bartowski / c4ai-command-r-plus-08-2024-GGUF

huggingface.co
Total runs: 5.3K
24-hour runs: 691
7-day runs: 3.0K
30-day runs: 3.9K
Model's Last Updated: Agosto 30 2024
text-generation

Introduction of c4ai-command-r-plus-08-2024-GGUF

Model Details of c4ai-command-r-plus-08-2024-GGUF

Llamacpp imatrix Quantizations of c4ai-command-r-plus-08-2024

Using llama.cpp release b3634 for quantization.

Original model: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024

All quants made using imatrix option with dataset from here

Run them in LM Studio

Prompt format
<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
Download a file (not the whole branch) from below:
Filename Quant type File Size Split Description
c4ai-command-r-plus-08-2024-Q8_0.gguf Q8_0 110.31GB true Extremely high quality, generally unneeded but max available quant.
c4ai-command-r-plus-08-2024-Q6_K.gguf Q6_K 85.17GB true Very high quality, near perfect, recommended .
c4ai-command-r-plus-08-2024-Q5_K_M.gguf Q5_K_M 73.62GB true High quality, recommended .
c4ai-command-r-plus-08-2024-Q4_K_L.gguf Q4_K_L 63.51GB true Uses Q8_0 for embed and output weights. Good quality, recommended .
c4ai-command-r-plus-08-2024-Q4_K_M.gguf Q4_K_M 62.75GB true Good quality, default size for must use cases, recommended .
c4ai-command-r-plus-08-2024-Q4_K_S.gguf Q4_K_S 59.64GB true Slightly lower quality with more space savings, recommended .
c4ai-command-r-plus-08-2024-Q4_0.gguf Q4_0 59.43GB true Legacy format, generally not worth using over similarly sized formats
c4ai-command-r-plus-08-2024-Q4_0_4_8.gguf Q4_0_4_8 59.22GB true Optimized for ARM and CPU inference, much faster than Q4_0 at similar quality.
c4ai-command-r-plus-08-2024-Q4_0_4_4.gguf Q4_0_4_4 59.22GB true Optimized for ARM and CPU inference, much faster than Q4_0 at similar quality.
c4ai-command-r-plus-08-2024-IQ4_XS.gguf IQ4_XS 56.20GB true Decent quality, smaller than Q4_K_S with similar performance, recommended .
c4ai-command-r-plus-08-2024-Q3_K_XL.gguf Q3_K_XL 56.16GB true Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
c4ai-command-r-plus-08-2024-Q3_K_L.gguf Q3_K_L 55.40GB true Lower quality but usable, good for low RAM availability.
c4ai-command-r-plus-08-2024-Q3_K_M.gguf Q3_K_M 50.98GB true Low quality.
c4ai-command-r-plus-08-2024-IQ3_M.gguf IQ3_M 47.68GB false Medium-low quality, new method with decent performance comparable to Q3_K_M.
c4ai-command-r-plus-08-2024-Q3_K_S.gguf Q3_K_S 45.85GB false Low quality, not recommended.
c4ai-command-r-plus-08-2024-IQ3_XXS.gguf IQ3_XXS 40.66GB false Lower quality, new method with decent performance, comparable to Q3 quants.
c4ai-command-r-plus-08-2024-Q2_K_L.gguf Q2_K_L 40.26GB false Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
c4ai-command-r-plus-08-2024-Q2_K.gguf Q2_K 39.50GB false Very low quality but surprisingly usable.
c4ai-command-r-plus-08-2024-IQ2_M.gguf IQ2_M 36.04GB false Relatively low quality, uses SOTA techniques to be surprisingly usable.
c4ai-command-r-plus-08-2024-IQ2_XS.gguf IQ2_XS 31.63GB false Low quality, uses SOTA techniques to be usable.
c4ai-command-r-plus-08-2024-IQ2_XXS.gguf IQ2_XXS 28.61GB false Very low quality, uses SOTA techniques to be usable.
c4ai-command-r-plus-08-2024-IQ1_M.gguf IQ1_M 25.22GB false Extremely low quality, not recommended.
Embed/output weights

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:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/c4ai-command-r-plus-08-2024-GGUF --include "c4ai-command-r-plus-08-2024-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/c4ai-command-r-plus-08-2024-GGUF --include "c4ai-command-r-plus-08-2024-Q8_0/*" --local-dir ./

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:

llama.cpp feature matrix

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.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Runs of bartowski c4ai-command-r-plus-08-2024-GGUF on huggingface.co

5.3K
Total runs
691
24-hour runs
2.6K
3-day runs
3.0K
7-day runs
3.9K
30-day runs

More Information About c4ai-command-r-plus-08-2024-GGUF huggingface.co Model

More c4ai-command-r-plus-08-2024-GGUF license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

c4ai-command-r-plus-08-2024-GGUF huggingface.co

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 Url

https://huggingface.co/bartowski/c4ai-command-r-plus-08-2024-GGUF

bartowski c4ai-command-r-plus-08-2024-GGUF online free

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:

https://huggingface.co/bartowski/c4ai-command-r-plus-08-2024-GGUF

c4ai-command-r-plus-08-2024-GGUF install

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:

https://huggingface.co/bartowski/c4ai-command-r-plus-08-2024-GGUF

Url of c4ai-command-r-plus-08-2024-GGUF

c4ai-command-r-plus-08-2024-GGUF huggingface.co Url

Provider of c4ai-command-r-plus-08-2024-GGUF huggingface.co

bartowski
ORGANIZATIONS

Other API from bartowski

huggingface.co

Total runs: 53.6K
Run Growth: 0
Growth Rate: 0.00%
Updated: Janeiro 11 2025