AI & ML interests

None defined yet.

group2test's activity

dylanebertΒ 
posted an update 4 days ago
view post
Post
2749
You now have the option to filter 3D Arena to open source models.

dylanebert/3d-arena
  • 1 reply
Β·
dylanebertΒ 
posted an update 9 days ago
view post
Post
1574
Impressive new Image-to-3D model from Tencent!

Here's how the topology (left) compares to the open source state-of-the-art (right)

(using the Simplify option for reduced poly count)

Try it out here: tencent/Hunyuan3D-2mv
dylanebertΒ 
posted an update 28 days ago
view post
Post
1180
πŸ“’ New #1 in Generative 3D

CSM/Cube from Common Sense Machines is now the top ranked image-to-3d model

check out the results in dylanebert/3d-arena
regisssΒ 
posted an update about 1 month ago
view post
Post
1677
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2: An Investigation of FP8 Across Accelerators for LLM Inference (2502.01070)

The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"

One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!

Gaudi3 results soon...
dylanebertΒ 
posted an update about 2 months ago
dylanebertΒ 
posted an update 2 months ago
view post
Post
697
βš™οΈ Convert .ply to .splat

i've created a simple space to convert .ply gaussian splat files to .splat format

dylanebert/ply-to-splat
dylanebertΒ 
posted an update 3 months ago
view post
Post
2024
🟦 New Image-to-3D model from Stability AI

stabilityai/stable-point-aware-3d

here's how it looks, with TRELLIS for comparison
akhaliqΒ 
posted an update 3 months ago
view post
Post
14786
Google drops Gemini 2.0 Flash Thinking

a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more

now available in anychat, try it out: akhaliq/anychat
Β·
regisssΒ 
posted an update 3 months ago
dylanebertΒ 
posted an update 4 months ago
view post
Post
2315
TRELLIS is now the highest ranked open-source model in the 3D Arena Leaderboard, surpassing InstantMesh

dylanebert/3d-arena
  • 1 reply
Β·
dylanebertΒ 
posted an update 4 months ago
view post
Post
2925
blender has AI now
dylanebertΒ 
posted an update 4 months ago
view post
Post
4652
🟦 New open-source Image-to-3D model from Microsoft

TRELLIS: Structured 3D Latents for Scalable and Versatile 3D Generation

it's really good! the topology isn't clean, but it's a very very good 3D reference

JeffreyXiang/TRELLIS-image-large
  • 2 replies
Β·
akhaliqΒ 
posted an update 4 months ago
view post
Post
15026
QwQ-32B-Preview is now available in anychat

A reasoning model that is competitive with OpenAI o1-mini and o1-preview

try it out: akhaliq/anychat
  • 1 reply
Β·
akhaliqΒ 
posted an update 4 months ago
view post
Post
4302
New model drop in anychat

allenai/Llama-3.1-Tulu-3-8B is now available

try it here: akhaliq/anychat
dylanebertΒ 
posted an update 4 months ago
view post
Post
1684
Generate meshes with AI locally in Blender

πŸ“’ New open-source release

meshgen, a local blender integration of LLaMa-Mesh, is open source and available now πŸ€—

get started here: https://github.com/huggingface/meshgen
akhaliqΒ 
posted an update 4 months ago
view post
Post
3208
anychat

supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app

try it out there: akhaliq/anychat
regisssΒ 
posted an update 5 months ago
view post
Post
1422
Interested in performing inference with an ONNX model?⚑️

The Optimum docs about model inference with ONNX Runtime is now much clearer and simpler!

You want to deploy your favorite model on the hub but you don't know how to export it to the ONNX format? You can do it in one line of code as follows:
from optimum.onnxruntime import ORTModelForSequenceClassification

# Load the model from the hub and export it to the ONNX format
model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = ORTModelForSequenceClassification.from_pretrained(model_id, export=True)

Check out the whole guide πŸ‘‰ https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models
dylanebertΒ 
posted an update 6 months ago
dylanebertΒ 
posted an update 6 months ago
dylanebertΒ 
posted an update 6 months ago