commit b1b905b2e5bba4212c92d4e0d80f93dfde5dd8f5 Author: ModelHub XC Date: Thu Jul 30 06:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed957f7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0-bf16.gguf filter=lfs diff=lfs merge=lfs -text +ReadyArt_The-Omega-Directive-M-12B-v1.0.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8df0180 --- /dev/null +++ b/README.md @@ -0,0 +1,176 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: apache-2.0 +tags: +- nsfw +- explicit +- roleplay +- unaligned +- dangerous +- ERP +base_model: ReadyArt/The-Omega-Directive-M-12B-v1.0 +language: +- en +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of The-Omega-Directive-M-12B-v1.0 by ReadyArt + +Using llama.cpp release b5064 for quantization. + +Original model: https://huggingface.co/ReadyArt/The-Omega-Directive-M-12B-v1.0 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +[INST]{prompt}[/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [The-Omega-Directive-M-12B-v1.0-bf16.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-bf16.gguf) | bf16 | 24.50GB | false | Full BF16 weights. | +| [The-Omega-Directive-M-12B-v1.0-Q8_0.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. | +| [The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q6_K.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K.gguf) | Q6_K | 10.06GB | false | Very high quality, near perfect, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf) | Q5_K_L | 9.14GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf) | Q5_K_M | 8.73GB | false | High quality, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf) | Q5_K_S | 8.52GB | false | High quality, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf) | Q4_K_L | 7.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q4_1.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_1.gguf) | Q4_1 | 7.80GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf) | Q4_K_M | 7.48GB | false | Good quality, default size for most use cases, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf) | IQ4_NL | 7.10GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [The-Omega-Directive-M-12B-v1.0-Q4_0.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. | +| [The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. | +| [The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf) | IQ3_M | 5.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf) | Q3_K_S | 5.53GB | false | Low quality, not recommended. | +| [The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf) | Q2_K_L | 5.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf) | IQ3_XS | 5.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf) | IQ3_XXS | 4.95GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [The-Omega-Directive-M-12B-v1.0-Q2_K.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K.gguf) | Q2_K | 4.79GB | false | Very low quality but surprisingly usable. | +| [The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf](https://huggingface.co/bartowski/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF/blob/main/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf) | IQ2_M | 4.44GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## 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. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +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/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF --include "ReadyArt_The-Omega-Directive-M-12B-v1.0-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/ReadyArt_The-Omega-Directive-M-12B-v1.0-GGUF --include "ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +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](https://github.com/ggerganov/llama.cpp/wiki/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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## 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. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf new file mode 100644 index 0000000..68c782b --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e660614781449f39482ed3c6320cb16e3208c532365f20f857b63e2a031685a5 +size 4435027136 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf new file mode 100644 index 0000000..3760441 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10a8378122aea71c50cc840d83ef7e13ad29198f3686b52f9c7e57e0aabe049 +size 5722236096 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf new file mode 100644 index 0000000..cfd5b60 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39782297495bebd8400ebc8e583eaeca9dc696f3eba162cb6c7127cf985c2e46 +size 5306492096 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf new file mode 100644 index 0000000..fd99658 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5644230431a2ab7c3f001d5c3e976e5f3dbc51f99a82adfe8d1b12cc10ef4c48 +size 4945388736 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf new file mode 100644 index 0000000..cc15a40 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3199af1f86ec5c35b0a06eb83f054735f6e2e0612978f7e1e8afcc0b1fc60f72 +size 7097918656 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf new file mode 100644 index 0000000..5df9ef5 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15d02aa956bd729fb691fbe0b5533a6ce7ab1d6b9727175f37ecdf15b162cd5 +size 6742713536 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K.gguf new file mode 100644 index 0000000..49f2ebe --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2037056201b7aeda70784e8ec1d9f4344599017689f5efbd81d2a2f293ecd9 +size 4791051456 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf new file mode 100644 index 0000000..5c9cf0b --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2194546644f316b5afecc8b39152f4cdecbb1bae45fe480ba962c30455786a08 +size 5446411456 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf new file mode 100644 index 0000000..cba6d15 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b932c221708772d5b8045c95534dcd982ca4e7268186836ea01ec0cc55533b3 +size 6561506496 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf new file mode 100644 index 0000000..3586b31 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641713a3494a63ee59c7d51ee00b94d41ac5e0f9a3798c6e10e361a1e80c0cdd +size 6083093696 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf new file mode 100644 index 0000000..6df7cca --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870fe87c301f8e350a4bd29cd8c12263d9e921c77eeee5da54cccacf6a619daf +size 5534229696 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf new file mode 100644 index 0000000..d946d66 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eff9827831d488c8c578dfdb8d3f7fa8ebd51a26889d73420c9eb9955ced8da +size 7148709056 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_0.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_0.gguf new file mode 100644 index 0000000..79618b8 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe2e27868a3a20d03aea26dc8a10a9a5ef0f36ba21c0818f32dab75e7a45bbe +size 7094641856 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_1.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_1.gguf new file mode 100644 index 0000000..ecbe8de --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a873c05e4abdc725a22e9b4ba411d069af3b3726ade671b71209575734c1195a +size 7795221696 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf new file mode 100644 index 0000000..6e07b71 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362cbcbfe0fe83a7433327e41dcb39d313b8c7b9812a18a8b843396a12f11978 +size 7975281856 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf new file mode 100644 index 0000000..a34ae04 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecbee51fdef1ca5f5a4dbfc7c66eda0e26541eb5cec1cd1de5e2074f1dff604 +size 7477208256 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf new file mode 100644 index 0000000..1fd6135 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2e074ea7a4eecf8328a23835ce72f98fbc60531dac78ec85558462c205729c +size 7120200896 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf new file mode 100644 index 0000000..a915685 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4a901625b5417c5e8de53fccb803e7ef6e93502d2a551faa1e5f330b4a4f19 +size 9141822656 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf new file mode 100644 index 0000000..df3a19c --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7df564b539745e92f4caa16f281aabd0c935941b99b3474b7a57722bf038cd55 +size 8727635136 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf new file mode 100644 index 0000000..d123eb4 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01207d8b0bc00abd3355aadd0f01d63d82de4c8afc91d557712bcbc7287d7c36 +size 8518739136 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K.gguf new file mode 100644 index 0000000..667ed53 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79845bd6d418b6816b1ebbf52e62f3442e9da0738a3dcd2623c7ce5effd2edb +size 10056213696 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf new file mode 100644 index 0000000..9e3afdc --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5822395a995056cd921cd1cd588f73cce3390a5ce34d64d5749463e35070f212 +size 10381272256 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0.gguf new file mode 100644 index 0000000..192c0e0 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f18446c425bbeb1e85e57e4374918f03b2e0cfdb1b6b70bd872ff10e065939 +size 13022373056 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0-bf16.gguf b/ReadyArt_The-Omega-Directive-M-12B-v1.0-bf16.gguf new file mode 100644 index 0000000..7f16c78 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a6429997dfb3458f2b7437954cd3b055a206e3d9fef53664e5cf365ecf0ac0 +size 24504279968 diff --git a/ReadyArt_The-Omega-Directive-M-12B-v1.0.imatrix b/ReadyArt_The-Omega-Directive-M-12B-v1.0.imatrix new file mode 100644 index 0000000..4384c27 --- /dev/null +++ b/ReadyArt_The-Omega-Directive-M-12B-v1.0.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671eb06f9b7f6bcfe8f86526e6e5ec3187809a6393e65042776388a803a12565 +size 7054418