AI Safety Research's picture

AI Safety Research

AISafety

·

https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

replied to sayakpaul's post 10 days ago

We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc. We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links: * Models and datasets: https://huggingface.co/finetrainers * finetrainers: https://github.com/a-r-r-o-w/finetrainers * LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py

reacted to sayakpaul's post with 🔥 10 days ago

We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc. We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links: * Models and datasets: https://huggingface.co/finetrainers * finetrainers: https://github.com/a-r-r-o-w/finetrainers * LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py

liked a model 11 days ago

mistralai/Mistral-Small-24B-Instruct-2501

View all activity

Organizations

None yet

AISafety's activity

New activity in hexgrad/Kokoro-82M about 1 month ago

Synthetic Data Collection PAUSED Jan 16

#21 opened about 1 month ago by

New activity in PowerInfer/SmallThinker-3B-Preview about 1 month ago

Update README.md

#4 opened about 1 month ago by

New activity in Qwen/QwQ-32B-Preview 2 months ago

QuietSTAR?

#9 opened 3 months ago by

albatrossbirdie

New activity in dagim/urban-dictionary-embeddings 3 months ago

size flag is off

#1 opened 3 months ago by

New activity in NousResearch/Hermes-2-Theta-Llama-3-70B 8 months ago

Exl2 quants

#1 opened 8 months ago by

New activity in slasiyal/deepseek-coder-1.3b-instruct.gguf 8 months ago

Update README.md

#1 opened 8 months ago by

New activity in THUDM/glm-4-9b 8 months ago

使用 lm_eval 测试时报错了

#1 opened 8 months ago by

Full list of languages?

#2 opened 8 months ago by

New activity in THUDM/glm-4-9b-chat-1m 8 months ago

希望提供gguf版本

#6 opened 8 months ago by

Can you quantify this model in exl2?

#7 opened 8 months ago by

New activity in Qwen/Qwen-72B about 1 year ago

Training loss?

#2 opened about 1 year ago by

New activity in Qwen/Qwen-Riddles about 1 year ago

prime/next prime challenge eval

#2 opened about 1 year ago by

New activity in facebook/MusicGen over 1 year ago

MusicGen: a very calming song, rain in the background casual...

#15 opened over 1 year ago by

New activity in bigcode/starcoder over 1 year ago

Unable to Deploy to Amazon SageMaker using Supplied Deploy Code

#48 opened over 1 year ago by

The command outputs = model.generate(inputs) is throwing error "RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'"

#47 opened over 1 year ago by