commit 6b6677434ba72a451fa200ef57ab8986c8851762 Author: ModelHub XC Date: Wed May 27 01:58:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/TitleOS_Lightning-1.7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c4c65a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.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 + +TitleOS_Lightning-1.7B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TitleOS_Lightning-1.7B-bf16.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..f057f1e --- /dev/null +++ b/README.md @@ -0,0 +1,184 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: TitleOS/Lightning-1.7B +base_model_relation: quantized +tags: +- lightning +- hermes-3 +- utility +- on-device +- text-generation +- finetune +model_creator: TitleOS +license: mpl-2.0 +inference: true +language: +- en +datasets: +- NousResearch/Hermes-3-Dataset +--- + +## Llamacpp imatrix Quantizations of Lightning-1.7B by TitleOS + +Using llama.cpp release b7340 for quantization. + +Original model: https://huggingface.co/TitleOS/Lightning-1.7B + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Lightning-1.7B-bf16.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-bf16.gguf) | bf16 | 3.45GB | false | Full BF16 weights. | +| [Lightning-1.7B-Q8_0.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q8_0.gguf) | Q8_0 | 1.83GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Lightning-1.7B-Q6_K_L.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q6_K_L.gguf) | Q6_K_L | 1.49GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Lightning-1.7B-Q6_K.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q6_K.gguf) | Q6_K | 1.42GB | false | Very high quality, near perfect, *recommended*. | +| [Lightning-1.7B-Q5_K_L.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q5_K_L.gguf) | Q5_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Lightning-1.7B-Q5_K_M.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q5_K_M.gguf) | Q5_K_M | 1.26GB | false | High quality, *recommended*. | +| [Lightning-1.7B-Q5_K_S.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q5_K_S.gguf) | Q5_K_S | 1.23GB | false | High quality, *recommended*. | +| [Lightning-1.7B-Q4_K_L.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q4_K_L.gguf) | Q4_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Lightning-1.7B-Q4_1.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q4_1.gguf) | Q4_1 | 1.14GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Lightning-1.7B-Q4_K_M.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q4_K_M.gguf) | Q4_K_M | 1.11GB | false | Good quality, default size for most use cases, *recommended*. | +| [Lightning-1.7B-Q3_K_XL.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q3_K_XL.gguf) | Q3_K_XL | 1.08GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Lightning-1.7B-Q4_K_S.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q4_K_S.gguf) | Q4_K_S | 1.06GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Lightning-1.7B-Q4_0.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q4_0.gguf) | Q4_0 | 1.06GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Lightning-1.7B-IQ4_NL.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ4_NL.gguf) | IQ4_NL | 1.05GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Lightning-1.7B-IQ4_XS.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ4_XS.gguf) | IQ4_XS | 1.01GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Lightning-1.7B-Q3_K_L.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q3_K_L.gguf) | Q3_K_L | 1.00GB | false | Lower quality but usable, good for low RAM availability. | +| [Lightning-1.7B-Q3_K_M.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q3_K_M.gguf) | Q3_K_M | 0.94GB | false | Low quality. | +| [Lightning-1.7B-IQ3_M.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ3_M.gguf) | IQ3_M | 0.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Lightning-1.7B-Q3_K_S.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q3_K_S.gguf) | Q3_K_S | 0.87GB | false | Low quality, not recommended. | +| [Lightning-1.7B-Q2_K_L.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q2_K_L.gguf) | Q2_K_L | 0.85GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Lightning-1.7B-IQ3_XS.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ3_XS.gguf) | IQ3_XS | 0.83GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Lightning-1.7B-Q2_K.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-Q2_K.gguf) | Q2_K | 0.78GB | false | Very low quality but surprisingly usable. | +| [Lightning-1.7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ3_XXS.gguf) | IQ3_XXS | 0.75GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Lightning-1.7B-IQ2_M.gguf](https://huggingface.co/bartowski/TitleOS_Lightning-1.7B-GGUF/blob/main/TitleOS_Lightning-1.7B-IQ2_M.gguf) | IQ2_M | 0.70GB | 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/TitleOS_Lightning-1.7B-GGUF --include "TitleOS_Lightning-1.7B-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/TitleOS_Lightning-1.7B-GGUF --include "TitleOS_Lightning-1.7B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (TitleOS_Lightning-1.7B-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/TitleOS_Lightning-1.7B-IQ2_M.gguf b/TitleOS_Lightning-1.7B-IQ2_M.gguf new file mode 100644 index 0000000..12d8d41 --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06efdd02c1656fe7396b45a7bcaff729ee88b2e0f4b3876d38d565cc68ed1052 +size 695181376 diff --git a/TitleOS_Lightning-1.7B-IQ3_M.gguf b/TitleOS_Lightning-1.7B-IQ3_M.gguf new file mode 100644 index 0000000..1a23e22 --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7043e081f15cb6aaa6639df63a176d999cea9fe97b4f7cb237eb644281fbbdca +size 895662144 diff --git a/TitleOS_Lightning-1.7B-IQ3_XS.gguf b/TitleOS_Lightning-1.7B-IQ3_XS.gguf new file mode 100644 index 0000000..e0c53d1 --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee06da9937935e077091eb67652df08c4278e8c1718ce4562b0427fc19db11ba +size 834222144 diff --git a/TitleOS_Lightning-1.7B-IQ3_XXS.gguf b/TitleOS_Lightning-1.7B-IQ3_XXS.gguf new file mode 100644 index 0000000..dc5746f --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd60f0d0122efff0c882b5734864996b9264134b4d89507a9170e4a27030e3f9 +size 754360384 diff --git a/TitleOS_Lightning-1.7B-IQ4_NL.gguf b/TitleOS_Lightning-1.7B-IQ4_NL.gguf new file mode 100644 index 0000000..ecd6237 --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a296ba77449efba2fd937611f32bccb44db21f0d1264764dba5f80a3334a720 +size 1054423104 diff --git a/TitleOS_Lightning-1.7B-IQ4_XS.gguf b/TitleOS_Lightning-1.7B-IQ4_XS.gguf new file mode 100644 index 0000000..ae8d322 --- /dev/null +++ b/TitleOS_Lightning-1.7B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3644f427d492bd6846e8f292e17780265c6162497e1be7552fd1172071b6ba +size 1010382912 diff --git a/TitleOS_Lightning-1.7B-Q2_K.gguf b/TitleOS_Lightning-1.7B-Q2_K.gguf new file mode 100644 index 0000000..8d68e98 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af121d68633514c6295d49ee527374444c60a511f9d56e17d92ca62ee74c890 +size 777795648 diff --git a/TitleOS_Lightning-1.7B-Q2_K_L.gguf b/TitleOS_Lightning-1.7B-Q2_K_L.gguf new file mode 100644 index 0000000..6d90dae --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbba9126d6469bc8b91462f041ab26ca665eb48eca324b510a2da9b9d5874ec +size 853155904 diff --git a/TitleOS_Lightning-1.7B-Q3_K_L.gguf b/TitleOS_Lightning-1.7B-Q3_K_L.gguf new file mode 100644 index 0000000..86efabe --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63630777a44182b6f1f6423c49efbb3c348b323d254cb05f79329a8911e7e34 +size 1003501632 diff --git a/TitleOS_Lightning-1.7B-Q3_K_M.gguf b/TitleOS_Lightning-1.7B-Q3_K_M.gguf new file mode 100644 index 0000000..90b865f --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bf47a90392b625bcb6afbcf65bedec56199dca3bf324d5f725970ab38a11a0 +size 939538496 diff --git a/TitleOS_Lightning-1.7B-Q3_K_S.gguf b/TitleOS_Lightning-1.7B-Q3_K_S.gguf new file mode 100644 index 0000000..81ef494 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691b48c4560f6ab3f8e5a3110eadb302d291a6dbae4670af480b2e208b79d2bd +size 867252288 diff --git a/TitleOS_Lightning-1.7B-Q3_K_XL.gguf b/TitleOS_Lightning-1.7B-Q3_K_XL.gguf new file mode 100644 index 0000000..32a6b14 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53649c785bdfc25e7432bbd872228c67a00632d64f5913d10982ab0df155ec6a +size 1078861888 diff --git a/TitleOS_Lightning-1.7B-Q4_0.gguf b/TitleOS_Lightning-1.7B-Q4_0.gguf new file mode 100644 index 0000000..140c32c --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab955648de9ef0969aeb20513c0c2925d90647b6c5a2525971c3c9d3fbfd411 +size 1056782400 diff --git a/TitleOS_Lightning-1.7B-Q4_1.gguf b/TitleOS_Lightning-1.7B-Q4_1.gguf new file mode 100644 index 0000000..4186afc --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a23e181802401afbe5f6de0c7ed193c8e778d8d8ca2d7847a1ff7c813309ac +size 1142503488 diff --git a/TitleOS_Lightning-1.7B-Q4_K_L.gguf b/TitleOS_Lightning-1.7B-Q4_K_L.gguf new file mode 100644 index 0000000..161b3c3 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3cd7a91b459acc3974cd6b0025dbdfd4d7446cc034512ee03d5002e4d40975 +size 1182769216 diff --git a/TitleOS_Lightning-1.7B-Q4_K_M.gguf b/TitleOS_Lightning-1.7B-Q4_K_M.gguf new file mode 100644 index 0000000..8bc2770 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc18e6a5bf99b6d9047669102aa0df22624dcfcf3700c99aa403e3aa6189500 +size 1107408960 diff --git a/TitleOS_Lightning-1.7B-Q4_K_S.gguf b/TitleOS_Lightning-1.7B-Q4_K_S.gguf new file mode 100644 index 0000000..f238002 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ee68931bc742ccac9d4526e79fedc1b5bfca0b06a53cfdb9ac030a27ea5f16 +size 1060190272 diff --git a/TitleOS_Lightning-1.7B-Q5_K_L.gguf b/TitleOS_Lightning-1.7B-Q5_K_L.gguf new file mode 100644 index 0000000..5a37259 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d396c1f4b51dfb0dd74a335918df3b39d027cd34d15ae3270aa65c75d537cf37 +size 1333239872 diff --git a/TitleOS_Lightning-1.7B-Q5_K_M.gguf b/TitleOS_Lightning-1.7B-Q5_K_M.gguf new file mode 100644 index 0000000..29f8368 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f72b024ba46016ec50338efd471d490c1502365b25bcbb2d59c3fb19aba94b +size 1257879616 diff --git a/TitleOS_Lightning-1.7B-Q5_K_S.gguf b/TitleOS_Lightning-1.7B-Q5_K_S.gguf new file mode 100644 index 0000000..9f0bf0b --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a224b579eb58c21899f75318e6fef2a0b264382c84f68e7567ef44b7db487f0c +size 1230583872 diff --git a/TitleOS_Lightning-1.7B-Q6_K.gguf b/TitleOS_Lightning-1.7B-Q6_K.gguf new file mode 100644 index 0000000..0457a6d --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533b97de05430416ec52ec51d9788b81d7feaf812f9f06336e4608d11c90b18c +size 1417754688 diff --git a/TitleOS_Lightning-1.7B-Q6_K_L.gguf b/TitleOS_Lightning-1.7B-Q6_K_L.gguf new file mode 100644 index 0000000..9ca1a4e --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a68b9aae8f1ebe016fc98f261b56f52272ec728dc0a0353a631296b77924d30 +size 1493114944 diff --git a/TitleOS_Lightning-1.7B-Q8_0.gguf b/TitleOS_Lightning-1.7B-Q8_0.gguf new file mode 100644 index 0000000..26c5b20 --- /dev/null +++ b/TitleOS_Lightning-1.7B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28bfcd316286668310b748e1fa2078a07dacb17b0842dc62f53abbdb2fb2306 +size 1834426432 diff --git a/TitleOS_Lightning-1.7B-bf16.gguf b/TitleOS_Lightning-1.7B-bf16.gguf new file mode 100644 index 0000000..a8eeada --- /dev/null +++ b/TitleOS_Lightning-1.7B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c5d01534f9cd35c9bd96c18585df42edb4b03ca7ab6ee0de8a5620ebf65707 +size 3447349024 diff --git a/TitleOS_Lightning-1.7B-imatrix.gguf b/TitleOS_Lightning-1.7B-imatrix.gguf new file mode 100644 index 0000000..2cdf416 --- /dev/null +++ b/TitleOS_Lightning-1.7B-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf1b7b0b4474205931a2f46dbf204bfea3ee172366e7fe4a066e49442ec3de4 +size 2094560 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