Hugging Face's logo
Rao's picture
🔄 In a Training Loop

Rao

RakshithFury
3 7 11
mightyeagle's profile picture Praful932's profile picture webbrain-one-972097's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to jiteshkprasad's post with 👀 10 days ago
We just released Drishya Tiny, a 212M-parameter video generator trained from scratch on open-domain video, using the frozen Wan2.2 VAE and the Flan-T5-Base text encoder. It turns a text prompt, or a photo plus a prompt, into a 2-second 256×256 clip. The training run was 15 hours on one L40S, and the model’s own path cost about $21 of GPU time. On VBench (our own sampling and scoring with the official code, not a certified entry) it scores 75.6 on quality, level with VideoCrafter-0.9 (74.9) and close to ModelScope (78.1). On semantic it’s 32.3 against their 65-67, so following the prompt is the weak part. In a controlled test, better captions gave +3.0, and adding 30% photos on top gave about 1.6 more, all of it in what objects are and none in composition. I think at this size, looking real is cheap and understanding the prompt is what costs. It’s a research release, so the weights, code, logs, the full cost ($57.43 with every failed run) and the negative results are all out. Weights are CC BY-NC 4.0 because the training clips are research-only; the code is Apache-2.0. And it runs right in your browser with WebGPU, from text or a photo, on your own device. The browser version uses the tiny TAEW2.2 decoder by Ollin Boer Bohan, so its clips are a bit softer, and a clip takes a few seconds on a recent Mac. Run it in your browser: https://udgamlabs.com/models/drishya-tiny Space: https://huggingface.co/spaces/udgamlabs/Drishya-Tiny Model: https://huggingface.co/udgamlabs/Drishya-Tiny Technical report: https://udgamlabs.com/research/drishya-tiny Write-up: https://udgamlabs.com/blog/drishya-tiny Code: https://github.com/udgamlabs/drishya-tiny
liked a model 11 days ago
RecursiveSI/flint
reacted to ifaposto's post with 🔥 11 days ago
Self-distillation methods usually rely on an Exponential Moving Average (EMA) teachers to get synced and stable critics. However, this doesn't scale well for large models since holding both teacher and student (trained) on GPU increases latency, zero3 communication, etc. We can mitigate this with LoRA finetuning: the backbone is shared & frozen, and we need to maintain two light adapters: one for the student (trained) and one for the teacher (EMA of the student adapter). Getting this to work cleanly under TRL and ZeRO-3 took some fixes, so I packaged it as a plug-and-play repo. It supports: -> robust SDFT implementation that runs under ZeRO-3 -> ZeRO-3 + LoRA integration with adapter switching for teacher/student passes -> Saving and resuming EMA teacher checkpoint -> working deepspeed configs that fix memory spikes when GPU memory is tight I tested on Qwen3.5 and ToolAlpaca. Repo: https://github.com/ifiaposto/sdft_zero3 Feedback/ more examples/ issues welcome!
View all activity

Organizations

Axionic Labs's profile picture