commit 8b52b21981282412133d7e5fa62025e5ae779e12 Author: ModelHub XC Date: Wed Jun 17 14:17:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32370ff --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Tralalabs_CHEETAH-350M-Merged-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-bf16.gguf filter=lfs diff=lfs merge=lfs -text +Tralalabs_CHEETAH-350M-Merged-imatrix.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0bf8454 --- /dev/null +++ b/README.md @@ -0,0 +1,193 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- cheetah +- cheetah-350m +- lfm2 +- liquid-ai +- merged +- fp16 +- instruction-tuned +- text-generation +- modal +language: +- en +license: other +base_model_relation: quantized +base_model: Tralalabs/CHEETAH-350M-Merged-FP16 +datasets: +- HuggingFaceTB/smol-smoltalk +--- + +## Llamacpp imatrix Quantizations of CHEETAH-350M-Merged by Tralalabs + +Using llama.cpp release b9384 for quantization. + +Original model: https://huggingface.co/Tralalabs/CHEETAH-350M-Merged-FP16 + +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 + +``` +<|startoftext|><|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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [CHEETAH-350M-Merged-bf16.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-bf16.gguf) | bf16 | 0.71GB | false | Full BF16 weights. | +| [CHEETAH-350M-Merged-Q8_0.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q8_0.gguf) | Q8_0 | 0.38GB | false | Extremely high quality, generally unneeded but max available quant. | +| [CHEETAH-350M-Merged-Q6_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q6_K_L.gguf) | Q6_K_L | 0.31GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [CHEETAH-350M-Merged-Q6_K.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q6_K.gguf) | Q6_K | 0.30GB | false | Very high quality, near perfect, *recommended*. | +| [CHEETAH-350M-Merged-Q5_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q5_K_L.gguf) | Q5_K_L | 0.28GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [CHEETAH-350M-Merged-Q5_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q5_K_M.gguf) | Q5_K_M | 0.26GB | false | High quality, *recommended*. | +| [CHEETAH-350M-Merged-Q5_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q5_K_S.gguf) | Q5_K_S | 0.26GB | false | High quality, *recommended*. | +| [CHEETAH-350M-Merged-Q4_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q4_K_L.gguf) | Q4_K_L | 0.25GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [CHEETAH-350M-Merged-Q4_1.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q4_1.gguf) | Q4_1 | 0.24GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [CHEETAH-350M-Merged-Q4_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q4_K_M.gguf) | Q4_K_M | 0.23GB | false | Good quality, default size for most use cases, *recommended*. | +| [CHEETAH-350M-Merged-Q4_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q4_K_S.gguf) | Q4_K_S | 0.22GB | false | Slightly lower quality with more space savings, *recommended*. | +| [CHEETAH-350M-Merged-Q4_0.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q4_0.gguf) | Q4_0 | 0.22GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [CHEETAH-350M-Merged-IQ4_NL.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ4_NL.gguf) | IQ4_NL | 0.22GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [CHEETAH-350M-Merged-Q3_K_XL.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q3_K_XL.gguf) | Q3_K_XL | 0.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [CHEETAH-350M-Merged-IQ4_XS.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ4_XS.gguf) | IQ4_XS | 0.21GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [CHEETAH-350M-Merged-Q3_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q3_K_L.gguf) | Q3_K_L | 0.20GB | false | Lower quality but usable, good for low RAM availability. | +| [CHEETAH-350M-Merged-Q3_K_M.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q3_K_M.gguf) | Q3_K_M | 0.19GB | false | Low quality. | +| [CHEETAH-350M-Merged-IQ3_M.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ3_M.gguf) | IQ3_M | 0.18GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [CHEETAH-350M-Merged-Q3_K_S.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q3_K_S.gguf) | Q3_K_S | 0.18GB | false | Low quality, not recommended. | +| [CHEETAH-350M-Merged-IQ3_XS.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ3_XS.gguf) | IQ3_XS | 0.18GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [CHEETAH-350M-Merged-Q2_K_L.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q2_K_L.gguf) | Q2_K_L | 0.18GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [CHEETAH-350M-Merged-IQ3_XXS.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ3_XXS.gguf) | IQ3_XXS | 0.16GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [CHEETAH-350M-Merged-Q2_K.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-Q2_K.gguf) | Q2_K | 0.16GB | false | Very low quality but surprisingly usable. | +| [CHEETAH-350M-Merged-IQ2_M.gguf](https://huggingface.co/bartowski/Tralalabs_CHEETAH-350M-Merged-GGUF/blob/main/Tralalabs_CHEETAH-350M-Merged-IQ2_M.gguf) | IQ2_M | 0.15GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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/Tralalabs_CHEETAH-350M-Merged-GGUF --include "Tralalabs_CHEETAH-350M-Merged-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/Tralalabs_CHEETAH-350M-Merged-GGUF --include "Tralalabs_CHEETAH-350M-Merged-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (Tralalabs_CHEETAH-350M-Merged-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/Tralalabs_CHEETAH-350M-Merged-IQ2_M.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ2_M.gguf new file mode 100644 index 0000000..7af797e --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c03eecdde8d7fa485ed0615b16b154f636984af0be2479e5480c5f6148755c0 +size 149488448 diff --git a/Tralalabs_CHEETAH-350M-Merged-IQ3_M.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ3_M.gguf new file mode 100644 index 0000000..6ff3cfb --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec9f62bced8e4e011932836b923ada9d0b8795a4e1830ee77bcb1f208a699c6 +size 184869696 diff --git a/Tralalabs_CHEETAH-350M-Merged-IQ3_XS.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ3_XS.gguf new file mode 100644 index 0000000..9b62638 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781111fabe8780643c352fef80c390bc33c41b58cdefa13888e0022998284992 +size 176661312 diff --git a/Tralalabs_CHEETAH-350M-Merged-IQ3_XXS.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ3_XXS.gguf new file mode 100644 index 0000000..21c8f9c --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d586f37b022425ac6cb5f0146df7e4ebee28b7658e776414683567140054cb1e +size 159982400 diff --git a/Tralalabs_CHEETAH-350M-Merged-IQ4_NL.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ4_NL.gguf new file mode 100644 index 0000000..ac2bf78 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfd8e3672c9ad731cdbb83d954ee7046f7d71c39f4067dc75dc403a78aa0114c +size 219849536 diff --git a/Tralalabs_CHEETAH-350M-Merged-IQ4_XS.gguf b/Tralalabs_CHEETAH-350M-Merged-IQ4_XS.gguf new file mode 100644 index 0000000..9055ebe --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b001db33a5ce34c7498365871df83acb6438383c7f7c073eb8ce281ab854e6 +size 210936640 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q2_K.gguf b/Tralalabs_CHEETAH-350M-Merged-Q2_K.gguf new file mode 100644 index 0000000..3b88f44 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d02a8172509c5d345dd279ee34eec49bf7ae2018adb6bb7986018aab5724fd4 +size 161628992 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q2_K_L.gguf b/Tralalabs_CHEETAH-350M-Merged-Q2_K_L.gguf new file mode 100644 index 0000000..22f0a6f --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e85fa92c5a4937fb90f8471dea2e92f167168bfe0f3784b02d2b04a75091b0b +size 177881920 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q3_K_L.gguf b/Tralalabs_CHEETAH-350M-Merged-Q3_K_L.gguf new file mode 100644 index 0000000..55c913e --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486c3306fe41b6de487e0ad2265483b2ca424d429e9ab24a9f44386d2878feb4 +size 203080512 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q3_K_M.gguf b/Tralalabs_CHEETAH-350M-Merged-Q3_K_M.gguf new file mode 100644 index 0000000..29b8a36 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d609802c4eac4bfbf6996a101b5b71caa5fe219e69eb0d32c11222ccc92c8b +size 193971008 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q3_K_S.gguf b/Tralalabs_CHEETAH-350M-Merged-Q3_K_S.gguf new file mode 100644 index 0000000..f4d0fa6 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09c465dac2656818aa51059adeaf8eb6a9a1da2a221dbbd1a440fd5c9956f50 +size 181969728 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q3_K_XL.gguf b/Tralalabs_CHEETAH-350M-Merged-Q3_K_XL.gguf new file mode 100644 index 0000000..f807ea5 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f610774fffd3bb8f0b9ea46a17f63ec54a6900f2899b25c1d8778a8f0aa2573 +size 219333440 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q4_0.gguf b/Tralalabs_CHEETAH-350M-Merged-Q4_0.gguf new file mode 100644 index 0000000..d77019c --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56fcb542fb88d03e5c55eacb61af0db12f60b113f3d8a03f4daadadb7f7c687 +size 220439360 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q4_1.gguf b/Tralalabs_CHEETAH-350M-Merged-Q4_1.gguf new file mode 100644 index 0000000..7f8461c --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df8e9bb4235e096733e52c127927d81c4eb291e40264d6b0bb0032b4f65236b +size 237675328 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q4_K_L.gguf b/Tralalabs_CHEETAH-350M-Merged-Q4_K_L.gguf new file mode 100644 index 0000000..908485e --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4baf41bebd46029b5d8b1e9d7c673b14e79d63a95410d91778536ccd702fc183 +size 247284544 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q4_K_M.gguf b/Tralalabs_CHEETAH-350M-Merged-Q4_K_M.gguf new file mode 100644 index 0000000..0743aaf --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb38362a9574e76baa65a2d53ee68bc8d44c2f148c086aaa037f49b5bf4a37f +size 231031616 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q4_K_S.gguf b/Tralalabs_CHEETAH-350M-Merged-Q4_K_S.gguf new file mode 100644 index 0000000..ec5ab07 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d09fbca53eb640da23fcee5098f3903ea8248e1def3450e4e4c447e7bfb1254 +size 221160256 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q5_K_L.gguf b/Tralalabs_CHEETAH-350M-Merged-Q5_K_L.gguf new file mode 100644 index 0000000..6ca16a1 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0db5a1059a296985a6fee9e3ed634193b6efb6c38197e1a5f012e695586e3c6 +size 278160192 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q5_K_M.gguf b/Tralalabs_CHEETAH-350M-Merged-Q5_K_M.gguf new file mode 100644 index 0000000..88dc581 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811149037694f8f1b96691d610dc67b85866ce56034e1a8036a3c6fd215d70fb +size 261907264 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q5_K_S.gguf b/Tralalabs_CHEETAH-350M-Merged-Q5_K_S.gguf new file mode 100644 index 0000000..843e80b --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2959f176c192764d9abc9de4e76b29540fc858a4391f5bd4125b21491bf1a2 +size 255501120 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q6_K.gguf b/Tralalabs_CHEETAH-350M-Merged-Q6_K.gguf new file mode 100644 index 0000000..2f2ad69 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0d76ee36f8b56bef4c8dd97748b67eeb9b94a6e15fdd935ef1bd62ec3f2051 +size 296428352 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q6_K_L.gguf b/Tralalabs_CHEETAH-350M-Merged-Q6_K_L.gguf new file mode 100644 index 0000000..77681df --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384f3bbf2667008ebf649c6167647f47a90363f10125b7698a49cfbbbc21ca55 +size 312681280 diff --git a/Tralalabs_CHEETAH-350M-Merged-Q8_0.gguf b/Tralalabs_CHEETAH-350M-Merged-Q8_0.gguf new file mode 100644 index 0000000..7c1c110 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39bcddf8ca53dea4008d51018b5936e7ebfb0b40857c3f9c0de361f09a6a4dc7 +size 379216704 diff --git a/Tralalabs_CHEETAH-350M-Merged-bf16.gguf b/Tralalabs_CHEETAH-350M-Merged-bf16.gguf new file mode 100644 index 0000000..eaba3fd --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbb9367ca3084874675afd9c76faf595581481d89e9be7154dcaa82e8f9b9db +size 711483936 diff --git a/Tralalabs_CHEETAH-350M-Merged-imatrix.gguf b/Tralalabs_CHEETAH-350M-Merged-imatrix.gguf new file mode 100644 index 0000000..108b7f3 --- /dev/null +++ b/Tralalabs_CHEETAH-350M-Merged-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:318c432f8dd161bf465bbd2bce73f263a65d547c6e39c54a68422eeaa1927738 +size 620864