From 973709eafb61fb1d55be310a83d434f256e021ca Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 10 Sep 2026 00:28:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: bartowski/soob3123_Veritas-12B-GGUF Source: Original Platform --- .gitattributes | 49 ++++++++ README.md | 192 ++++++++++++++++++++++++++++++ configuration.json | 1 + soob3123_Veritas-12B-IQ2_M.gguf | 3 + soob3123_Veritas-12B-IQ2_S.gguf | 3 + soob3123_Veritas-12B-IQ3_M.gguf | 3 + soob3123_Veritas-12B-IQ3_XS.gguf | 3 + soob3123_Veritas-12B-IQ3_XXS.gguf | 3 + soob3123_Veritas-12B-IQ4_NL.gguf | 3 + soob3123_Veritas-12B-IQ4_XS.gguf | 3 + soob3123_Veritas-12B-Q2_K.gguf | 3 + soob3123_Veritas-12B-Q2_K_L.gguf | 3 + soob3123_Veritas-12B-Q3_K_L.gguf | 3 + soob3123_Veritas-12B-Q3_K_M.gguf | 3 + soob3123_Veritas-12B-Q3_K_S.gguf | 3 + soob3123_Veritas-12B-Q3_K_XL.gguf | 3 + soob3123_Veritas-12B-Q4_0.gguf | 3 + soob3123_Veritas-12B-Q4_1.gguf | 3 + soob3123_Veritas-12B-Q4_K_L.gguf | 3 + soob3123_Veritas-12B-Q4_K_M.gguf | 3 + soob3123_Veritas-12B-Q4_K_S.gguf | 3 + soob3123_Veritas-12B-Q5_K_L.gguf | 3 + soob3123_Veritas-12B-Q5_K_M.gguf | 3 + soob3123_Veritas-12B-Q5_K_S.gguf | 3 + soob3123_Veritas-12B-Q6_K.gguf | 3 + soob3123_Veritas-12B-Q6_K_L.gguf | 3 + soob3123_Veritas-12B-Q8_0.gguf | 3 + soob3123_Veritas-12B-bf16.gguf | 3 + soob3123_Veritas-12B.imatrix | 3 + 29 files changed, 320 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 configuration.json create mode 100644 soob3123_Veritas-12B-IQ2_M.gguf create mode 100644 soob3123_Veritas-12B-IQ2_S.gguf create mode 100644 soob3123_Veritas-12B-IQ3_M.gguf create mode 100644 soob3123_Veritas-12B-IQ3_XS.gguf create mode 100644 soob3123_Veritas-12B-IQ3_XXS.gguf create mode 100644 soob3123_Veritas-12B-IQ4_NL.gguf create mode 100644 soob3123_Veritas-12B-IQ4_XS.gguf create mode 100644 soob3123_Veritas-12B-Q2_K.gguf create mode 100644 soob3123_Veritas-12B-Q2_K_L.gguf create mode 100644 soob3123_Veritas-12B-Q3_K_L.gguf create mode 100644 soob3123_Veritas-12B-Q3_K_M.gguf create mode 100644 soob3123_Veritas-12B-Q3_K_S.gguf create mode 100644 soob3123_Veritas-12B-Q3_K_XL.gguf create mode 100644 soob3123_Veritas-12B-Q4_0.gguf create mode 100644 soob3123_Veritas-12B-Q4_1.gguf create mode 100644 soob3123_Veritas-12B-Q4_K_L.gguf create mode 100644 soob3123_Veritas-12B-Q4_K_M.gguf create mode 100644 soob3123_Veritas-12B-Q4_K_S.gguf create mode 100644 soob3123_Veritas-12B-Q5_K_L.gguf create mode 100644 soob3123_Veritas-12B-Q5_K_M.gguf create mode 100644 soob3123_Veritas-12B-Q5_K_S.gguf create mode 100644 soob3123_Veritas-12B-Q6_K.gguf create mode 100644 soob3123_Veritas-12B-Q6_K_L.gguf create mode 100644 soob3123_Veritas-12B-Q8_0.gguf create mode 100644 soob3123_Veritas-12B-bf16.gguf create mode 100644 soob3123_Veritas-12B.imatrix diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40f51a9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +soob3123_Veritas-12B.imatrix filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c4c54a --- /dev/null +++ b/README.md @@ -0,0 +1,192 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: soob3123/Veritas-12B +datasets: +- AiresPucrs/stanford-encyclopedia-philosophy +- debasisdwivedy/Dataset_Philosophy_Ethics_Morality +- joey234/mmlu-philosophy +tags: +- philosophy +- reasoning +- logic +- ethics +- metaphysics +- epistemology +- critical-thinking +- debate +- dialogue +- text-generation +- uncensored +thumbnail: '"https://cdn-uploads.huggingface.co/production/uploads/62f93f9477b722f1866398c2/IuhCq-5PcEbDBqXD5xnup.png"' +language: +- en +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Veritas-12B by soob3123 + +Using llama.cpp release b5173 for quantization. + +Original model: https://huggingface.co/soob3123/Veritas-12B + +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 + +``` +user +{system_prompt} + +{prompt} +model + +model +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Veritas-12B-bf16.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-bf16.gguf) | bf16 | 23.54GB | false | Full BF16 weights. | +| [Veritas-12B-Q8_0.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q8_0.gguf) | Q8_0 | 12.51GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Veritas-12B-Q6_K_L.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q6_K_L.gguf) | Q6_K_L | 9.90GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Veritas-12B-Q6_K.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q6_K.gguf) | Q6_K | 9.66GB | false | Very high quality, near perfect, *recommended*. | +| [Veritas-12B-Q5_K_L.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q5_K_L.gguf) | Q5_K_L | 8.69GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Veritas-12B-Q5_K_M.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q5_K_M.gguf) | Q5_K_M | 8.45GB | false | High quality, *recommended*. | +| [Veritas-12B-Q5_K_S.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q5_K_S.gguf) | Q5_K_S | 8.23GB | false | High quality, *recommended*. | +| [Veritas-12B-Q4_1.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q4_1.gguf) | Q4_1 | 7.56GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Veritas-12B-Q4_K_L.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q4_K_L.gguf) | Q4_K_L | 7.54GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Veritas-12B-Q4_K_M.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q4_K_M.gguf) | Q4_K_M | 7.30GB | false | Good quality, default size for most use cases, *recommended*. | +| [Veritas-12B-Q4_K_S.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q4_K_S.gguf) | Q4_K_S | 6.94GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Veritas-12B-Q4_0.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q4_0.gguf) | Q4_0 | 6.91GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Veritas-12B-IQ4_NL.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ4_NL.gguf) | IQ4_NL | 6.89GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Veritas-12B-Q3_K_XL.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q3_K_XL.gguf) | Q3_K_XL | 6.72GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Veritas-12B-IQ4_XS.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ4_XS.gguf) | IQ4_XS | 6.55GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Veritas-12B-Q3_K_L.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q3_K_L.gguf) | Q3_K_L | 6.48GB | false | Lower quality but usable, good for low RAM availability. | +| [Veritas-12B-Q3_K_M.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q3_K_M.gguf) | Q3_K_M | 6.01GB | false | Low quality. | +| [Veritas-12B-IQ3_M.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ3_M.gguf) | IQ3_M | 5.66GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Veritas-12B-Q3_K_S.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q3_K_S.gguf) | Q3_K_S | 5.46GB | false | Low quality, not recommended. | +| [Veritas-12B-IQ3_XS.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ3_XS.gguf) | IQ3_XS | 5.21GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Veritas-12B-Q2_K_L.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q2_K_L.gguf) | Q2_K_L | 5.01GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Veritas-12B-IQ3_XXS.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ3_XXS.gguf) | IQ3_XXS | 4.78GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Veritas-12B-Q2_K.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-Q2_K.gguf) | Q2_K | 4.77GB | false | Very low quality but surprisingly usable. | +| [Veritas-12B-IQ2_M.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ2_M.gguf) | IQ2_M | 4.31GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Veritas-12B-IQ2_S.gguf](https://huggingface.co/bartowski/soob3123_Veritas-12B-GGUF/blob/main/soob3123_Veritas-12B-IQ2_S.gguf) | IQ2_S | 4.02GB | false | Low quality, uses SOTA techniques to be 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/soob3123_Veritas-12B-GGUF --include "soob3123_Veritas-12B-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/soob3123_Veritas-12B-GGUF --include "soob3123_Veritas-12B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (soob3123_Veritas-12B-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/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/soob3123_Veritas-12B-IQ2_M.gguf b/soob3123_Veritas-12B-IQ2_M.gguf new file mode 100644 index 0000000..318d8a8 --- /dev/null +++ b/soob3123_Veritas-12B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d544d90853c30c8e71b4f698a522103bf5927f955d1479f5f4a03a3d91ec9989 +size 4310462144 diff --git a/soob3123_Veritas-12B-IQ2_S.gguf b/soob3123_Veritas-12B-IQ2_S.gguf new file mode 100644 index 0000000..b7edb30 --- /dev/null +++ b/soob3123_Veritas-12B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79715c5c20a3eeff32ebf9509021d83c50d28b5c7d21f7ca74788e5d88a62dd9 +size 4020711104 diff --git a/soob3123_Veritas-12B-IQ3_M.gguf b/soob3123_Veritas-12B-IQ3_M.gguf new file mode 100644 index 0000000..24411f6 --- /dev/null +++ b/soob3123_Veritas-12B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac39aa8217fab5c31f943b0a0cc67f0fae3e7c297f2156f4664532832e83acb +size 5655723584 diff --git a/soob3123_Veritas-12B-IQ3_XS.gguf b/soob3123_Veritas-12B-IQ3_XS.gguf new file mode 100644 index 0000000..778716a --- /dev/null +++ b/soob3123_Veritas-12B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4536fd4bce2d6df58434ae26b21c71ed39c8d997f6eca73ab02d7f647d46b54a +size 5206167104 diff --git a/soob3123_Veritas-12B-IQ3_XXS.gguf b/soob3123_Veritas-12B-IQ3_XXS.gguf new file mode 100644 index 0000000..9ef8301 --- /dev/null +++ b/soob3123_Veritas-12B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e324fca485403fc35e927536b2037e409e51e3f42f0f5bb8df21129ab76d19 +size 4784901824 diff --git a/soob3123_Veritas-12B-IQ4_NL.gguf b/soob3123_Veritas-12B-IQ4_NL.gguf new file mode 100644 index 0000000..7bb4dc9 --- /dev/null +++ b/soob3123_Veritas-12B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a187ef3c9eb4e5e1407a0358b177df953e727be4ede10820970cc32af53b331 +size 6887165504 diff --git a/soob3123_Veritas-12B-IQ4_XS.gguf b/soob3123_Veritas-12B-IQ4_XS.gguf new file mode 100644 index 0000000..a07a2c5 --- /dev/null +++ b/soob3123_Veritas-12B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c5f6aa0ee41c5fe9df6a115eb2b39ad67866d4a136e4995b9a8973d6567360 +size 6550965824 diff --git a/soob3123_Veritas-12B-Q2_K.gguf b/soob3123_Veritas-12B-Q2_K.gguf new file mode 100644 index 0000000..def4f17 --- /dev/null +++ b/soob3123_Veritas-12B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9230238a806d3246ba6084ad1ef3b8141298c837c58a4561a0c67b91dbd470fe +size 4768222784 diff --git a/soob3123_Veritas-12B-Q2_K_L.gguf b/soob3123_Veritas-12B-Q2_K_L.gguf new file mode 100644 index 0000000..be35bae --- /dev/null +++ b/soob3123_Veritas-12B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636876337ba472344904e62aca49d85d3482f6a714c0afd4d36a08414c37b885 +size 5012076224 diff --git a/soob3123_Veritas-12B-Q3_K_L.gguf b/soob3123_Veritas-12B-Q3_K_L.gguf new file mode 100644 index 0000000..4750184 --- /dev/null +++ b/soob3123_Veritas-12B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339c65390dd7c665f08f6498e3d32f33a19a066caa5aa846a9cae204cb5b136f +size 6480186944 diff --git a/soob3123_Veritas-12B-Q3_K_M.gguf b/soob3123_Veritas-12B-Q3_K_M.gguf new file mode 100644 index 0000000..1f94cc4 --- /dev/null +++ b/soob3123_Veritas-12B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27df1bcd2dc3605d6ce12f80273af865ce137364d713aa5d4a5e3e6a328eb287 +size 6008819264 diff --git a/soob3123_Veritas-12B-Q3_K_S.gguf b/soob3123_Veritas-12B-Q3_K_S.gguf new file mode 100644 index 0000000..6a500ab --- /dev/null +++ b/soob3123_Veritas-12B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f7815014a3316cfa79f96c0ae7d430c4f5483011fd049723ed48ce7453cec3 +size 5458316864 diff --git a/soob3123_Veritas-12B-Q3_K_XL.gguf b/soob3123_Veritas-12B-Q3_K_XL.gguf new file mode 100644 index 0000000..1258704 --- /dev/null +++ b/soob3123_Veritas-12B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85778271315419d487bf7c68efdb2fded5cd8f48cbe9db080425b8737d5e020b +size 6724040384 diff --git a/soob3123_Veritas-12B-Q4_0.gguf b/soob3123_Veritas-12B-Q4_0.gguf new file mode 100644 index 0000000..7c12018 --- /dev/null +++ b/soob3123_Veritas-12B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc54822815131b3d4a4941d030579e562d48407e96e743d675754a09c9b8f6b7 +size 6909283904 diff --git a/soob3123_Veritas-12B-Q4_1.gguf b/soob3123_Veritas-12B-Q4_1.gguf new file mode 100644 index 0000000..7f0396d --- /dev/null +++ b/soob3123_Veritas-12B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a711b895647076ce8c19aef4ad2e6d3b50ebb6a97ca4405aebc931f62e69a194 +size 7559564864 diff --git a/soob3123_Veritas-12B-Q4_K_L.gguf b/soob3123_Veritas-12B-Q4_K_L.gguf new file mode 100644 index 0000000..bf05686 --- /dev/null +++ b/soob3123_Veritas-12B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e116aa277758ff5e4a8ae78e3a5dfb3320931c798d59e314bd53480d8ee64e2 +size 7544633024 diff --git a/soob3123_Veritas-12B-Q4_K_M.gguf b/soob3123_Veritas-12B-Q4_K_M.gguf new file mode 100644 index 0000000..c1f6b38 --- /dev/null +++ b/soob3123_Veritas-12B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41821d6b0dd2b81a5bddd843a5534fd64d95e75b8e9dc952340868af320d49a7 +size 7300779584 diff --git a/soob3123_Veritas-12B-Q4_K_S.gguf b/soob3123_Veritas-12B-Q4_K_S.gguf new file mode 100644 index 0000000..47501ef --- /dev/null +++ b/soob3123_Veritas-12B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc577b11877dc6777bcafd0fc0ff0c7cc3f1cdc5dceada64a61f8f19f662399d +size 6935334464 diff --git a/soob3123_Veritas-12B-Q5_K_L.gguf b/soob3123_Veritas-12B-Q5_K_L.gguf new file mode 100644 index 0000000..c614050 --- /dev/null +++ b/soob3123_Veritas-12B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753dcdcbb2707b5b06d94023a4ff0fe51b6a81839dd3008e39c9f2dc0d985352 +size 8688891584 diff --git a/soob3123_Veritas-12B-Q5_K_M.gguf b/soob3123_Veritas-12B-Q5_K_M.gguf new file mode 100644 index 0000000..301e119 --- /dev/null +++ b/soob3123_Veritas-12B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d84ac9f194516b79d36f3ca3efd81951f3c065ec92f00c23ed92ecbda1ce75b +size 8445038144 diff --git a/soob3123_Veritas-12B-Q5_K_S.gguf b/soob3123_Veritas-12B-Q5_K_S.gguf new file mode 100644 index 0000000..ce506ff --- /dev/null +++ b/soob3123_Veritas-12B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9fb8a0ffd09d5598e27499b64f232829608e03b1eade250423e76eaa3e0fba +size 8231964224 diff --git a/soob3123_Veritas-12B-Q6_K.gguf b/soob3123_Veritas-12B-Q6_K.gguf new file mode 100644 index 0000000..21a7c11 --- /dev/null +++ b/soob3123_Veritas-12B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05796645c04b1e39967b19bb7fc5162feb4da82aad57e9282bc4fb23b0b3ceae +size 9660812864 diff --git a/soob3123_Veritas-12B-Q6_K_L.gguf b/soob3123_Veritas-12B-Q6_K_L.gguf new file mode 100644 index 0000000..c8a215c --- /dev/null +++ b/soob3123_Veritas-12B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04a63b15b49899df14fe859d6ec194eeb9e901a71bec5b9fe6c9f9fde92006b +size 9904666304 diff --git a/soob3123_Veritas-12B-Q8_0.gguf b/soob3123_Veritas-12B-Q8_0.gguf new file mode 100644 index 0000000..c8cbd35 --- /dev/null +++ b/soob3123_Veritas-12B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd39ae3a6aa189b6dea2085be2bb520bbccd8f95563fb79f9b8fe4038a4b2e6 +size 12510213824 diff --git a/soob3123_Veritas-12B-bf16.gguf b/soob3123_Veritas-12B-bf16.gguf new file mode 100644 index 0000000..77c8857 --- /dev/null +++ b/soob3123_Veritas-12B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7680cbfbfaf35b49f1f0764f302064b3b412431044174082a4c83a2d6ba0848e +size 23540152736 diff --git a/soob3123_Veritas-12B.imatrix b/soob3123_Veritas-12B.imatrix new file mode 100644 index 0000000..6ea405f --- /dev/null +++ b/soob3123_Veritas-12B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5472231aeb777f44e90fd18372732df93d8c6af026f98abfe3242f1b53c14c2c +size 7433114