commit 0f6b9df29a7091d0093148e098d567dc524d189c Author: ModelHub XC Date: Mon May 11 14:38:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RealmSky/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF-oss Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2bc4e26 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Sao10K_Llama-3.3-70B-Vulpecula-r1.imatrix filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..34417fd --- /dev/null +++ b/README.md @@ -0,0 +1,173 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +license: llama3.3 +base_model_relation: quantized +language: +- en +base_model: Sao10K/Llama-3.3-70B-Vulpecula-r1 +--- + +## Llamacpp imatrix Quantizations of Llama-3.3-70B-Vulpecula-r1 by Sao10K + +Using llama.cpp release b4925 for quantization. + +Original model: https://huggingface.co/Sao10K/Llama-3.3-70B-Vulpecula-r1 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Llama-3.3-70B-Vulpecula-r1-Q8_0.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/tree/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0) | Q8_0 | 74.98GB | true | Extremely high quality, generally unneeded but max available quant. | +| [Llama-3.3-70B-Vulpecula-r1-Q6_K.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/tree/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K) | Q6_K | 57.89GB | true | Very high quality, near perfect, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q5_K_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/tree/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M) | Q5_K_M | 49.95GB | true | High quality, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q5_K_S.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_S.gguf) | Q5_K_S | 48.66GB | false | High quality, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q4_1.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_1.gguf) | Q4_1 | 44.31GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf) | Q4_K_M | 42.52GB | false | Good quality, default size for most use cases, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q4_K_S.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_S.gguf) | Q4_K_S | 40.35GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q4_0.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_0.gguf) | Q4_0 | 40.12GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Llama-3.3-70B-Vulpecula-r1-IQ4_NL.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_NL.gguf) | IQ4_NL | 40.05GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Llama-3.3-70B-Vulpecula-r1-Q3_K_XL.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_XL.gguf) | Q3_K_XL | 38.06GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Llama-3.3-70B-Vulpecula-r1-IQ4_XS.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_XS.gguf) | IQ4_XS | 37.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Llama-3.3-70B-Vulpecula-r1-Q3_K_L.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_L.gguf) | Q3_K_L | 37.14GB | false | Lower quality but usable, good for low RAM availability. | +| [Llama-3.3-70B-Vulpecula-r1-Q3_K_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_M.gguf) | Q3_K_M | 34.27GB | false | Low quality. | +| [Llama-3.3-70B-Vulpecula-r1-IQ3_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_M.gguf) | IQ3_M | 31.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Llama-3.3-70B-Vulpecula-r1-Q3_K_S.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_S.gguf) | Q3_K_S | 30.91GB | false | Low quality, not recommended. | +| [Llama-3.3-70B-Vulpecula-r1-IQ3_XS.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XS.gguf) | IQ3_XS | 29.31GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Llama-3.3-70B-Vulpecula-r1-IQ3_XXS.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XXS.gguf) | IQ3_XXS | 27.47GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Llama-3.3-70B-Vulpecula-r1-Q2_K_L.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K_L.gguf) | Q2_K_L | 27.40GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Llama-3.3-70B-Vulpecula-r1-Q2_K.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K.gguf) | Q2_K | 26.38GB | false | Very low quality but surprisingly usable. | +| [Llama-3.3-70B-Vulpecula-r1-IQ2_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_M.gguf) | IQ2_M | 24.12GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Llama-3.3-70B-Vulpecula-r1-IQ2_S.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_S.gguf) | IQ2_S | 22.24GB | false | Low quality, uses SOTA techniques to be usable. | +| [Llama-3.3-70B-Vulpecula-r1-IQ2_XS.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XS.gguf) | IQ2_XS | 21.14GB | false | Low quality, uses SOTA techniques to be usable. | +| [Llama-3.3-70B-Vulpecula-r1-IQ2_XXS.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XXS.gguf) | IQ2_XXS | 19.10GB | false | Very low quality, uses SOTA techniques to be usable. | +| [Llama-3.3-70B-Vulpecula-r1-IQ1_M.gguf](https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/blob/main/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ1_M.gguf) | IQ1_M | 16.75GB | false | Extremely low quality, *not* recommended. | + +## 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/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF --include "Sao10K_Llama-3.3-70B-Vulpecula-r1-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/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF --include "Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ1_M.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ1_M.gguf new file mode 100644 index 0000000..1b87728 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:881f0ce8de6d95d58fcd497169644c685447a4a0986227b87b4e4b02e2cf70a6 +size 16751201024 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_M.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_M.gguf new file mode 100644 index 0000000..7d66255 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744abbe1213e805ee1b938f5e41c0053a60c93d95519e57bd1885e81d8cb6d23 +size 24119298816 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_S.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_S.gguf new file mode 100644 index 0000000..a4df31e --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a4142c07248f6e0c513eb3687990b79b2e535ea2fffb14841d76227a72ad6ab +size 22242347776 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XS.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XS.gguf new file mode 100644 index 0000000..fe55830 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf7ef5fe288605bdf172f271bf43220c8f516fc84fd515499be55fa8e8306e8 +size 21142113024 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XXS.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XXS.gguf new file mode 100644 index 0000000..62d2a25 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0285c45dde2a86fa283b42325ca75e8a0ed0c33c2cfa53af327cebc39c6c8e1d +size 19097389824 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_M.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_M.gguf new file mode 100644 index 0000000..7f7a408 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d802deffd6f3bb35c02b1fcfa3fc5d780ce7c469fefa653588146b6746596fbf +size 31937039104 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XS.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XS.gguf new file mode 100644 index 0000000..dc8d17c --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4735cb44b0d7313c14cff1b7d25d33870017193a5837f2023347439ec040a62b +size 29307734784 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XXS.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XXS.gguf new file mode 100644 index 0000000..e47f368 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1165e638c163af4e6ed881d164e37cdcc1115700395e0072a05b0a06a85ed91e +size 27469499136 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_NL.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_NL.gguf new file mode 100644 index 0000000..7eabe1b --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc529175d204bd7623c5d9b514820d1f05eda00254b4b97338d591988620996b +size 40053623552 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_XS.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_XS.gguf new file mode 100644 index 0000000..e303bc7 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadccee53af407c46dc5180ffe9e2c1f434b1f4c31e31c05186ae39b6b96ebd3 +size 37902666496 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K.gguf new file mode 100644 index 0000000..10f4158 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ede1c0df85db57db7171a97c2085e4050ff3e5c512be92f62dee318690bd498 +size 26375113472 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K_L.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K_L.gguf new file mode 100644 index 0000000..926d9d2 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefed870cdc628c410aebf65efe00ddd9379ada9cbc9dd913578c64077173c42 +size 27401161472 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_L.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_L.gguf new file mode 100644 index 0000000..d19d192 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1be6fa5c9422a8c6c5bc4ef97783b49b31417ae63d7eb7fa3be360ba1329e6 +size 37140597504 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_M.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_M.gguf new file mode 100644 index 0000000..842c4b8 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb62240f4729b4e3bea203fe598847fe3f26a5a92de412b1ac74a0d3a4e75651 +size 34267499264 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_S.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_S.gguf new file mode 100644 index 0000000..111e41d --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e043e447ee750fb6b35be2e2486c74d9b024dbf51f85f6e666027a1becc551 +size 30912056064 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_XL.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_XL.gguf new file mode 100644 index 0000000..c2ea447 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5827f731f55ba0c007a36596824106e38e9b773b4e9041d1eee3bffdca425d60 +size 38059936512 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_0.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_0.gguf new file mode 100644 index 0000000..74f434e --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd322b8f669cf4a5832b5bb9a62a9a86800a526804290d46e8be65be9ebb4c89 +size 40116538112 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_1.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_1.gguf new file mode 100644 index 0000000..be9020e --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba8a1ff42d662a9afc777a3edc5000dac562e3286177f8f11ce5c0a7ab4453b +size 44313594624 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf new file mode 100644 index 0000000..51b625e --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817073c85286c25a9373f330aad32b503e6c13d626a3fbee926d96a7ab866845 +size 42520398592 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_S.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_S.gguf new file mode 100644 index 0000000..366261f --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2011df213ed2a3defb54444bb5d179b4f01e4336d4a52c5090e9072d05f6ffd +size 40347224832 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00001-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00001-of-00002.gguf new file mode 100644 index 0000000..580c45b --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa2128c42ad4a002bfb2343740533141077201988a2dda3f4a35073ab720d31 +size 39987554656 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00002-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00002-of-00002.gguf new file mode 100644 index 0000000..b9ccf2e --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_M-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9043c3afeb81622c7fee2b6a2cbb5e88dd53d56bd882d44dbd432dff81b854b4 +size 9962267232 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_S.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_S.gguf new file mode 100644 index 0000000..a3fab8c --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75981f51072374726a10bfa665555dbbed023cf9be68fe4c8fea2d2c0d1d46eb +size 48657451776 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00001-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00001-of-00002.gguf new file mode 100644 index 0000000..60cb40b --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbcd12e710ea5e9fc5a90be12076c7b94c784379c4716904b31923132dbe0661 +size 39953847808 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00002-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00002-of-00002.gguf new file mode 100644 index 0000000..0005a26 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q6_K-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1235763c01401bcd9878b521b39b5c0a027d778343c41248ad78a81e9d3814 +size 17934300608 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00001-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00001-of-00002.gguf new file mode 100644 index 0000000..6ca7f78 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00001-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3095df04ed96b1b065aefec7c67c556b4013de2805852e0492c389f626825400 +size 39927003840 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00002-of-00002.gguf b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00002-of-00002.gguf new file mode 100644 index 0000000..5ac3820 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q8_0-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92b3db490a05d46885f6d7a7973463d574ae5ffe337d043fd0c05789de976be +size 35048050944 diff --git a/Sao10K_Llama-3.3-70B-Vulpecula-r1.imatrix b/Sao10K_Llama-3.3-70B-Vulpecula-r1.imatrix new file mode 100644 index 0000000..53b0ac3 --- /dev/null +++ b/Sao10K_Llama-3.3-70B-Vulpecula-r1.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b96f80ea8dcff92a6f7b6583ca8e63cb551cb50f3462a27b50588ac45e088ca +size 24922298 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