commit a0e266cb554f33a7434785d5347ed4fb3ec839a5 Author: ModelHub XC Date: Sun Jun 21 03:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4d3b47a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-bf16.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Rocinante-XL-16B-v1-imatrix.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7f46a34 --- /dev/null +++ b/README.md @@ -0,0 +1,177 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: TheDrummer/Rocinante-XL-16B-v1 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Rocinante-XL-16B-v1 by TheDrummer + +Using llama.cpp release b8919 for quantization. + +Original model: https://huggingface.co/TheDrummer/Rocinante-XL-16B-v1 + +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) +- [ramalama](https://github.com/containers/ramalama) +- [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 + +``` +[INST]{system_prompt} + +{prompt}[/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Rocinante-XL-16B-v1-bf16.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-bf16.gguf) | bf16 | 32.14GB | false | Full BF16 weights. | +| [Rocinante-XL-16B-v1-Q8_0.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q8_0.gguf) | Q8_0 | 17.08GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Rocinante-XL-16B-v1-Q6_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q6_K_L.gguf) | Q6_K_L | 14.02GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Rocinante-XL-16B-v1-Q6_K.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q6_K.gguf) | Q6_K | 13.70GB | false | Very high quality, near perfect, *recommended*. | +| [Rocinante-XL-16B-v1-Q5_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q5_K_L.gguf) | Q5_K_L | 12.09GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Rocinante-XL-16B-v1-Q5_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q5_K_M.gguf) | Q5_K_M | 11.68GB | false | High quality, *recommended*. | +| [Rocinante-XL-16B-v1-Q5_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q5_K_S.gguf) | Q5_K_S | 11.22GB | false | High quality, *recommended*. | +| [Rocinante-XL-16B-v1-Q4_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q4_K_L.gguf) | Q4_K_L | 10.56GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Rocinante-XL-16B-v1-Q4_1.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q4_1.gguf) | Q4_1 | 10.29GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Rocinante-XL-16B-v1-Q4_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q4_K_M.gguf) | Q4_K_M | 10.06GB | false | Good quality, default size for most use cases, *recommended*. | +| [Rocinante-XL-16B-v1-Q4_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q4_K_S.gguf) | Q4_K_S | 9.43GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Rocinante-XL-16B-v1-IQ4_NL.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ4_NL.gguf) | IQ4_NL | 9.43GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Rocinante-XL-16B-v1-Q4_0.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q4_0.gguf) | Q4_0 | 9.39GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Rocinante-XL-16B-v1-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q3_K_XL.gguf) | Q3_K_XL | 9.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Rocinante-XL-16B-v1-IQ4_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ4_XS.gguf) | IQ4_XS | 8.98GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Rocinante-XL-16B-v1-Q3_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q3_K_L.gguf) | Q3_K_L | 8.63GB | false | Lower quality but usable, good for low RAM availability. | +| [Rocinante-XL-16B-v1-Q3_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q3_K_M.gguf) | Q3_K_M | 8.15GB | false | Low quality. | +| [Rocinante-XL-16B-v1-IQ3_M.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ3_M.gguf) | IQ3_M | 7.67GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Rocinante-XL-16B-v1-Q3_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q3_K_S.gguf) | Q3_K_S | 7.39GB | false | Low quality, not recommended. | +| [Rocinante-XL-16B-v1-IQ3_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ3_XS.gguf) | IQ3_XS | 7.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Rocinante-XL-16B-v1-Q2_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q2_K_L.gguf) | Q2_K_L | 7.12GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Rocinante-XL-16B-v1-IQ3_XXS.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ3_XXS.gguf) | IQ3_XXS | 6.74GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Rocinante-XL-16B-v1-Q2_K.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-Q2_K.gguf) | Q2_K | 6.46GB | false | Very low quality but surprisingly usable. | +| [Rocinante-XL-16B-v1-IQ2_M.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ2_M.gguf) | IQ2_M | 6.33GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Rocinante-XL-16B-v1-IQ2_S.gguf](https://huggingface.co/bartowski/TheDrummer_Rocinante-XL-16B-v1-GGUF/blob/main/TheDrummer_Rocinante-XL-16B-v1-IQ2_S.gguf) | IQ2_S | 6.00GB | 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_Rocinante-XL-16B-v1-GGUF --include "TheDrummer_Rocinante-XL-16B-v1-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_Rocinante-XL-16B-v1-GGUF --include "TheDrummer_Rocinante-XL-16B-v1-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (TheDrummer_Rocinante-XL-16B-v1-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_Rocinante-XL-16B-v1-IQ2_M.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ2_M.gguf new file mode 100644 index 0000000..4a2c6ad --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65897668a446b0e3f735e7baed177a64153fa21398f951fb77b8a2b26b31bfd4 +size 6334922816 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ2_S.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ2_S.gguf new file mode 100644 index 0000000..89ca556 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d12ee2110c9bc7db3066aca909238e1c9f57333969ddae8ebe62e379b0e8c48 +size 6004621376 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ3_M.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ3_M.gguf new file mode 100644 index 0000000..dd77664 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69607a2da47e515f448eacb9d90c70ee3cbc676c8ff0cdfa8cc765882085f418 +size 7669727296 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ3_XS.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ3_XS.gguf new file mode 100644 index 0000000..e746e07 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8438bc32e92bf616aa98f7672e06728a61be893208f29d49bb8dc6fabb4fd4 +size 7143309376 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ3_XXS.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ3_XXS.gguf new file mode 100644 index 0000000..cccd0ab --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d10872c82b180510acdb740834d9f9e378d65b5acacd25fde1d7bd34fd054d +size 6738133056 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ4_NL.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ4_NL.gguf new file mode 100644 index 0000000..9ce7eca --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de6b443f273efeb7985c51ea2b37222de5e84c5e0390d4a1c490eedf61099ac +size 9432809536 diff --git a/TheDrummer_Rocinante-XL-16B-v1-IQ4_XS.gguf b/TheDrummer_Rocinante-XL-16B-v1-IQ4_XS.gguf new file mode 100644 index 0000000..34ff75c --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a291eb499773db2b80e67ac5479898de056bcd1b63e44a8c5dd6c9b43d2596 +size 8977662016 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q2_K.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q2_K.gguf new file mode 100644 index 0000000..493f3bb --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc11d791c14d79ac6f33dd83c607d39db2a8973d3849a56f129c45d99562fa2 +size 6463782976 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q2_K_L.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q2_K_L.gguf new file mode 100644 index 0000000..c38d2fa --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15130e0706e1350cf51f393c0d23c148b223c3031a10e2ef1452d6872eb06b29 +size 7119142976 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q3_K_L.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_L.gguf new file mode 100644 index 0000000..8303060 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4013741ab16254e91a093e3d245410f35cbd6de95ecab875f7b872dc78e3a75f +size 8633106496 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q3_K_M.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_M.gguf new file mode 100644 index 0000000..13ecb42 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f8e50bcb03d96309e8e64fb44175f60339bde769eb30097b7c9279cd126de2 +size 8146829376 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q3_K_S.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_S.gguf new file mode 100644 index 0000000..a91a510 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6feb20738021478c131b90c760059946969d7527b25617acc6e4588ffab6c1b0 +size 7387840576 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q3_K_XL.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_XL.gguf new file mode 100644 index 0000000..75e1b9b --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8963f2586b040a627666486295e1c8d6c0745203a5591337bdd8cfd8b417913 +size 9220309056 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q4_0.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q4_0.gguf new file mode 100644 index 0000000..bbc9120 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce8bc60a7f8e8b2786d937afa948d2307b852639c11deb441a93261318936d9 +size 9387343936 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q4_1.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q4_1.gguf new file mode 100644 index 0000000..9c19f15 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec9f92757991f5000e4eb27ebb908c4f7a7d5b961662949ecb54ffa2148cf0a +size 10287808576 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q4_K_L.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_L.gguf new file mode 100644 index 0000000..4665089 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bd29b0e1de915954d9e7ad3f23bcbab204bc93e66986f60c1b81362335b018 +size 10561994816 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q4_K_M.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_M.gguf new file mode 100644 index 0000000..e68b22b --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdfb5b1d393fef22fddd9a015599a0a42aecf79b5d4be4b79c8f6580dc46154b +size 10063921216 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q4_K_S.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_S.gguf new file mode 100644 index 0000000..866a5b2 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5843af76655c428b9aa7ea3b1b7656e3f45ff0a192ab6d6a75547f789badae4 +size 9431908416 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q5_K_L.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_L.gguf new file mode 100644 index 0000000..bb9a40f --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503d1a717f97d834984f33a0a8a20816b028ebeee8dead2543f49945f180429b +size 12089557056 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q5_K_M.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_M.gguf new file mode 100644 index 0000000..def7265 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdbddaac5cb27c1a037f62f3e1fcb14435cb7208e64a6e1e4cab14e26773653a +size 11675369536 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q5_K_S.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_S.gguf new file mode 100644 index 0000000..5c00c7f --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d2f2eb4e62ec03079428f6ce76ea47ef24140d40b97199345d8789865d5b4c +size 11215798336 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q6_K.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q6_K.gguf new file mode 100644 index 0000000..cc742c1 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861ea77f34d6a82ff12dd5d0275e3f6cdd5147a2ec66752830bd507a8c4b9079 +size 13695680576 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q6_K_L.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q6_K_L.gguf new file mode 100644 index 0000000..5c8edd3 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd46e8ba4dbef0ee82a6d63ce8adb3d0202749569098b4dd18b3f5a8dd0d33fa +size 14020739136 diff --git a/TheDrummer_Rocinante-XL-16B-v1-Q8_0.gguf b/TheDrummer_Rocinante-XL-16B-v1-Q8_0.gguf new file mode 100644 index 0000000..6009d71 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847bee4f3cc1be8bd89225de25bdd16b8bc3d1c240a3615e5ac248c84c4f2b73 +size 17078321216 diff --git a/TheDrummer_Rocinante-XL-16B-v1-bf16.gguf b/TheDrummer_Rocinante-XL-16B-v1-bf16.gguf new file mode 100644 index 0000000..1cd4c75 --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3804ae53ee69e53ce197c15d957ad1b4041df12e5745e43a362f06717df24b +size 32138493728 diff --git a/TheDrummer_Rocinante-XL-16B-v1-imatrix.gguf b/TheDrummer_Rocinante-XL-16B-v1-imatrix.gguf new file mode 100644 index 0000000..be1356f --- /dev/null +++ b/TheDrummer_Rocinante-XL-16B-v1-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d5fc71c0364c1ca47e66ca5464e6fcc0fc9b4df2e3175ca51915f2cdd5514f +size 9569056