llama-cpu
Fork of Facebooks LLaMa model to run on CPU (by markasoftware)
fickling
A Python pickling decompiler and static analyzer (by trailofbits)
| llama-cpu | fickling | |
|---|---|---|
| 9 | 7 | |
| 775 | 331 | |
| - | 5.1% | |
| 3.1 | 8.4 | |
| about 1 year ago | 4 days ago | |
| Python | Python | |
| GNU General Public License v3.0 only | GNU Lesser General Public License v3.0 only |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
llama-cpu
Posts with mentions or reviews of llama-cpu.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-03-08.
-
Why is ChatGPT 3.5 API 10x cheaper than GPT3?
You've probably heard, but LLaMA just released, and its 13B parameter model outperforms GPT-3 on most metrics (because they trained it on a lot more data). Someone's already quantized it to 4 and 3 bits and it performs virtually the same. It also apparently performs well on CPUs (several words per second on a 7900X). Running something equivalent to GPT3.5 on a phone is not out that far out.
- Fork of Facebook’s LLaMa model to run on CPU
- Llama-CPU: Fork of Facebooks LLaMa model to run on CPU
-
[D] Tutorial: Run LLaMA on 8gb vram on windows (thanks to bitsandbytes 8bit quantization)
I tried to port the llama-cpu version to a gpu-accelerated mps version for macs, it runs, but the outputs are not as good as expected and it often gives "-1" tokens. Any help and contributions on fixing it are welcome!
-
Facebook LLAMA is being openly distributed via torrents | Hacker News
You can run it with only a CPU and 32 gigs of RAM: https://github.com/markasoftware/llama-cpu
- [D] Is it possible to run Meta's LLaMA 65B model on consumer-grade hardware?
-
Facebook LLAMA is being openly distributed via torrents
I was able to run 7B on a CPU, inferring several words per second: https://github.com/markasoftware/llama-cpu
fickling
Posts with mentions or reviews of fickling.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-30.
- Fickling – A Python pickling decompiler and static analyzer
- ⚠️WARNING⚠️ never open a .ckpt file without knowing exactly what's inside (especially SDXL)
-
Facebook LLAMA is being openly distributed via torrents
You're right! You should probably use Trail of Bits Fickling tool to investigate. https://github.com/trailofbits/fickling
-
Safety of downloading random checkpoints
I tested the Anything V3 pruned from Hugging Face, and indeed nothing funny in its pickle. I used the Fickling library to decompile it. I do not use Windows so my interests in .ckpt security are largely related to Pickle exploits— which could extract malicious code from a data file and then do something with it, but the data files themselves are not executed. I will edit this comment with lines referencing that data file.
-
Draw Things, Stable Diffusion in your pocket, 100% offline and free
I've been using Diffusion Bee on my Mac, and it's just gained the ability to import models (which it converts), but it is unpickling to do so— but barely. It unpickles, figures out what sort of data is in every data file and then computes what it wants from them on its own. I would love it to not use unpickling at all, so my intention is if I can figure it out, to write a script to decode the pickle file (with Fickling or otherwise) and then just do the weight calculation/assignment.
- Novel AI models allegedly leaked.
-
Never a dill moment: Exploiting machine learning pickle files
Something you won't gather from skim-reading the headline is that this is that the author has also created a tool, Fickling: https://github.com/trailofbits/fickling - to aid in playing around with pickle files.
From the article: [Fickling] can help you reverse engineer, test, and even create malicious pickle files.
What are some alternatives?
When comparing llama-cpu and fickling you can also consider the following projects:
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
swift-diffusion
llama - Inference code for Llama models
diffusionbee-stable-diffusion-ui - Diffusion Bee
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
safer_unpickle
wrapyfi-examples_llama - Inference code for facebook LLaMA models with Wrapyfi support
sd-webui-model-converter - model convert extension for stable-diffusion-webui. supports convert fp16/bf16 no-ema/ema-only safetensors
bitsandbytes-win-prebuilt
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
FlexGen - Running large language models on a single GPU for throughput-oriented scenarios.
KoboldAI-Client
llama-cpu vs text-generation-webui
fickling vs swift-diffusion
llama-cpu vs llama
fickling vs diffusionbee-stable-diffusion-ui
llama-cpu vs GPTQ-for-LLaMa
fickling vs safer_unpickle
llama-cpu vs wrapyfi-examples_llama
fickling vs sd-webui-model-converter
llama-cpu vs bitsandbytes-win-prebuilt
llama-cpu vs transformers
llama-cpu vs FlexGen
llama-cpu vs KoboldAI-Client