Post
1507
How do you train self-paying rl agents with jax? New colab that will set you up with Jaxpot is here: https://colab.research.google.com/drive/1-rm_Bh8CNaM861We97ZoicfgKxz0xOSi?usp=sharing
- 1 reply
Antonii
Apartman
AI & ML interests
Deep Learning
Neural Network
Recent Activity
reacted to DedeProGames's post with 🚀 20 days ago
GRaPE 2 Pro is now available.
https://huggingface.co/SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the `<thinking_mode>` tag. This gives you real control over how hard the model thinks, from skipping the reasoning phase entirely with `minimal`, all the way up to `xtra-Hi` for deep, extended thought on hard problems. For most agentic use, `auto` or `low` is the move to keep things snappy.
It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at `contact@skinnertopia.com` reacted to HannesVonEssen's post with ❤️ 22 days ago
📣 I made a visualizer for Hugging Face models: https://hfviewer.com
✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!
🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B
Feel free to try it out and give me feedback on how it can be improved! ❤️
Organizations
reacted to mipo57's post with 👍 17 days ago
reacted to DedeProGames's post with 🚀 20 days ago
Post
8575
GRaPE 2 Pro is now available.
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
SL-AI/GRaPE-2-Pro
This is the flagship model of the GRaPE 2 family and the largest model I have trained to date, sitting at 27B parameters. It is built on Qwen3.5-27B and trained on a closed-source proprietary dataset, with roughly half of post-training focused on code and the rest split between STEAM subjects and structured logical reasoning. It punches seriously above its weight class.
GRaPE 2 Pro supports multimodal input (image + text) and features 6 thinking modes via the
minimal, all the way up to xtra-Hi for deep, extended thought on hard problems. For most agentic use, auto or low is the move to keep things snappy.It also runs on consumer hardware. You can get it going with as low as 12GB of VRAM on a quantized build.
If you want to try it out and give feedback, that would be really appreciated. Email us at
contact@skinnertopia.com 
- 1 reply
reacted to HannesVonEssen's post with ❤️ 22 days ago
Post
222
📣 I made a visualizer for Hugging Face models: https://hfviewer.com
✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!
🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B
Feel free to try it out and give me feedback on how it can be improved! ❤️
✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!
🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B
Feel free to try it out and give me feedback on how it can be improved! ❤️
- 1 reply
liked a
model 22 days ago
upvoted a collection 22 days ago
reacted to eaddario's post with 🚀 23 days ago
Post
3189
Experimental global target bits‑per‑weight quantization of Qwen/Qwen3.6-27B and Qwen/Qwen3.6-35B-A3B.
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file size target.
Key Advantages:
- VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM).
- Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs.
Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the models' cards.
eaddario/Qwen3.6-27B-GGUF
eaddario/Qwen3.6-35B-A3B-GGUF
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file size target.
Key Advantages:
- VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM).
- Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs.
Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the models' cards.
eaddario/Qwen3.6-27B-GGUF
eaddario/Qwen3.6-35B-A3B-GGUF
upvoted a collection 27 days ago
reacted to projectlosangeles's post with 🔥 30 days ago
Post
11709
🔥Check out first-of-its-kind SOTA Orpheus Morpheus preview!🔥
projectlosangeles/Orpheus-Morpheus
Easily generate variations or similar compositions from any MIDI!
Please ❤️if you enjoyed Orpheus Morpheus!
Sincerely,
Alex
projectlosangeles/Orpheus-Morpheus
Easily generate variations or similar compositions from any MIDI!
Please ❤️if you enjoyed Orpheus Morpheus!
Sincerely,
Alex
reacted to danielhanchen's post with 🔥 about 1 month ago
Post
5343
Qwen3.6-27B is out now! Run it locally on 18GB RAM. 💜
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks.
GGUFs to run: unsloth/Qwen3.6-27B-GGUF
Guide + MLX: https://unsloth.ai/docs/models/qwen3.6
reacted to Ujjwal-Tyagi's post with 👍 about 1 month ago
Post
3951
We are hiring at Shirova AI. We need AI researchers and engineers to work in our research lab. Shirova AI is a research lab in India, so we can help our researchers move to nearby workspaces or let them work from home without ever coming to the lab. We're building our founding team, so the pay will be good. You can learn, so don't hesitate to mail us at: careers@shirova.com
liked a
model about 1 month ago
Qwen/Qwen3.6-27B
🧠🚀 72
6
#9442 opened about 1 month ago
by 
brickqwer
liked a
Space about 1 month ago
liked 2
models about 1 month ago
mistralai/Voxtral-4B-TTS-2603
🔥👀 30
4
#8882 opened 2 months ago
by 
theiceman
liked a
model about 1 month ago
liked 3
models 2 months ago
