IFM/PAN2
Image-Text-to-Video • 29B • Updated • 248 • 96
alkinun
AtAndDev
AI & ML interests
decentralize
Recent Activity
liked a model 1 day ago
IFM/PAN2 upvoted a paper 1 day ago
Arcee's MergeKit: A Toolkit for Merging Large Language Models liked a model 2 days ago
tencent/Qwen3.8-27B-DSpine-b16Organizations
liked a
model 1 day ago
upvoted a paper 1 day ago
liked 2
models 2 days ago
upvoted a collection 3 days ago
reacted to sergiopaniego's post with 🚀🔥 3 days ago
Post
6,749
New post-training example: SFT on agent traces with TRL
→ A large model works as a coding agent in OpenCode, run through OpenEnv
→ The tasks it solves become the training data
→ A 2B model goes from 5.5% to 34.4% on held-out tasks
About 500 traces get most of the gain. Five times more add only 3 to 4 points, so SFT gets the agent working and RL has to do the rest
Full guide, with the models, traces and every rollout open:
https://github.com/huggingface/trl/tree/main/examples/sft_agent_traces
→ A large model works as a coding agent in OpenCode, run through OpenEnv
→ The tasks it solves become the training data
→ A 2B model goes from 5.5% to 34.4% on held-out tasks
About 500 traces get most of the gain. Five times more add only 3 to 4 points, so SFT gets the agent working and RL has to do the rest
Full guide, with the models, traces and every rollout open:
https://github.com/huggingface/trl/tree/main/examples/sft_agent_traces
- 1 reply
liked a
model 3 days ago
replied to Banaxi-Tech's post 4 days ago
oh nice! well, good luck. very excited.
replied to Banaxi-Tech's post 4 days ago
cool, but what happened to the promise? :)
reacted to Banaxi-Tech's post with 🔥 4 days ago
Post
4,896
We're excited to release BananaMind 2.5 Pro.
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the AxiomicLabs/Open_SLM_Leaderboard
Check it out at BananaMind/BananaMind-2.5-Pro
BananaMind
@ArushCodes
@Bc-AI
It's done some post-training on our BananaMind 2 Pro base, via distillation of SmolLM2 360M.
It scores 28.98 INT INDEX compared to 24.96 of BananaMind 2 Pro on the AxiomicLabs/Open_SLM_Leaderboard
Check it out at BananaMind/BananaMind-2.5-Pro
@ArushCodes
@Bc-AI
- 53 replies
liked a
model 4 days ago
reacted to savoji's post with 🔥 5 days ago
Post
2,506
Idol, a new Apache-2.0 image-to-3D model from @speridlabs , makes a 3D Gaussian splat from one image in 7.2 GB of peak VRAM. It is the #1 trending model on the Hub with 1,057 likes.
It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28.
📊 The numbers
• Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885)
• LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat
• 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080
🛠️ Try it
• Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login
• python -m idol.sample --image photo.jpg --mode real
• --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB)
⚠️ Caveats
• Test set and size are not named, and no independent evaluation exists yet
• The card says "under 2 seconds", but the timing table shows 3.4 s at best
• Single objects only, NVIDIA CUDA required, no failure cases shown
speridlabs/idol
https://speridlabs.com/research/idol
If you run it on your own messy photos, how do the unseen sides hold up?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/5f660ae6ae56
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats
• The thread on X: https://x.com/saavoji/status/2119137739580858545
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol
It writes a standard 3DGS .ply with up to 1,048,576 Gaussians, including sides the picture never showed, and does background removal and framing itself. The catch: the only quality evidence is the authors' own benchmark, on a repo created 2026-10-28.
📊 The numbers
• Authors' benchmark, 1 x H100: best in 6 of 8 columns vs TripoSplat, TRELLIS and LGM (SSIM 0.726, LPIPS 0.213, DINOv2 0.781, CLIP 0.885)
• LGM wins PSNR (12.46 vs 12.25) and speed (1.1 s). Idol takes 6.8 s vs 7.1 s for TRELLIS and 9.9 s for TripoSplat
• 262,144 Gaussians, 50 steps: 3.4 s on B300, 6.7 s on H100, 19.1 s on RTX 4090, 46.2 s on a 10 GB RTX 3080
🛠️ Try it
• Install idol-sdk, accept the terms of the gated DINOv3 and FLUX.2-dev models, run hf auth login
• python -m idol.sample --image photo.jpg --mode real
• --num_gaussians runs from 32,768 (0.4 MB) to 1,048,576 (12.2 MB)
⚠️ Caveats
• Test set and size are not named, and no independent evaluation exists yet
• The card says "under 2 seconds", but the timing table shows 3.4 s at best
• Single objects only, NVIDIA CUDA required, no failure cases shown
speridlabs/idol
https://speridlabs.com/research/idol
If you run it on your own messy photos, how do the unseen sides hold up?
📚 Read it elsewhere
• The deep dive on Medium: https://medium.com/p/5f660ae6ae56
• The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/speridlabs-idol-builds-3d-splats
• The thread on X: https://x.com/saavoji/status/2119137739580858545
• Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#speridlabs-idol
- 4 replies
liked a
Space 5 days ago
liked 2
datasets 5 days ago
liked 4
models 5 days ago
