commit a1dbe2093de2858b9e565f9379c635beb33b8574 Author: ModelHub XC Date: Wed Aug 5 19:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5557aff --- /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 + +speakleash_Bielik-11B-v3.0-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +speakleash_Bielik-11B-v3.0-Instruct-Q8_0.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..a63d296 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: speakleash/Bielik-11B-v3.0-Instruct +--- + +## Llamacpp imatrix Quantizations of Bielik-11B-v3.0-Instruct by speakleash + +Using llama.cpp release b7610 for quantization. + +Original model: https://huggingface.co/speakleash/Bielik-11B-v3.0-Instruct + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d) + +Run them in your choice of tools: + +- [llama.cpp](https://github.com/ggml-org/llama.cpp) +- [LM Studio](https://lmstudio.ai/) +- [koboldcpp](https://github.com/LostRuins/koboldcpp) +- [Jan AI](https://www.jan.ai/) +- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui) +- [LoLLMs](https://github.com/ParisNeo/lollms) + +Note: if it's a newly supported model, you may need to wait for an update from the developers. + +## 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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Bielik-11B-v3.0-Instruct-bf16.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-bf16.gguf) | bf16 | 22.34GB | false | Full BF16 weights. | +| [Bielik-11B-v3.0-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q8_0.gguf) | Q8_0 | 11.87GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Bielik-11B-v3.0-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q6_K_L.gguf) | Q6_K_L | 9.23GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q6_K.gguf) | Q6_K | 9.16GB | false | Very high quality, near perfect, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_L.gguf) | Q5_K_L | 7.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_M.gguf) | Q5_K_M | 7.91GB | false | High quality, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_S.gguf) | Q5_K_S | 7.70GB | false | High quality, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q4_1.gguf) | Q4_1 | 7.01GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Bielik-11B-v3.0-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_L.gguf) | Q4_K_L | 6.82GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_M.gguf) | Q4_K_M | 6.72GB | false | Good quality, default size for most use cases, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_S.gguf) | Q4_K_S | 6.36GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q4_0.gguf) | Q4_0 | 6.34GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Bielik-11B-v3.0-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ4_NL.gguf) | IQ4_NL | 6.34GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Bielik-11B-v3.0-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ4_XS.gguf) | IQ4_XS | 6.01GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf) | Q3_K_XL | 6.00GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Bielik-11B-v3.0-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_L.gguf) | Q3_K_L | 5.88GB | false | Lower quality but usable, good for low RAM availability. | +| [Bielik-11B-v3.0-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_M.gguf) | Q3_K_M | 5.40GB | false | Low quality. | +| [Bielik-11B-v3.0-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ3_M.gguf) | IQ3_M | 5.04GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Bielik-11B-v3.0-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_S.gguf) | Q3_K_S | 4.85GB | false | Low quality, not recommended. | +| [Bielik-11B-v3.0-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XS.gguf) | IQ3_XS | 4.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 4.34GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Bielik-11B-v3.0-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q2_K_L.gguf) | Q2_K_L | 4.29GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Bielik-11B-v3.0-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-Q2_K.gguf) | Q2_K | 4.16GB | false | Very low quality but surprisingly usable. | +| [Bielik-11B-v3.0-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ2_M.gguf) | IQ2_M | 3.82GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Bielik-11B-v3.0-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/speakleash_Bielik-11B-v3.0-Instruct-GGUF/blob/main/speakleash_Bielik-11B-v3.0-Instruct-IQ2_S.gguf) | IQ2_S | 3.53GB | 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/speakleash_Bielik-11B-v3.0-Instruct-GGUF --include "speakleash_Bielik-11B-v3.0-Instruct-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/speakleash_Bielik-11B-v3.0-Instruct-GGUF --include "speakleash_Bielik-11B-v3.0-Instruct-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (speakleash_Bielik-11B-v3.0-Instruct-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/speakleash_Bielik-11B-v3.0-Instruct-IQ2_M.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..d3b59fd --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dab5354077f63cb19a65769e40a43b3b62a191381c2974bd7c00a408bc45b39 +size 3823567552 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ2_S.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..7408459 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58428d1dfe19143e15d036a82758466b7b32682061ff69841b58916d688be28 +size 3526558400 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ3_M.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..85a727c --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550c18dd23d6826737e54522d1c9cd7edcf6abd8f30ae01d0ed9a2ddf2209340 +size 5038781120 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XS.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..1a7cfdf --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f538bbd98bc2a1a4c7e431434c1d6c2956756b8a5ced1446427af4b2c8b9e3 +size 4627739328 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..b75396b --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8d6ece200c7f5cf8596bf99c9dc33c3840987f44321d8c07dd8778702f56c7 +size 4335534784 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ4_NL.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..6ac8e2d --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c847d08904648796a8f451bd108042c0005aea4764ce4212e6022f06dab2688a +size 6344762048 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-IQ4_XS.gguf b/speakleash_Bielik-11B-v3.0-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..007a650 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3039c389720f128515fd42af9f214376e1a97750623ea11d8c03963b95f32cad +size 6006416064 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q2_K.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q2_K.gguf new file mode 100644 index 0000000..161e0e9 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9626edecab2ff0820941a2a75b07ae6d9eae470b58643d205e73b568b6f94c8 +size 4164338368 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q2_K_L.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q2_K_L.gguf new file mode 100644 index 0000000..55a1bc9 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7f7ab9f7942550c6be24e7bc7f2b92ba0a072986decdc22468f05df9a95250a +size 4292850368 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_L.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..394c929 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2f26f2d6dc1ef8220587e444482607e1e90c0549959dc5239f326ca9d08092 +size 5880001216 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_M.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..72d81c2 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47ad0f4f9cc11b6604a1e103deaa07e88608f5e1e9dad563d8e80738c8369b9 +size 5404996288 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_S.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..0620551 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61b852001dc767c4698283d3c5355c85c50251f6ff7f2bb61662ff57ba78fdd +size 4852724416 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf new file mode 100644 index 0000000..8232dcc --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ac5586a2d2911152bad408405c7069a7aeb32fbe2dc18b02e7e6c6c4087c62 +size 5995147968 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q4_0.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q4_0.gguf new file mode 100644 index 0000000..7c16628 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc8fe763809ccf8fe777fb966fa5607dc7c81edcc88772c6c10eb1acc69dfa52 +size 6340567744 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q4_1.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q4_1.gguf new file mode 100644 index 0000000..92aee29 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ba3eaa335a7e5f7c29e7ed19aa5c74c84774c651aa650f8cdb31dd542bea31 +size 7008346816 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_L.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_L.gguf new file mode 100644 index 0000000..26fc780 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f97486be19a78c530ea3c471529f1f8369e5413177dd250d9ed23fedc8c5d9b +size 6821720768 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_M.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..89b8699 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2466261fcc2898cb49ed7b08a47799257de68be952bee5e7fd19c8ddaabc087a +size 6724051648 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_S.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..d117ed2 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b072b7f0e291b8a1586010e1416376f69ea6ea4ea864f5be4c143dd088d71d6 +size 6364684992 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_L.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_L.gguf new file mode 100644 index 0000000..dd2d68c --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ffcb87e3e776fc42f922a6c6e0dfbd9e85e8a7cab8cd02564ef7c83327a907 +size 7988261568 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_M.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..f112d18 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91296461ad7401fa22a02e826cade499e11be26351d1f33315571bcaff2ea686 +size 7907041984 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_S.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..fe8fc29 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91bcb50b7d0e11161ab46a746f1215f84e1defc3e3074f67e7315c631f15b10b +size 7698145984 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q6_K.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q6_K.gguf new file mode 100644 index 0000000..fb762ff --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b3d7b53909713cace617c7524c18f1b285d29e1f446a29f9e6f2b8845ab897 +size 9163969216 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q6_K_L.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q6_K_L.gguf new file mode 100644 index 0000000..097005b --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ef0161964b3b575db93c23c30f8521b41770921af3f16e828611b6db2c4304 +size 9227711168 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-Q8_0.gguf b/speakleash_Bielik-11B-v3.0-Instruct-Q8_0.gguf new file mode 100644 index 0000000..fc4d2c3 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf25b62b3b843f7dcef7478a26984cba2bfab7ae32e30286c1cf25dda9fabf2 +size 11868811968 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-bf16.gguf b/speakleash_Bielik-11B-v3.0-Instruct-bf16.gguf new file mode 100644 index 0000000..101caf2 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b36c28be39b6b22a8acef89a9929150cbd9293eb34e008acdc4475880a8e691d +size 22339170688 diff --git a/speakleash_Bielik-11B-v3.0-Instruct-imatrix.gguf b/speakleash_Bielik-11B-v3.0-Instruct-imatrix.gguf new file mode 100644 index 0000000..2cec7c9 --- /dev/null +++ b/speakleash_Bielik-11B-v3.0-Instruct-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35f9a88be5179dcbe6ef67f79ec70fa0a201e4295f74f9ba86780c987c08dc5 +size 7836256