sparsegpt
safetensors
sparsegpt | safetensors | |
---|---|---|
16 | 31 | |
634 | 2,472 | |
5.0% | 4.8% | |
2.4 | 8.2 | |
about 1 month ago | 3 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sparsegpt
-
(1/2) May 2023
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot (https://arxiv.org/abs/2301.00774)
- Why Falcon going Apache 2.0 is a BIG deal for all of us.
-
New Open-source LLMs! 🤯 The Falcon has landed! 7B and 40B
There is this : https://github.com/IST-DASLab/sparsegpt
-
Webinar: Running LLMs performantly on CPUs Utilizing Pruning and Quantization
Check the paper here, it's intersting: https://arxiv.org/abs/2301.00774
-
OpenAI chief goes before US Congress to propose licenses for building AI
There's no chance that we've peeked from a bang for buck sense - we still haven't adequately investigated sparse networks.
Relevantish: https://arxiv.org/abs/2301.00774
The fact that we can reach those levels of sparseness with pruning also indicates that we're not doing a very good job of generating the initial network conditions.
Being able to come up with trainable initial settings for sparse networks across different topologies is hard, but given that we've had a degree of success with pre-trained networks, pre-training and pre-pruning might also allow for sparse networks with minimally compromised learning capabilities.
If it's possible to pre-train composable network modules, it might also be feasible to define trainable sparse networks with significantly relaxed topological constraints.
-
How to run Llama 13B with a 6GB graphics card
Training uses gradient descent, so you want to have good precision during that process. But once you have the overall structure of the network, https://arxiv.org/abs/2210.17323 (GPTQ) showed that you can cut down the precision quite a bit without losing a lot of accuracy. It seems you can cut down further for larger models. For the 13B Llama-based ones, going below 5 bit per parameter is noticeably worse, but for 30B models you can do 4 bits.
The same group did another paper https://arxiv.org/abs/2301.00774 which shows that in addition to reducing the precision of each parameter, you can also prune out a bunch of parameters entirely. It's harder to apply this optimization because models are usually loaded into RAM densely, but I hope someone figures out how to do it for popular models.
- SparseGPT: Language Models Can Be Accurately Pruned in One-Shot
safetensors
-
Llamafile lets you distribute and run LLMs with a single file
The ML field is doing work in that area: https://github.com/huggingface/safetensors
-
Hugging Face raises $235M from investors including Salesforce and Nvidia
FYI the file format, safetensors, was proposed, developed and maintained by HF, and involved people from groups such as Eleuther and Stability for external security audits.
https://github.com/huggingface/safetensors https://huggingface.co/blog/safetensors-security-audit
-
I Made Stable Diffusion XL Smarter by Finetuning It on Bad AI-Generated Images
Thank you for note on this. I had not heard there were already trojan horse malware being slipped into tensor files as python scripts. Apparently torch pickle uses eval on the tensor file with no filter.
Heard surprisingly little commentary on this topic. The full explanation of how Safetensors are "Safe" can be found from the developer at: https://github.com/huggingface/safetensors/discussions/111
- Pickle safety in Python
-
What makes .safetensors files safe?
Here the developer goes into some detail about what kinds of protections .safetensor files have : https://github.com/huggingface/safetensors/discussions/111
-
Security PSA: huggingface models are code. not just data.
Use the safetensors format, which allows safe persistence and loading of models for common libraries - TensorFlow, PyTorch, JAX, etc. We went through external audits in the last few months (blog post). The current direction will be to have this as the default format.
- What's your favorite model. Right now I'm really enjoying dreamshaper.
- Lora, ggml, safetensors, hf, etc. Is there a glossary and guide on which model to choose?
-
Stability AI Launches the First of Its StableLM Suite of Language Models
I've been diving in lately and while it's not efficient, the only way to do manage is to create a new conda/mamba environment, or a custom Docker image for all the conflicting packages.
For safety and speed, you should prefer the safetensor format: https://huggingface.co/docs/safetensors/speed
If you know what you are doing you can do your own conversions: https://github.com/huggingface/safetensors or for safety, https://huggingface.co/spaces/diffusers/convert
-
CKPT to Safetensors
GitHub - huggingface/safetensors: Simple, safe way to store and distribute tensors
What are some alternatives?
StableLM - StableLM: Stability AI Language Models
stable-diffusion-webui - Stable Diffusion web UI
github-copilot-product-specific-terms
llama.cpp - LLM inference in C/C++
promptfoo - Test your prompts, models, and RAGs. Catch regressions and improve prompt quality. LLM evals for OpenAI, Azure, Anthropic, Gemini, Mistral, Llama, Bedrock, Ollama, and other local & private models with CI/CD integration.
Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI - Convert your Stable Diffusion checkpoints quickly and easily.
chat-ui - Open source codebase powering the HuggingChat app
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
intel-extension-for-pytorch - A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Stable-Diffusion-Pickle-Scanner-GUI - Pickle Scanner GUI
geov - The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER). We have shared a pre-trained 9B parameter model.
stable-diffusion-webui-model-toolkit - A Multipurpose toolkit for managing, editing and creating models.