SL-AI/GRaPE-2-Pro
Image-Text-to-Text • 28B • Updated • 182 • 2
Djuunaa
djuna
AI & ML interests
None yet
Recent Activity
new activity about 1 hour ago
SL-AI/GRaPE-2-Pro:WOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO liked a model about 1 hour ago
SL-AI/GRaPE-2-ProOrganizations
WOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO
1
#1 opened about 4 hours ago
by 
Kquant03
liked a
model about 1 hour ago
reacted to mrs83's post with 🔥 about 1 hour ago
Post
136
Real-time 3D telemetry of ethicalabs/Echo-DSRN-114M-v0.1.2 processing "can you please order a pizza" through the Intent classifier LoRA adapter.
Each orange lattice is a DSRNBlock slow state manifold. The red sphere is live entropy. The right panel shows the surprise gate firing token by token as the model converges on [TAKEAWAY_ORDER].
I built this because I'm a visual learner and I wanted to see the surprise gate open and close on each token. I needed to see what was happening inside the network, not just trust that it was working.
Turns out it's also a decent way to explain the architecture to someone who's never heard of this.
Made with Google Antigravity (Gemini)
mrs83/Echo-DSRN-114M-Telemetry-3D
Each orange lattice is a DSRNBlock slow state manifold. The red sphere is live entropy. The right panel shows the surprise gate firing token by token as the model converges on [TAKEAWAY_ORDER].
I built this because I'm a visual learner and I wanted to see the surprise gate open and close on each token. I needed to see what was happening inside the network, not just trust that it was working.
Turns out it's also a decent way to explain the architecture to someone who's never heard of this.
Made with Google Antigravity (Gemini)
mrs83/Echo-DSRN-114M-Telemetry-3D
- 1 reply
liked a
model 21 days ago
liked 3
models 24 days ago
liked 2
models 25 days ago
liked 3
models about 1 month ago
liked 3
models about 2 months ago
reacted to Reubencf's post with 🔥 about 2 months ago
Post
2759
🚀 I am thrilled to announce the release of a new Konkani LLM!
We've seen some fantastic results for both translation and transliteration tasks, and I'm excited to share this progress with the community.
📖 Read the launch article and see the results: https://huggingface.co/blog/Reubencf/konkani-llm
🤖 Explore the model and collection:
konkani
I would love to hear your feedback or see what you build with it! #Konkani #LLM #NLP #HuggingFace #IndicNLP #Konkani
We've seen some fantastic results for both translation and transliteration tasks, and I'm excited to share this progress with the community.
📖 Read the launch article and see the results: https://huggingface.co/blog/Reubencf/konkani-llm
🤖 Explore the model and collection:
I would love to hear your feedback or see what you build with it! #Konkani #LLM #NLP #HuggingFace #IndicNLP #Konkani
liked a
model about 2 months ago
reacted to sequelbox's post with ❤️ about 2 months ago
Post
249
NEW RELEASE: Esper 3.1 for the all-new Qwen 3.5 27b!
- Esper is our full-stack, full-cycle coding, DevOps, and architecture specialist!
- Our newest, best DeepSeek technical datasets emphasize more challenging queries and tough real-world coding tasks across a variety of programming languages and development paradigms:
- Titanium 3 for coding and reasoning in DevOps and architecture: sequelbox/Titanium3-DeepSeek-V3.1-Terminus
- Tachibana 3 for high-difficulty code production in a variety of topics and programming languages:
- sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus
- sequelbox/Tachibana3-Part2-DeepSeek-V3.2
- Mitakihara for MLOps, AI building, use, expertise, and research: sequelbox/Mitakihara-DeepSeek-R1-0528
Get Esper 3.1 now for Qwen 3.5 27b: ValiantLabs/Qwen3.5-27B-Esper3.1
We're very excited to build on the new Qwen 3.5 - look for Shining Valiant, Guardpoint, and the rest of our crew coming soon!
We're also planning for new datasets with the upcoming Deepseek V4, including improved agentic and deep-thinking capabilities, and making use of Deepseek's architecture innovations!
See our Experimental Reasoning models and open-source datasets: @sequelbox
Help us keep working for open source AI with a donation - used directly for new models and datasets: sequelbox/SupportOpenSource
Fight for open source. It's an investment in your own future with AI. Closed-source providers will get more expensive, restrictive, and punitive in the long run if they win.
with love, your captain,
allegra
- Esper is our full-stack, full-cycle coding, DevOps, and architecture specialist!
- Our newest, best DeepSeek technical datasets emphasize more challenging queries and tough real-world coding tasks across a variety of programming languages and development paradigms:
- Titanium 3 for coding and reasoning in DevOps and architecture: sequelbox/Titanium3-DeepSeek-V3.1-Terminus
- Tachibana 3 for high-difficulty code production in a variety of topics and programming languages:
- sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus
- sequelbox/Tachibana3-Part2-DeepSeek-V3.2
- Mitakihara for MLOps, AI building, use, expertise, and research: sequelbox/Mitakihara-DeepSeek-R1-0528
Get Esper 3.1 now for Qwen 3.5 27b: ValiantLabs/Qwen3.5-27B-Esper3.1
We're very excited to build on the new Qwen 3.5 - look for Shining Valiant, Guardpoint, and the rest of our crew coming soon!
We're also planning for new datasets with the upcoming Deepseek V4, including improved agentic and deep-thinking capabilities, and making use of Deepseek's architecture innovations!
See our Experimental Reasoning models and open-source datasets: @sequelbox
Help us keep working for open source AI with a donation - used directly for new models and datasets: sequelbox/SupportOpenSource
Fight for open source. It's an investment in your own future with AI. Closed-source providers will get more expensive, restrictive, and punitive in the long run if they win.
with love, your captain,
allegra
- 1 reply
liked a
model about 2 months ago
liked a
model 2 months ago
