commit 26873334cfeaa8770ecde9ce0b461df194f26d99 Author: ModelHub XC Date: Wed Jul 22 12:50:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3448ae --- /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 + +TheDrummer_Snowpiercer-15B-v4-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-bf16.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TheDrummer_Snowpiercer-15B-v4-Q4_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..95dd6a9 --- /dev/null +++ b/README.md @@ -0,0 +1,171 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: TheDrummer/Snowpiercer-15B-v4 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Snowpiercer-15B-v4 by TheDrummer + +Using llama.cpp release b7127 for quantization. + +Original model: https://huggingface.co/TheDrummer/Snowpiercer-15B-v4 + +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 + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Snowpiercer-15B-v4-bf16.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-bf16.gguf) | bf16 | 29.96GB | false | Full BF16 weights. | +| [Snowpiercer-15B-v4-Q8_0.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q8_0.gguf) | Q8_0 | 15.92GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Snowpiercer-15B-v4-Q6_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q6_K_L.gguf) | Q6_K_L | 12.62GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Snowpiercer-15B-v4-Q6_K.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q6_K.gguf) | Q6_K | 12.29GB | false | Very high quality, near perfect, *recommended*. | +| [Snowpiercer-15B-v4-Q5_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q5_K_L.gguf) | Q5_K_L | 11.07GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Snowpiercer-15B-v4-Q5_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q5_K_M.gguf) | Q5_K_M | 10.65GB | false | High quality, *recommended*. | +| [Snowpiercer-15B-v4-Q5_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q5_K_S.gguf) | Q5_K_S | 10.39GB | false | High quality, *recommended*. | +| [Snowpiercer-15B-v4-Q4_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q4_K_L.gguf) | Q4_K_L | 9.61GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Snowpiercer-15B-v4-Q4_1.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q4_1.gguf) | Q4_1 | 9.50GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Snowpiercer-15B-v4-Q4_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q4_K_M.gguf) | Q4_K_M | 9.11GB | false | Good quality, default size for most use cases, *recommended*. | +| [Snowpiercer-15B-v4-Q4_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q4_K_S.gguf) | Q4_K_S | 8.66GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Snowpiercer-15B-v4-IQ4_NL.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ4_NL.gguf) | IQ4_NL | 8.64GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Snowpiercer-15B-v4-Q4_0.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q4_0.gguf) | Q4_0 | 8.63GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Snowpiercer-15B-v4-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-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. | +| [Snowpiercer-15B-v4-IQ4_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ4_XS.gguf) | IQ4_XS | 8.20GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Snowpiercer-15B-v4-Q3_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q3_K_L.gguf) | Q3_K_L | 7.99GB | false | Lower quality but usable, good for low RAM availability. | +| [Snowpiercer-15B-v4-Q3_K_M.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q3_K_M.gguf) | Q3_K_M | 7.40GB | false | Low quality. | +| [Snowpiercer-15B-v4-IQ3_M.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ3_M.gguf) | IQ3_M | 6.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Snowpiercer-15B-v4-Q3_K_S.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q3_K_S.gguf) | Q3_K_S | 6.71GB | false | Low quality, not recommended. | +| [Snowpiercer-15B-v4-Q2_K_L.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q2_K_L.gguf) | Q2_K_L | 6.45GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Snowpiercer-15B-v4-IQ3_XS.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ3_XS.gguf) | IQ3_XS | 6.42GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Snowpiercer-15B-v4-IQ3_XXS.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ3_XXS.gguf) | IQ3_XXS | 5.99GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Snowpiercer-15B-v4-Q2_K.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-Q2_K.gguf) | Q2_K | 5.79GB | false | Very low quality but surprisingly usable. | +| [Snowpiercer-15B-v4-IQ2_M.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ2_M.gguf) | IQ2_M | 5.35GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Snowpiercer-15B-v4-IQ2_S.gguf](https://huggingface.co/bartowski/TheDrummer_Snowpiercer-15B-v4-GGUF/blob/main/TheDrummer_Snowpiercer-15B-v4-IQ2_S.gguf) | IQ2_S | 4.98GB | 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_Snowpiercer-15B-v4-GGUF --include "TheDrummer_Snowpiercer-15B-v4-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_Snowpiercer-15B-v4-GGUF --include "TheDrummer_Snowpiercer-15B-v4-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (TheDrummer_Snowpiercer-15B-v4-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_Snowpiercer-15B-v4-IQ2_M.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ2_M.gguf new file mode 100644 index 0000000..a047b5c --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bf8066575c9379c458e561f7d2aa37ac67ce23cb74ac235d29b72d539fd7b9 +size 5352369280 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ2_S.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ2_S.gguf new file mode 100644 index 0000000..a05c90c --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88142646f3cd190c73fc5cbbfbad27a910fe9f80e307a07dfff0bbb5ce225af +size 4981107840 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ3_M.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ3_M.gguf new file mode 100644 index 0000000..904ce87 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee7ad69803bc5212c4f815677878234c8092865c46c75e874f9397509be4ef4d +size 6938668160 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ3_XS.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ3_XS.gguf new file mode 100644 index 0000000..9ecc280 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103399e7f03724a609b71085cdba934d08e3132809d2972f94bc1bc3cbf6d96f +size 6424865920 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ3_XXS.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ3_XXS.gguf new file mode 100644 index 0000000..d43cec2 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afc7cf3d9077fee1f8fb083b6f735bae375d411f9d2c4ef241119d5e8cb9bb9 +size 5992328320 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ4_NL.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ4_NL.gguf new file mode 100644 index 0000000..8a46b74 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:017579787fabc931a6220d97e2ba4fc628eec82edad64c447b4e0d98d0332ded +size 8638426240 diff --git a/TheDrummer_Snowpiercer-15B-v4-IQ4_XS.gguf b/TheDrummer_Snowpiercer-15B-v4-IQ4_XS.gguf new file mode 100644 index 0000000..3745b97 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe090beb03d7aa15b186775cbd1cfae79ad46fb6fe4e84a666e22a6705a333b +size 8199662720 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q2_K.gguf b/TheDrummer_Snowpiercer-15B-v4-Q2_K.gguf new file mode 100644 index 0000000..05323c9 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6271f734346ac9f7bc987b76094a098fbc009775e3f42ee3d842d28092607c7 +size 5794163840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q2_K_L.gguf b/TheDrummer_Snowpiercer-15B-v4-Q2_K_L.gguf new file mode 100644 index 0000000..00000c8 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2e399972e72eba0e3a8e19741fed31106afbd3ddc609c9ca5409772d65e247 +size 6449523840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q3_K_L.gguf b/TheDrummer_Snowpiercer-15B-v4-Q3_K_L.gguf new file mode 100644 index 0000000..ba1f566 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5bea624f1a968579a31b619235c67d22c328b63878f0469ab6ae9c871b2378 +size 7990193280 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q3_K_M.gguf b/TheDrummer_Snowpiercer-15B-v4-Q3_K_M.gguf new file mode 100644 index 0000000..91021eb --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566b726a44076a04c9f7fdab0a0256a060427c42f641f27a745187bfd9172fdc +size 7396437120 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q3_K_S.gguf b/TheDrummer_Snowpiercer-15B-v4-Q3_K_S.gguf new file mode 100644 index 0000000..dc89740 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb3a5b60de4b54c59536b930c3bbcdd014db4d7969307ed89efd83a76beddc1 +size 6706097280 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q3_K_XL.gguf b/TheDrummer_Snowpiercer-15B-v4-Q3_K_XL.gguf new file mode 100644 index 0000000..885eec0 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55174cc95192cd9f9a178f5601d9207c4d6da594fcdad1bf32c651903a9ef94b +size 8577395840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q4_0.gguf b/TheDrummer_Snowpiercer-15B-v4-Q4_0.gguf new file mode 100644 index 0000000..9b70f33 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c03d5836e49a6582a6ff84815c60a11972b57b4c0ad704d1aa90ac1069c508b +size 8633183360 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q4_1.gguf b/TheDrummer_Snowpiercer-15B-v4-Q4_1.gguf new file mode 100644 index 0000000..40e9d3a --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1e5427ec6b4efdc7d14efd156f6150ddbfcb82db4d16d044b83218538b6fc7 +size 9499569280 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q4_K_L.gguf b/TheDrummer_Snowpiercer-15B-v4-Q4_K_L.gguf new file mode 100644 index 0000000..fe031e8 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039176502ad3f6b0358ea07ae34ae88a960aa88731343cdfd533c2d544b40455 +size 9610611840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q4_K_M.gguf b/TheDrummer_Snowpiercer-15B-v4-Q4_K_M.gguf new file mode 100644 index 0000000..271f3e5 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39798ed5a401e786e8c8fbc8d5865d8030a814de819ee829839f22c5060a0188 +size 9112538240 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q4_K_S.gguf b/TheDrummer_Snowpiercer-15B-v4-Q4_K_S.gguf new file mode 100644 index 0000000..ec93bb4 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2e7faccaa1a1d671b7140498b5828ff70169cde344237aa659cdb72a32ee99 +size 8663329920 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q5_K_L.gguf b/TheDrummer_Snowpiercer-15B-v4-Q5_K_L.gguf new file mode 100644 index 0000000..94f889a --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b6e850ec57b34ce1722bb4c6feefcb37694a0d4d8f66b66368b0c53aaeb987 +size 11068787840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q5_K_M.gguf b/TheDrummer_Snowpiercer-15B-v4-Q5_K_M.gguf new file mode 100644 index 0000000..7eb2093 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c9e5a14fff646c03a2dd897677014f60a60aee5025516c426f2eb22061ad9bd +size 10654600320 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q5_K_S.gguf b/TheDrummer_Snowpiercer-15B-v4-Q5_K_S.gguf new file mode 100644 index 0000000..8695403 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf912ba2f629e2a4411c62f6e4138e79f91f56e35320dee9f144f0183701aee +size 10393480320 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q6_K.gguf b/TheDrummer_Snowpiercer-15B-v4-Q6_K.gguf new file mode 100644 index 0000000..e594bf5 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bca5005006a8c75a49e39e7cf911b9ffe2fd1d9f8a4383a341484faf6c027f8 +size 12293041280 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q6_K_L.gguf b/TheDrummer_Snowpiercer-15B-v4-Q6_K_L.gguf new file mode 100644 index 0000000..01aae78 --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c095f859c59a0e3644abc20dec361ebfe41142098b29379a5bf080b9e07f649 +size 12618099840 diff --git a/TheDrummer_Snowpiercer-15B-v4-Q8_0.gguf b/TheDrummer_Snowpiercer-15B-v4-Q8_0.gguf new file mode 100644 index 0000000..ec8ae7b --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a4e99a63c1b764be93a8bf048f471f16a37e98ead40947afbf671186c14a33 +size 15919475840 diff --git a/TheDrummer_Snowpiercer-15B-v4-bf16.gguf b/TheDrummer_Snowpiercer-15B-v4-bf16.gguf new file mode 100644 index 0000000..1e8a9bb --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:579031c4692d0aaa42d0f68e82dbef08cd79a50d499953f97063b9f139578266 +size 29957286752 diff --git a/TheDrummer_Snowpiercer-15B-v4-imatrix.gguf b/TheDrummer_Snowpiercer-15B-v4-imatrix.gguf new file mode 100644 index 0000000..125c34f --- /dev/null +++ b/TheDrummer_Snowpiercer-15B-v4-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e414bc35784995c4b7d4be4407754163d1234792f836a05b7c02b55f43f1cb50 +size 8860256 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