Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
Thank you ZeroWw for the inspiration to experiment with embed/output
Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
You can either specify a new local-dir (c4ai-command-r-plus-08-2024-Q8_0) or download them all in place (./)
Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2
here
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are
not
compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
c4ai-command-r-plus-08-2024-GGUF huggingface.co is an AI model on huggingface.co that provides c4ai-command-r-plus-08-2024-GGUF's model effect (), which can be used instantly with this bartowski c4ai-command-r-plus-08-2024-GGUF model. huggingface.co supports a free trial of the c4ai-command-r-plus-08-2024-GGUF model, and also provides paid use of the c4ai-command-r-plus-08-2024-GGUF. Support call c4ai-command-r-plus-08-2024-GGUF model through api, including Node.js, Python, http.
c4ai-command-r-plus-08-2024-GGUF huggingface.co is an online trial and call api platform, which integrates c4ai-command-r-plus-08-2024-GGUF's modeling effects, including api services, and provides a free online trial of c4ai-command-r-plus-08-2024-GGUF, you can try c4ai-command-r-plus-08-2024-GGUF online for free by clicking the link below.
bartowski c4ai-command-r-plus-08-2024-GGUF online free url in huggingface.co:
c4ai-command-r-plus-08-2024-GGUF is an open source model from GitHub that offers a free installation service, and any user can find c4ai-command-r-plus-08-2024-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of c4ai-command-r-plus-08-2024-GGUF install, users can directly use c4ai-command-r-plus-08-2024-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
c4ai-command-r-plus-08-2024-GGUF install url in huggingface.co: