commit b91fd7d50d3e5c9bf8554aa7d7039a36588f6d0b Author: ModelHub XC Date: Mon Jul 13 04:02:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5de60e8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,75 @@ +*.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 + +*.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 + +TheDrummer_Magidonia-24B-v4.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-bf16.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Magidonia-24B-v4.3-Q4_1.gguf 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..673a7d3 --- /dev/null +++ b/README.md @@ -0,0 +1,168 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: TheDrummer/Magidonia-24B-v4.3 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Magidonia-24B-v4.3 by TheDrummer + +Using llama.cpp release b7306 for quantization. + +Original model: https://huggingface.co/TheDrummer/Magidonia-24B-v4.3 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Magidonia-24B-v4.3-bf16.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. | +| [Magidonia-24B-v4.3-Q8_0.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Magidonia-24B-v4.3-Q6_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Magidonia-24B-v4.3-Q6_K.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. | +| [Magidonia-24B-v4.3-Q5_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Magidonia-24B-v4.3-Q5_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. | +| [Magidonia-24B-v4.3-Q5_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. | +| [Magidonia-24B-v4.3-Q4_1.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Magidonia-24B-v4.3-Q4_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Magidonia-24B-v4.3-Q4_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. | +| [Magidonia-24B-v4.3-Q4_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Magidonia-24B-v4.3-Q4_0.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Magidonia-24B-v4.3-IQ4_NL.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Magidonia-24B-v4.3-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q3_K_XL.gguf) | Q3_K_XL | 12.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Magidonia-24B-v4.3-IQ4_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Magidonia-24B-v4.3-Q3_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. | +| [Magidonia-24B-v4.3-Q3_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. | +| [Magidonia-24B-v4.3-IQ3_M.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Magidonia-24B-v4.3-Q3_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. | +| [Magidonia-24B-v4.3-IQ3_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Magidonia-24B-v4.3-Q2_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Magidonia-24B-v4.3-IQ3_XXS.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Magidonia-24B-v4.3-Q2_K.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. | +| [Magidonia-24B-v4.3-IQ2_M.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Magidonia-24B-v4.3-IQ2_S.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. | +| [Magidonia-24B-v4.3-IQ2_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Magidonia-24B-v4.3-GGUF/blob/main/TheDrummer_Magidonia-24B-v4.3-IQ2_XS.gguf) | IQ2_XS | 7.21GB | 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/TheDrummer_Magidonia-24B-v4.3-GGUF --include "TheDrummer_Magidonia-24B-v4.3-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/TheDrummer_Magidonia-24B-v4.3-GGUF --include "TheDrummer_Magidonia-24B-v4.3-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (TheDrummer_Magidonia-24B-v4.3-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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/TheDrummer_Magidonia-24B-v4.3-IQ2_M.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ2_M.gguf new file mode 100644 index 0000000..e06364d --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c2c7741ad83d430abb9867c834b3750f197fd2c4332849a3fb0a62268e1e80 +size 8114054560 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ2_S.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ2_S.gguf new file mode 100644 index 0000000..9c890ac --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba73a9f87bcbf632be6e4f1c16ab8c59c51050df4d906cf1ff1a45eef7bfb0fe +size 7478355360 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ2_XS.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ2_XS.gguf new file mode 100644 index 0000000..5d260b3 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6022de0c8cebd6ab483eacca0c00817a6b7028243421f7daacc05dd88235234c +size 7207036320 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ3_M.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ3_M.gguf new file mode 100644 index 0000000..bc468d5 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748117301a4c587715b8275b3b37ea0d8ae96d264cbb23f6d3eaaa39d8f3d312 +size 10650953120 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ3_XS.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ3_XS.gguf new file mode 100644 index 0000000..0c97295 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ea2cb28ef5c45c18480e0936c8f43a8f13d2a304f5007b5ac927e4302d54c6 +size 9907119520 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ3_XXS.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ3_XXS.gguf new file mode 100644 index 0000000..af2a056 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff896b9114e3121db9f00328cf16a464ad920590ace16ba6868d1bd89d6ecdf +size 9280595360 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ4_NL.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ4_NL.gguf new file mode 100644 index 0000000..67893a0 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f5c6fe7be7ff9e4b09eedca86833a71995bdeacc63db71d54f7d13aa8db048 +size 13468018080 diff --git a/TheDrummer_Magidonia-24B-v4.3-IQ4_XS.gguf b/TheDrummer_Magidonia-24B-v4.3-IQ4_XS.gguf new file mode 100644 index 0000000..82f9fbb --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25071c3ef24574924201cbae422bf20415129db85efb025e9d73cb22e5ad873 +size 12758918560 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q2_K.gguf b/TheDrummer_Magidonia-24B-v4.3-Q2_K.gguf new file mode 100644 index 0000000..337a301 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04c614faa59a00b5f8659a28ec801779d6a00948862c2e0aeddcf4ab3d129182 +size 8890328480 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q2_K_L.gguf b/TheDrummer_Magidonia-24B-v4.3-Q2_K_L.gguf new file mode 100644 index 0000000..821f8a9 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989843df555cadcda7a798b30372ddbe83dd4449fb6d1f0abfb6ac3525d3928c +size 9545688480 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q3_K_L.gguf b/TheDrummer_Magidonia-24B-v4.3-Q3_K_L.gguf new file mode 100644 index 0000000..c2d71d5 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9744e846b4b6123d12bd2a12a25280afee29273d21b067799a8e8e40e9b0c087 +size 12400764320 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q3_K_M.gguf b/TheDrummer_Magidonia-24B-v4.3-Q3_K_M.gguf new file mode 100644 index 0000000..b60e2a9 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad61e2bc8f650c6459552f93ca9ec40537579cf4e2de2ba6ea4c22cce40125a +size 11474085280 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q3_K_S.gguf b/TheDrummer_Magidonia-24B-v4.3-Q3_K_S.gguf new file mode 100644 index 0000000..fa6af17 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9d90bb7de06c33781490f87433526dbb99d5448540c581946b58ca240ad425 +size 10400277920 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q3_K_XL.gguf b/TheDrummer_Magidonia-24B-v4.3-Q3_K_XL.gguf new file mode 100644 index 0000000..5a3d3f0 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0addc38e13e5af287efc45435059500fab868f813aff8be2391bfae4965a932 +size 12987966880 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q4_0.gguf b/TheDrummer_Magidonia-24B-v4.3-Q4_0.gguf new file mode 100644 index 0000000..f6f29ff --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea8c0d4455f8c613f5152cb509352fea53e90ddbd2af46798845a76a99269d3 +size 13494232480 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q4_1.gguf b/TheDrummer_Magidonia-24B-v4.3-Q4_1.gguf new file mode 100644 index 0000000..2a67a61 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4269a806ac91f925bfdb7abbfb65fca07c98c98eb1d0f08181c30a5d69d06a2 +size 14873109920 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q4_K_L.gguf b/TheDrummer_Magidonia-24B-v4.3-Q4_K_L.gguf new file mode 100644 index 0000000..012981a --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946795142185004da5fb242797a2f482a61b73c334b49ad7e7e86d55c5d53707 +size 14831986080 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q4_K_M.gguf b/TheDrummer_Magidonia-24B-v4.3-Q4_K_M.gguf new file mode 100644 index 0000000..b120c8c --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50fb55038172e5b2f4cd1f7a4d3acd01b9e076ab92f0aa3febba1336f870b3e9 +size 14333912480 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q4_K_S.gguf b/TheDrummer_Magidonia-24B-v4.3-Q4_K_S.gguf new file mode 100644 index 0000000..148c8c8 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9483081375577af9fe9d097ec4be5fb87dd9c6c699e6094c550fe4977d54c0c3 +size 13549282720 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q5_K_L.gguf b/TheDrummer_Magidonia-24B-v4.3-Q5_K_L.gguf new file mode 100644 index 0000000..060acf6 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196ed1553aac046e6922360a47ffb53aea3b2613bd81c9d6269512ebd70b833d +size 17178174880 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q5_K_M.gguf b/TheDrummer_Magidonia-24B-v4.3-Q5_K_M.gguf new file mode 100644 index 0000000..372f14e --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc6ae29e2c33d09963436d1924c8e3ed258bbb55ff956fdf309fc167f23f3f0 +size 16763987360 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q5_K_S.gguf b/TheDrummer_Magidonia-24B-v4.3-Q5_K_S.gguf new file mode 100644 index 0000000..314cd0d --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c1c603f9455586b135d392e944d36e94c3b0a4f52e952a20a7e62def33b83d +size 16304416160 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q6_K.gguf b/TheDrummer_Magidonia-24B-v4.3-Q6_K.gguf new file mode 100644 index 0000000..0cc6e5e --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2a309550ad694cf1a8f407c2e057edfe8eaf08ea4b9903ff9a39dd054be4b9 +size 19345941920 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q6_K_L.gguf b/TheDrummer_Magidonia-24B-v4.3-Q6_K_L.gguf new file mode 100644 index 0000000..57ebe7f --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4899f0b72f580ea146c3f7464abe250eea926ab979658f51a601b37286362864 +size 19671000480 diff --git a/TheDrummer_Magidonia-24B-v4.3-Q8_0.gguf b/TheDrummer_Magidonia-24B-v4.3-Q8_0.gguf new file mode 100644 index 0000000..90605e9 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f4a0cacc4e5437541ab4faaf220723e337e2460f0cf672caac45fafc63d3c2 +size 25054782880 diff --git a/TheDrummer_Magidonia-24B-v4.3-bf16.gguf b/TheDrummer_Magidonia-24B-v4.3-bf16.gguf new file mode 100644 index 0000000..3ef98ff --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa899f76f3dfd3982d0fcb58a65022b6c30bbd31ec4467e39cad259a747220d +size 47153521760 diff --git a/TheDrummer_Magidonia-24B-v4.3-imatrix.gguf b/TheDrummer_Magidonia-24B-v4.3-imatrix.gguf new file mode 100644 index 0000000..8d12d00 --- /dev/null +++ b/TheDrummer_Magidonia-24B-v4.3-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020fbcd0dc157fe39f18b53611ab2b7845eb82f55484344396905672bb0064c2 +size 10037344 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