commit fd17655f22014bacacc076acdfc09860c55494af Author: ModelHub XC Date: Wed Sep 2 19:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c106b79 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,74 @@ +*.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 + +lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.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..ff59dd1 --- /dev/null +++ b/README.md @@ -0,0 +1,165 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: lemon07r/VellumMini-0.1-Qwen3-14B +--- + +## Llamacpp imatrix Quantizations of VellumMini-0.1-Qwen3-14B by lemon07r + +Using llama.cpp release b6683 for quantization. + +Original model: https://huggingface.co/lemon07r/VellumMini-0.1-Qwen3-14B + +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 + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [VellumMini-0.1-Qwen3-14B-bf16.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. | +| [VellumMini-0.1-Qwen3-14B-Q8_0.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. | +| [VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q6_K.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q4_1.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q4_0.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. | +| [VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. | +| [VellumMini-0.1-Qwen3-14B-IQ3_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. | +| [VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [VellumMini-0.1-Qwen3-14B-Q2_K.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. | +| [VellumMini-0.1-Qwen3-14B-IQ2_M.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [VellumMini-0.1-Qwen3-14B-IQ2_S.gguf](https://huggingface.co/bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF/blob/main/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf) | IQ2_S | 4.96GB | 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/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF --include "lemon07r_VellumMini-0.1-Qwen3-14B-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/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF --include "lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (lemon07r_VellumMini-0.1-Qwen3-14B-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/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/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf new file mode 100644 index 0000000..1213c37 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e77254921cd28cc6b7f97d2dc911cdb4099ce40276d621a57c08d6956b8d7da +size 5322941568 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf new file mode 100644 index 0000000..3c89bad --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36580a9748aaf86ee267135ee1c92db1de6c93d7d5fb977769e2be2661b04b7 +size 4963312768 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf new file mode 100644 index 0000000..54b8d65 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c861703386165acdc5a6e836e37c8de58907288fa5b0566749df425570b68701 +size 6883410048 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf new file mode 100644 index 0000000..b0870c5 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3596f0794fb47a2a9d1347c721b4f87852d839022b26a200da4040ec2584d36 +size 6375301248 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf new file mode 100644 index 0000000..77999fd --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7ef5a0997372dfe9c744877536a5807ce7cbc168f4713a066079ff0f25b27b1 +size 5942666368 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf new file mode 100644 index 0000000..9ea44d2 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e2fcefe0a6d2cdbc1337c2890ae17112ed3c3513e005f0fce749907facd08e +size 8541363328 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf new file mode 100644 index 0000000..afb4a8f --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862d2611e71da538c44978b8f851533442bd82a90dd83292c1c33ef8e546772f +size 8110730368 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf new file mode 100644 index 0000000..879da7d --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3880e9d2fc88a7fce38d97b4f28c148730e0467666fe722c602089645c9f96 +size 5753984128 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf new file mode 100644 index 0000000..dc26f9b --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c53635f6443c2e2dd46b1375dc0b06bc0e0f18c9baaf0317fa5b5483f28324 +size 6513664128 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf new file mode 100644 index 0000000..f78e323 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1bfdd6f4e45459b8b0c386e5d55e897984895ba5be100aea07ea8437740d93f +size 7900651648 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf new file mode 100644 index 0000000..7c14dac --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52d391010144e19e359140fe2cfdb546b83fe29aa5001baeb1dc8c56a716c19 +size 7321313408 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf new file mode 100644 index 0000000..34c3226 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a7aa9ac5edf3a0e8d35a29d7e792497e07de97bb769057d4c601ed8e7de9c0 +size 6657106048 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf new file mode 100644 index 0000000..55300bd --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2f530bbb9ee2d980624958ec5ac650cfea1415c47b381cecf4070a6c9247a30 +size 8581324928 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf new file mode 100644 index 0000000..62c4cc0 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b43a4ca32bafd133548a7edfabfe10abdab46a9f5ff77a5cf47e2bf2c6bd67 +size 8543001728 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf new file mode 100644 index 0000000..7b613f4 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56269dcadf1f7aa7fbeb81145d5b610821121acc3a7cc37e2860729dfd56f0d +size 9389522048 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf new file mode 100644 index 0000000..e4c6a64 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deaddadfc28bf95bf48e974699f7482f4b1ac8adadf934d8291af02751a1ded5 +size 9579110528 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf new file mode 100644 index 0000000..9bba23f --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c56980b12c757e06bd4d4e99fca4eacf76fbad9bc46d59fde5fb62280157320 +size 9001753728 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf new file mode 100644 index 0000000..6d2ee42 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b8fcc2ba9ac8ff1f356a051bdef349bf751161c380140ebce9a2379c5265ee +size 8573475968 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf new file mode 100644 index 0000000..242f66e --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5b5cd6b153b0af7cd4acba0224ec0103918800b832980ac40f08abfe8d1f01 +size 10994688128 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf new file mode 100644 index 0000000..607e115 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a82d4ff8e07a2aa22846d74458dd23276c101c5fb5287d4a437444b0877762b0 +size 10514570368 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf new file mode 100644 index 0000000..0d09557 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95229867401697f8ace6279f15c2c90cc00ac010ff89c018545da34ebc80e38b +size 10263895168 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf new file mode 100644 index 0000000..d2888f3 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a15c0570718b6c388780575f2efb73b2d74cf24c9349df6c0818650e6499781 +size 12121938048 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf new file mode 100644 index 0000000..a393aba --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a296c3f76e42d5ceba1a0c4b10e08c5a2669d8cb43fd4f0e4ae1017112615d77 +size 12498739328 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf new file mode 100644 index 0000000..2fb30b5 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa499475ea3ef826610d418658d5947d29cc4b03b74ef9d3a1ff7d9486e7c1da +size 15698534528 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf new file mode 100644 index 0000000..903a52e --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77791e6fecd442fd8245b70aa741128bfba9b48c6f37e3d284962da317872bd +size 29543423840 diff --git a/lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf b/lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf new file mode 100644 index 0000000..3edf416 --- /dev/null +++ b/lemon07r_VellumMini-0.1-Qwen3-14B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1cf0eb8eedeb32947ed50c8c0dd07151826dbcc9e18d8218c53d001340d236 +size 7743584