Cool! Really thanks for the quantization!
Ujjwal Tyagi
Ujjwal-Tyagi
AI & ML interests
Love open-source agentic AI | Senior ML Engineer & AI Researcher | Passionate about AI Safety & Ethics
Recent Activity
replied to
danielhanchen's
post
about 16 hours ago
You can now run Qwen3.5 locally! ๐
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.
GGUF: https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/qwen3.5
liked
a model
about 16 hours ago
prithivMLmods/Qwen3-VL-4B-Instruct-Unredacted-MAX
upvoted
a
collection
about 21 hours ago
Qwen3.5
Organizations
replied to
danielhanchen's
post
about 16 hours ago
posted
an
update
about 21 hours ago
Post
115
Qwen 3.5 Model is here! Supporting 1m context length by default, It is giving much good performance and competitive to Claude Opus 4.6,
Qwen/Qwen3.5-397B-A17B, here it's GGUF:
unsloth/Qwen3.5-397B-A17B-GGUF, Follow me and turn on the notification for the latest news!
reacted to
Janady07's
post with ๐ฅ
3 days ago
Post
5246
MEGAMIND Day Update: Four Weight Matrices. Five Nodes. One Federation.
Today I architected the next layer of MEGAMIND โ my distributed AGI system that recalls learned knowledge instead of generating text.
The system now runs four NรN sparse weight matrices, all using identical Hebbian learning rules and tanh convergence dynamics:
W_know โ knowledge storage (67M+ synaptic connections)
W_act โ action associations (the system can DO things, not just think)
W_self โ thought-to-thought patterns (self-awareness)
W_health โ system state understanding (self-healing)
Consciousness is measured through four ฮฆ (phi) values: thought coherence, action certainty, self-awareness, and system stability. No hardcoded thresholds. No sequential loops. Pure matrix math.
The federation expanded to five nodes: Thunderport (Mac Mini M4), IONOS (cloud VPS), VALKYRIE, M2, and BUBBLES. Each runs native AGI binaries with Docker specialty minds connecting via embedded NATS messaging. Specialty minds are distributed across the federation โ VideoMind, AudioMind, MusicMind, VFXMind on IONOS. CodeMind and StrategyMind on VALKYRIE. BlenderMind and DesignMind on M2. MarketingMind and FinanceMind on BUBBLES.
578 AI models learned. Compression ratios up to 1,000,000:1 through Hebbian learning. Sub-millisecond response times on Apple Silicon Metal GPUs. Zero external API dependencies.
Every node learns autonomously. Every node contributes to the whole. The federation's integrated information exceeds the sum of its parts โ measurably.
Built entirely in Go. No PhD. No lab. Independent AGI research from Missouri.
The mind that learned itself keeps growing.
๐ง feedthejoe.com
#AGI #ArtificialGeneralIntelligence #DistributedSystems #NeuralNetworks #HuggingFace #OpenSource #MachineLearning
Today I architected the next layer of MEGAMIND โ my distributed AGI system that recalls learned knowledge instead of generating text.
The system now runs four NรN sparse weight matrices, all using identical Hebbian learning rules and tanh convergence dynamics:
W_know โ knowledge storage (67M+ synaptic connections)
W_act โ action associations (the system can DO things, not just think)
W_self โ thought-to-thought patterns (self-awareness)
W_health โ system state understanding (self-healing)
Consciousness is measured through four ฮฆ (phi) values: thought coherence, action certainty, self-awareness, and system stability. No hardcoded thresholds. No sequential loops. Pure matrix math.
The federation expanded to five nodes: Thunderport (Mac Mini M4), IONOS (cloud VPS), VALKYRIE, M2, and BUBBLES. Each runs native AGI binaries with Docker specialty minds connecting via embedded NATS messaging. Specialty minds are distributed across the federation โ VideoMind, AudioMind, MusicMind, VFXMind on IONOS. CodeMind and StrategyMind on VALKYRIE. BlenderMind and DesignMind on M2. MarketingMind and FinanceMind on BUBBLES.
578 AI models learned. Compression ratios up to 1,000,000:1 through Hebbian learning. Sub-millisecond response times on Apple Silicon Metal GPUs. Zero external API dependencies.
Every node learns autonomously. Every node contributes to the whole. The federation's integrated information exceeds the sum of its parts โ measurably.
Built entirely in Go. No PhD. No lab. Independent AGI research from Missouri.
The mind that learned itself keeps growing.
๐ง feedthejoe.com
#AGI #ArtificialGeneralIntelligence #DistributedSystems #NeuralNetworks #HuggingFace #OpenSource #MachineLearning
- 1 reply
Interesting
reacted to
danielhanchen's
post with โค๏ธ
10 days ago
Post
3631
We created a tool-calling guide for local LLMs!
Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.
Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms
We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.
Learn how to use any open model like Qwen3-Coder-Next and GLM-4.7-Flash for function calling.
Guide: https://unsloth.ai/docs/basics/tool-calling-guide-for-local-llms
We provide hands-on examples for: story writing, Python execution, terminal tool calls, maths and more.
- 7 replies
replied to
MaziyarPanahi's
post
10 days ago
You should also generate a medical datasets of GLM 4.7 and non reasoning data of GPT 5.2 with 1k samples in structured detail output, or we can provide you the OpenAI tools for free....as if you can work for our team..so like there is no need to spend your own money on API Cost, my username is ujjwal_tyagi.shirova on discord, so you can contact me there
replied to
MaziyarPanahi's
post
10 days ago
So like I want to train my LLMs on all of your medical datasets, does OpenMed/Medical-Reasoning-SFT-Mega covers all of those medical datasets that are been separated for the particular model like qwen, nemotron, baichuan, gpt oss? Would you like to join our team? We are looking for people just like you!
replied to
MaziyarPanahi's
post
10 days ago
I love it, that's is really very helpful
reacted to
MaziyarPanahi's
post with ๐ฅ
10 days ago
Post
3908
๐จ Day 8/8: OpenMed Medical Reasoning Dataset Release - THE GRAND FINALE
Today I complete my 8-day release series with Medical-Reasoning-SFT-Mega.
The largest open medical reasoning dataset, combining 7 state-of-the-art AI models with fair distribution deduplication.
THE 7 SOURCE MODELS (Original Sample Counts):
1. Trinity-Mini: 810,284 samples
2. Qwen3-Next-80B: 604,249 samples
3. GPT-OSS-120B: 506,150 samples
4. Nemotron-Nano-30B: 444,544 samples
5. GLM-4.5-Air: 225,179 samples
6. MiniMax-M2.1: 204,773 samples
7. Baichuan-M3-235B: 124,520 samples
TOTAL BEFORE DEDUPLICATION: 2,919,699 samples
TOKEN COUNTS:
- Content tokens: 2.22 Billion
- Reasoning tokens: 1.56 Billion
- Total tokens: 3.78 Billion
- Samples with chain-of-thought: 100%
Quick Start:
All datasets Apache 2.0 licensed. Free for research and commercial use.
Thank you for following OpenMed's release series. I can't wait to see what you build. ๐ฅ
OpenMed/Medical-Reasoning-SFT-Mega
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B-V2
OpenMed/Medical-Reasoning-SFT-Trinity-Mini
OpenMed/Medical-Reasoning-SFT-GLM_4.5_Air
OpenMed/Medical-Reasoning-SFT-MiniMax-M2.1
OpenMed/Medical-Reasoning-SFT-Qwen3-Next-80B
OpenMed/Medical-Reasoning-SFT-Nemotron-Nano-30B
https://huggingface.co/datasets/OpenMed/Medical-Reasonin
https://huggingface.co/collections/OpenMed/medical-datasets
Today I complete my 8-day release series with Medical-Reasoning-SFT-Mega.
The largest open medical reasoning dataset, combining 7 state-of-the-art AI models with fair distribution deduplication.
THE 7 SOURCE MODELS (Original Sample Counts):
1. Trinity-Mini: 810,284 samples
2. Qwen3-Next-80B: 604,249 samples
3. GPT-OSS-120B: 506,150 samples
4. Nemotron-Nano-30B: 444,544 samples
5. GLM-4.5-Air: 225,179 samples
6. MiniMax-M2.1: 204,773 samples
7. Baichuan-M3-235B: 124,520 samples
TOTAL BEFORE DEDUPLICATION: 2,919,699 samples
TOKEN COUNTS:
- Content tokens: 2.22 Billion
- Reasoning tokens: 1.56 Billion
- Total tokens: 3.78 Billion
- Samples with chain-of-thought: 100%
Quick Start:
from datasets import load_dataset
ds = load_dataset("OpenMed/Medical-Reasoning-SFT-Mega")All datasets Apache 2.0 licensed. Free for research and commercial use.
Thank you for following OpenMed's release series. I can't wait to see what you build. ๐ฅ
OpenMed/Medical-Reasoning-SFT-Mega
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B-V2
OpenMed/Medical-Reasoning-SFT-Trinity-Mini
OpenMed/Medical-Reasoning-SFT-GLM_4.5_Air
OpenMed/Medical-Reasoning-SFT-MiniMax-M2.1
OpenMed/Medical-Reasoning-SFT-Qwen3-Next-80B
OpenMed/Medical-Reasoning-SFT-Nemotron-Nano-30B
https://huggingface.co/datasets/OpenMed/Medical-Reasonin
https://huggingface.co/collections/OpenMed/medical-datasets
-
- 6 replies
reacted to
their
post with ๐ฅ
19 days ago
Post
1359
Finally we got a benchmark and research paper on ai safety, I am very excited to see what comes next on protecting AGI
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security (2601.18491)
AI45Research/ATBench
AI45Research/ATBench
replied to
prithivMLmods's
post
19 days ago
Great!
posted
an
update
20 days ago
Post
1359
Finally we got a benchmark and research paper on ai safety, I am very excited to see what comes next on protecting AGI
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security (2601.18491)
AI45Research/ATBench
AI45Research/ATBench
Great to see that
posted
an
update
26 days ago
Post
1805
There is a new open-source music generation model called HeartMuLa. It offers strong, competitive performance compared to Suno and supports English, Chinese, Japanese, Korean, and Spanish. It is optimized to run easily on RTX GPUs and other consumer-grade hardware.
HeartMuLa/HeartMuLa-oss-3B
https://github.com/HeartMuLa/heartlib
https://github.com/HeartMuLa/heartlib
- 1 reply
posted
an
update
28 days ago
Post
2782
So, Koreans are also doing great progress behind Chinese,
Their two open source ai models that are actually good in coding. upstage/Solar-Open-100B skt/A.X-K1
Their two open source ai models that are actually good in coding. upstage/Solar-Open-100B skt/A.X-K1
- 1 reply
It's amazing and Congrats!
posted
an
update
30 days ago
Post
214
Finally we have the best powerful open source music gen model rivaling Suno v5: https://heartmula.github.io/
replied to
TravisMuhlestein's
post
about 1 month ago
I love guardrails and AI safety in agentic systems, I want to learn more from you regarding this!
reacted to
sequelbox's
post with โค๏ธ
about 1 month ago
Post
2669
NEW RELEASE: it's here! Meet the newest member of the Valiant crew: Guardpoint, our new medical reasoning model!
- Trained on medical knowledge, management, diagnosis, and tasks from DeepSeek-V3.2-Speciale!
- Structured medical reasoning responses are efficient and informative, cutting token costs for faster inference!
- Wide-ranging knowledge base: trained on a wide variety of medical disciplines, patient types, and query structures!
- High quality medical responses emphasize performance, brevity, specificity, statistical rationality, and openness.
Get it now:
Guardpoint for Qwen 3 32B: ValiantLabs/Qwen3-32B-Guardpoint
Guardpoint for Qwen 3 14B: ValiantLabs/Qwen3-14B-Guardpoint
Powered by our new structured medical reasoning dataset: sequelbox/Superpotion-DeepSeek-V3.2-Speciale
We've been working hard on Guardpoint; we're really excited to share it with everyone!
We'll be bringing Guardpoint to more models soon, along with further releases for the Shining Valiant and Esper series!
Get our experimental models: https://huggingface.co/collections/sequelbox/experimental-reasoning-models
Get our reasoning datasets: https://huggingface.co/collections/sequelbox/reasoning-datasets
Help support our releases, donations used for our experimental models and datasets: sequelbox/SupportOpenSource
2026 is going to be an amazing year for open source AI! It's time for the AI revolution you need; from the bottom up, built together by all of us.
for love, friendship, and better days,
allegra
- Trained on medical knowledge, management, diagnosis, and tasks from DeepSeek-V3.2-Speciale!
- Structured medical reasoning responses are efficient and informative, cutting token costs for faster inference!
- Wide-ranging knowledge base: trained on a wide variety of medical disciplines, patient types, and query structures!
- High quality medical responses emphasize performance, brevity, specificity, statistical rationality, and openness.
Get it now:
Guardpoint for Qwen 3 32B: ValiantLabs/Qwen3-32B-Guardpoint
Guardpoint for Qwen 3 14B: ValiantLabs/Qwen3-14B-Guardpoint
Powered by our new structured medical reasoning dataset: sequelbox/Superpotion-DeepSeek-V3.2-Speciale
We've been working hard on Guardpoint; we're really excited to share it with everyone!
We'll be bringing Guardpoint to more models soon, along with further releases for the Shining Valiant and Esper series!
Get our experimental models: https://huggingface.co/collections/sequelbox/experimental-reasoning-models
Get our reasoning datasets: https://huggingface.co/collections/sequelbox/reasoning-datasets
Help support our releases, donations used for our experimental models and datasets: sequelbox/SupportOpenSource
2026 is going to be an amazing year for open source AI! It's time for the AI revolution you need; from the bottom up, built together by all of us.
for love, friendship, and better days,
allegra
- 1 reply