BeaverAI/Spectre-37B-v1b-GGUF
37B • Updated • 4
Brandon H Hawes
BrandonH
AI & ML interests
None yet
Recent Activity
liked a model about 12 hours ago
BeaverAI/Spectre-37B-v1b-GGUF liked a model 1 day ago
zerofata/G4-LuneLight-31B-GGUF liked a model 1 day ago
zerofata/G4-LuneLight-31BOrganizations
None yet
liked a
model about 12 hours ago
liked 2
models 1 day ago
liked a
dataset 2 months ago
liked a
Space 2 months ago
liked a
dataset 2 months ago
liked 2
models 3 months ago
liked 2
models 7 months ago
liked a
Space 10 months ago
reacted to Ruurd's post with 🔥 over 1 year ago
Post
2,394
The past year I have been trying to get diffusion models to work for language generation, without having to retrain a LLM from scratch. And recently, we finally succeeded:
We introduce "LAD: LoRA-Adapted Denoiser", a method to convert a LLaMA model into a text diffusion model using LoRA finetuning and structured input corruption.
🎯 Try the demo and read the write-up here!
https://ruurdkuiper.github.io/tini-lad/
Unlike autoregressive (word-for-word) models like ChatGPT, diffusion models iteratively refine a noised sequence. However, most current diffusion approaches rely on all-parameter retraining and repeatedly remasking tokens, which is costly and slow during both training and inference!
🧠 With LAD:
- We can finetune an autoregressive model for diffusive generation in just 10 hours on a single GPU.
- Test-time compute is fully adjustable: fewer steps means faster outputs while more steps improve output quality.
- Due to our unique noising schedule, remasking is not always needed during inference. All tokens are attended to in each iteration!
🔍 LAD is built using:
– A frozen LLaMA-8B backbone
– Structured noising: token swaps, duplications, replacements, span shifts
– Modified attention masks for bidirectional decoding
💡 We show that even small, fast-trained models can perform diffusive generation — with competitive benchmark performance, perplexity and more flexible test-time behavior than traditional transformers.
We introduce "LAD: LoRA-Adapted Denoiser", a method to convert a LLaMA model into a text diffusion model using LoRA finetuning and structured input corruption.
🎯 Try the demo and read the write-up here!
https://ruurdkuiper.github.io/tini-lad/
Unlike autoregressive (word-for-word) models like ChatGPT, diffusion models iteratively refine a noised sequence. However, most current diffusion approaches rely on all-parameter retraining and repeatedly remasking tokens, which is costly and slow during both training and inference!
🧠 With LAD:
- We can finetune an autoregressive model for diffusive generation in just 10 hours on a single GPU.
- Test-time compute is fully adjustable: fewer steps means faster outputs while more steps improve output quality.
- Due to our unique noising schedule, remasking is not always needed during inference. All tokens are attended to in each iteration!
🔍 LAD is built using:
– A frozen LLaMA-8B backbone
– Structured noising: token swaps, duplications, replacements, span shifts
– Modified attention masks for bidirectional decoding
💡 We show that even small, fast-trained models can perform diffusive generation — with competitive benchmark performance, perplexity and more flexible test-time behavior than traditional transformers.
- 2 replies
liked a
model about 2 years ago
liked a
model over 2 years ago
liked a
Space about 3 years ago
liked a
Space over 3 years ago