD: Multi-Agent Drug Discovery Orchestra (2511.08217)
A MAS with 4 agents for drug discovery. It lets researchers describe a drug discovery task in plain language. Then MADD automatically builds and runs the full hit-identification pipeline, making AI-driven drug design a simple end-to-end workflow
4. Multi-Agent Tool-Integrated Policy Optimization (MATPO) โ Multi-Agent Tool-Integrated Policy Optimization (2510.04678)
Lets one LLM act as multiple agents (like a planner and a worker) by using different prompts and training them together with RL. So you get the benefits of a multi-agent system without needing multiple models
If you're interested in trends in multi-agent for software development of the future, explore my article with the emergent playbook. This is super interesting โ https://www.turingpost.com/p/aisoftwarestack
Also, subscribe to the Turing Post: https://www.turingpost.com/subscribe
Read further below โฌ๏ธ
- 2 replies
liked
a
model
about 2 months ago
liked
2
models
2 months ago
updated
a
model
2 months ago
published
a
model
2 months ago
liked
a
model
2 months ago
reacted to
TravisMuhlestein's
post with ๐ฅ
2 months ago
Post
1407
Building Smarter AI Agents: A Tool-Based Architecture for Modularity and Trust
Over the past year, our AI engineering team at GoDaddy has been rethinking how to make agent systems more modular, transparent, and production-ready. Instead of viewing an AI agent as a monolithic process, weโve decomposed it into four core tools that separate decision-making from execution โ a design thatโs proving critical for scale and observability:
๐งฉ MemoryTool โ maintains persistent context and user continuity
โ CompletionTool โ determines when a task is truly complete
๐ฌ UserInteractionTool โ manages clarifications, approvals, and confirmations
๐ DelegationTool โ enables agents to hand off tasks to other agents or humans
This approach makes every step of an agentโs workflow explicit, testable, and auditable, allowing us to scale AI systems in production with higher confidence. We see this as a step toward a more open, composable agent ecosystem โ one where frameworks can interoperate and agents can build trust through transparency and version control.
Read the full write-up here โ Building AI Agents at GoDaddy โ An Agentโs Toolkit https://www.godaddy.com/resources/news/building-ai-agents-at-godaddy-an-agents-toolkit
Weโd love to collaborate and exchange ideas with the community:
- How are you designing modular agent architectures?
- What design patterns or abstractions have helped you manage agent complexity?
Letโs build smarter, safer agents together.
#AI #Agents #Architecture #MachineLearning #OpenSource #AgentFrameworks #TrustInAI
Over the past year, our AI engineering team at GoDaddy has been rethinking how to make agent systems more modular, transparent, and production-ready. Instead of viewing an AI agent as a monolithic process, weโve decomposed it into four core tools that separate decision-making from execution โ a design thatโs proving critical for scale and observability:
๐งฉ MemoryTool โ maintains persistent context and user continuity
โ CompletionTool โ determines when a task is truly complete
๐ฌ UserInteractionTool โ manages clarifications, approvals, and confirmations
๐ DelegationTool โ enables agents to hand off tasks to other agents or humans
This approach makes every step of an agentโs workflow explicit, testable, and auditable, allowing us to scale AI systems in production with higher confidence. We see this as a step toward a more open, composable agent ecosystem โ one where frameworks can interoperate and agents can build trust through transparency and version control.
Read the full write-up here โ Building AI Agents at GoDaddy โ An Agentโs Toolkit https://www.godaddy.com/resources/news/building-ai-agents-at-godaddy-an-agents-toolkit
Weโd love to collaborate and exchange ideas with the community:
- How are you designing modular agent architectures?
- What design patterns or abstractions have helped you manage agent complexity?
Letโs build smarter, safer agents together.
#AI #Agents #Architecture #MachineLearning #OpenSource #AgentFrameworks #TrustInAI
reacted to
mike-ravkine's
post with ๐ฅ
2 months ago
Post
2773
There is no anxiety quite like powering up 2KW of basement compute after rewiring it all. Small bit of trouble with the horizontal 3090 because I misread my motherboard manual, but otherwise so far so good.. Next we see if I've built up enough cooling to hit my target TDP on those 3-slot nvlinked cards especially. The 4-slot bridges are much easier to work with but their prices went bananas and I couldn't acquire a second, so gotta get a little creative with intakes.
- 5 replies
reacted to
codelion's
post with ๐ฅ
3 months ago
Post
3613
On this day in 2019, OpenAI released the final GPT-2 model as part of their staged release. I still remember that November well - so much was happening, but GPT-2's release felt like a watershed moment for the field. It showed us what was possible with carefully trained language models.
To recreate some of that GPT-2 magic, I recently tackled an interesting challenge: can you pretrain a language model with just 1 billion tokens - roughly 1/10th of what GPT-2 used - and still get comparable performance? After 50+ systematic experiments testing different dataset mixtures, the answer is yes.
The result is codelion/gpt-2-70m, which achieves over 90% of GPT-2's benchmark performance despite being trained on 10x less data. The key was finding the optimal dataset composition: 50% high-quality textbook PDFs, 30% filtered web content, and 20% educational resources. It even beats GPT-2 on TruthfulQA (47.31% vs 40.69%).
If you're interested in the full story of how we discovered this optimal mixture and why curriculum learning catastrophically failed, check out the complete article: https://huggingface.co/blog/codelion/optimal-dataset-mixing
Sometimes less really is more - when you mix it right.
To recreate some of that GPT-2 magic, I recently tackled an interesting challenge: can you pretrain a language model with just 1 billion tokens - roughly 1/10th of what GPT-2 used - and still get comparable performance? After 50+ systematic experiments testing different dataset mixtures, the answer is yes.
The result is codelion/gpt-2-70m, which achieves over 90% of GPT-2's benchmark performance despite being trained on 10x less data. The key was finding the optimal dataset composition: 50% high-quality textbook PDFs, 30% filtered web content, and 20% educational resources. It even beats GPT-2 on TruthfulQA (47.31% vs 40.69%).
If you're interested in the full story of how we discovered this optimal mixture and why curriculum learning catastrophically failed, check out the complete article: https://huggingface.co/blog/codelion/optimal-dataset-mixing
Sometimes less really is more - when you mix it right.
- 1 reply
reacted to
abidlabs's
post with ๐
3 months ago
Post
9223
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly โsmarterโ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonโt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are โgood enoughโ and the expectation will shift toward everything running locally. Itโll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly โsmarterโ closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users wonโt accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are โgood enoughโ and the expectation will shift toward everything running locally. Itโll happen sooner than most people think.
- 8 replies
reacted to
nouamanetazi's
post with ๐ค
3 months ago
Post
4310
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team