From 11f6896f4befff0adc595c1c1204457d0c29ddaf Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 28 Aug 2026 04:20:21 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: bartowski/inclusionAI_Ling-lite-GGUF Source: Original Platform --- .gitattributes | 49 +++++++++ README.md | 169 +++++++++++++++++++++++++++++ configuration.json | 1 + inclusionAI_Ling-lite-IQ2_M.gguf | 3 + inclusionAI_Ling-lite-IQ2_S.gguf | 3 + inclusionAI_Ling-lite-IQ2_XS.gguf | 3 + inclusionAI_Ling-lite-IQ3_M.gguf | 3 + inclusionAI_Ling-lite-IQ3_XS.gguf | 3 + inclusionAI_Ling-lite-IQ3_XXS.gguf | 3 + inclusionAI_Ling-lite-IQ4_NL.gguf | 3 + inclusionAI_Ling-lite-IQ4_XS.gguf | 3 + inclusionAI_Ling-lite-Q2_K.gguf | 3 + inclusionAI_Ling-lite-Q2_K_L.gguf | 3 + inclusionAI_Ling-lite-Q3_K_L.gguf | 3 + inclusionAI_Ling-lite-Q3_K_M.gguf | 3 + inclusionAI_Ling-lite-Q3_K_S.gguf | 3 + inclusionAI_Ling-lite-Q3_K_XL.gguf | 3 + inclusionAI_Ling-lite-Q4_0.gguf | 3 + inclusionAI_Ling-lite-Q4_1.gguf | 3 + inclusionAI_Ling-lite-Q4_K_L.gguf | 3 + inclusionAI_Ling-lite-Q4_K_M.gguf | 3 + inclusionAI_Ling-lite-Q4_K_S.gguf | 3 + inclusionAI_Ling-lite-Q5_K_L.gguf | 3 + inclusionAI_Ling-lite-Q5_K_M.gguf | 3 + inclusionAI_Ling-lite-Q5_K_S.gguf | 3 + inclusionAI_Ling-lite-Q6_K.gguf | 3 + inclusionAI_Ling-lite-Q6_K_L.gguf | 3 + inclusionAI_Ling-lite-Q8_0.gguf | 3 + inclusionAI_Ling-lite-bf16.gguf | 3 + inclusionAI_Ling-lite.imatrix | 3 + 30 files changed, 300 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 configuration.json create mode 100644 inclusionAI_Ling-lite-IQ2_M.gguf create mode 100644 inclusionAI_Ling-lite-IQ2_S.gguf create mode 100644 inclusionAI_Ling-lite-IQ2_XS.gguf create mode 100644 inclusionAI_Ling-lite-IQ3_M.gguf create mode 100644 inclusionAI_Ling-lite-IQ3_XS.gguf create mode 100644 inclusionAI_Ling-lite-IQ3_XXS.gguf create mode 100644 inclusionAI_Ling-lite-IQ4_NL.gguf create mode 100644 inclusionAI_Ling-lite-IQ4_XS.gguf create mode 100644 inclusionAI_Ling-lite-Q2_K.gguf create mode 100644 inclusionAI_Ling-lite-Q2_K_L.gguf create mode 100644 inclusionAI_Ling-lite-Q3_K_L.gguf create mode 100644 inclusionAI_Ling-lite-Q3_K_M.gguf create mode 100644 inclusionAI_Ling-lite-Q3_K_S.gguf create mode 100644 inclusionAI_Ling-lite-Q3_K_XL.gguf create mode 100644 inclusionAI_Ling-lite-Q4_0.gguf create mode 100644 inclusionAI_Ling-lite-Q4_1.gguf create mode 100644 inclusionAI_Ling-lite-Q4_K_L.gguf create mode 100644 inclusionAI_Ling-lite-Q4_K_M.gguf create mode 100644 inclusionAI_Ling-lite-Q4_K_S.gguf create mode 100644 inclusionAI_Ling-lite-Q5_K_L.gguf create mode 100644 inclusionAI_Ling-lite-Q5_K_M.gguf create mode 100644 inclusionAI_Ling-lite-Q5_K_S.gguf create mode 100644 inclusionAI_Ling-lite-Q6_K.gguf create mode 100644 inclusionAI_Ling-lite-Q6_K_L.gguf create mode 100644 inclusionAI_Ling-lite-Q8_0.gguf create mode 100644 inclusionAI_Ling-lite-bf16.gguf create mode 100644 inclusionAI_Ling-lite.imatrix diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e9db2b --- /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 + +inclusionAI_Ling-lite.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..d428dd9 --- /dev/null +++ b/README.md @@ -0,0 +1,169 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: inclusionAI/Ling-lite +license: mit +--- + +## Llamacpp imatrix Quantizations of Ling-lite by inclusionAI + +Using llama.cpp release b5035 for quantization. + +Original model: https://huggingface.co/inclusionAI/Ling-lite + +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 + +``` +SYSTEM{system_prompt}HUMAN{prompt}ASSISTANTASSISTANT +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Ling-lite-bf16.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-bf16.gguf) | bf16 | 33.62GB | false | Full BF16 weights. | +| [Ling-lite-Q8_0.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q8_0.gguf) | Q8_0 | 17.87GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Ling-lite-Q6_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q6_K_L.gguf) | Q6_K_L | 15.18GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Ling-lite-Q6_K.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q6_K.gguf) | Q6_K | 15.05GB | false | Very high quality, near perfect, *recommended*. | +| [Ling-lite-Q5_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q5_K_L.gguf) | Q5_K_L | 12.91GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Ling-lite-Q5_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q5_K_M.gguf) | Q5_K_M | 12.75GB | false | High quality, *recommended*. | +| [Ling-lite-Q5_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q5_K_S.gguf) | Q5_K_S | 11.93GB | false | High quality, *recommended*. | +| [Ling-lite-Q4_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q4_K_L.gguf) | Q4_K_L | 11.37GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Ling-lite-Q4_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q4_K_M.gguf) | Q4_K_M | 11.18GB | false | Good quality, default size for most use cases, *recommended*. | +| [Ling-lite-Q4_1.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q4_1.gguf) | Q4_1 | 10.57GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Ling-lite-Q4_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q4_K_S.gguf) | Q4_K_S | 10.22GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Ling-lite-Q4_0.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q4_0.gguf) | Q4_0 | 9.57GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Ling-lite-IQ4_NL.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ4_NL.gguf) | IQ4_NL | 9.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Ling-lite-Q3_K_XL.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q3_K_XL.gguf) | Q3_K_XL | 9.30GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Ling-lite-IQ4_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ4_XS.gguf) | IQ4_XS | 9.19GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Ling-lite-Q3_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q3_K_L.gguf) | Q3_K_L | 9.07GB | false | Lower quality but usable, good for low RAM availability. | +| [Ling-lite-Q3_K_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q3_K_M.gguf) | Q3_K_M | 8.73GB | false | Low quality. | +| [Ling-lite-IQ3_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ3_M.gguf) | IQ3_M | 8.12GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Ling-lite-Q3_K_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q3_K_S.gguf) | Q3_K_S | 8.03GB | false | Low quality, not recommended. | +| [Ling-lite-IQ3_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ3_XS.gguf) | IQ3_XS | 7.65GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Ling-lite-IQ3_XXS.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ3_XXS.gguf) | IQ3_XXS | 7.47GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Ling-lite-Q2_K_L.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q2_K_L.gguf) | Q2_K_L | 7.16GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Ling-lite-Q2_K.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-Q2_K.gguf) | Q2_K | 6.91GB | false | Very low quality but surprisingly usable. | +| [Ling-lite-IQ2_M.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ2_M.gguf) | IQ2_M | 6.80GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Ling-lite-IQ2_S.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ2_S.gguf) | IQ2_S | 6.45GB | false | Low quality, uses SOTA techniques to be usable. | +| [Ling-lite-IQ2_XS.gguf](https://huggingface.co/bartowski/inclusionAI_Ling-lite-GGUF/blob/main/inclusionAI_Ling-lite-IQ2_XS.gguf) | IQ2_XS | 6.41GB | 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/inclusionAI_Ling-lite-GGUF --include "inclusionAI_Ling-lite-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/inclusionAI_Ling-lite-GGUF --include "inclusionAI_Ling-lite-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (inclusionAI_Ling-lite-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/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 diff --git a/inclusionAI_Ling-lite-IQ2_M.gguf b/inclusionAI_Ling-lite-IQ2_M.gguf new file mode 100644 index 0000000..4d88484 --- /dev/null +++ b/inclusionAI_Ling-lite-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b3e03a7d6f744e879edbaaa2be9eaf16138df10229efc99a1486439e5029aa +size 6796490304 diff --git a/inclusionAI_Ling-lite-IQ2_S.gguf b/inclusionAI_Ling-lite-IQ2_S.gguf new file mode 100644 index 0000000..260edfa --- /dev/null +++ b/inclusionAI_Ling-lite-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956a133953aef3279ee201a49f2a143d020d4d692cc614a5d2387ec9e6eedc08 +size 6453982784 diff --git a/inclusionAI_Ling-lite-IQ2_XS.gguf b/inclusionAI_Ling-lite-IQ2_XS.gguf new file mode 100644 index 0000000..284bc09 --- /dev/null +++ b/inclusionAI_Ling-lite-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400fcd2edcf19b1419ea78ec8fee8f8d24535fdac3f554fd414f063626fa3eaa +size 6410577472 diff --git a/inclusionAI_Ling-lite-IQ3_M.gguf b/inclusionAI_Ling-lite-IQ3_M.gguf new file mode 100644 index 0000000..6276e30 --- /dev/null +++ b/inclusionAI_Ling-lite-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0958fda2a7ce34cf7ebcc810056b7813762d567bd79f74b2698b9f86721f5deb +size 8116766272 diff --git a/inclusionAI_Ling-lite-IQ3_XS.gguf b/inclusionAI_Ling-lite-IQ3_XS.gguf new file mode 100644 index 0000000..62847c8 --- /dev/null +++ b/inclusionAI_Ling-lite-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a04cc947d983fbd45fabd04680e9592fe8281202b81413f1da007cdb7f634da +size 7648097856 diff --git a/inclusionAI_Ling-lite-IQ3_XXS.gguf b/inclusionAI_Ling-lite-IQ3_XXS.gguf new file mode 100644 index 0000000..927bedf --- /dev/null +++ b/inclusionAI_Ling-lite-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73da2f60547b228629e15c3d256c515931ec9f72436f200b2033d73d31077cdb +size 7472059968 diff --git a/inclusionAI_Ling-lite-IQ4_NL.gguf b/inclusionAI_Ling-lite-IQ4_NL.gguf new file mode 100644 index 0000000..f68b18c --- /dev/null +++ b/inclusionAI_Ling-lite-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49a41c800c3522544bcc57f939a58c46482233ed9e6ed893d552bba0234ecfbe +size 9539753536 diff --git a/inclusionAI_Ling-lite-IQ4_XS.gguf b/inclusionAI_Ling-lite-IQ4_XS.gguf new file mode 100644 index 0000000..77441b3 --- /dev/null +++ b/inclusionAI_Ling-lite-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e81477bee23adfaa9184b06cfb1d8b2c80613ff1d9ebddb46e86ac9ec1bcea7e +size 9185302080 diff --git a/inclusionAI_Ling-lite-Q2_K.gguf b/inclusionAI_Ling-lite-Q2_K.gguf new file mode 100644 index 0000000..2c029a6 --- /dev/null +++ b/inclusionAI_Ling-lite-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e8c55021acd6b93a45ac96ca51887198b0287b39e9d6865f35352720d86f63 +size 6906025536 diff --git a/inclusionAI_Ling-lite-Q2_K_L.gguf b/inclusionAI_Ling-lite-Q2_K_L.gguf new file mode 100644 index 0000000..ca89aa2 --- /dev/null +++ b/inclusionAI_Ling-lite-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14a4c3e8a9421c66ef689564f7821cadeab514aa3c3da2932dfb525a558987f5 +size 7158953536 diff --git a/inclusionAI_Ling-lite-Q3_K_L.gguf b/inclusionAI_Ling-lite-Q3_K_L.gguf new file mode 100644 index 0000000..7cee7e2 --- /dev/null +++ b/inclusionAI_Ling-lite-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066111709f2041604dd3f77317084058b94fad7ac0a768f3df37e692caa7f9a2 +size 9074128448 diff --git a/inclusionAI_Ling-lite-Q3_K_M.gguf b/inclusionAI_Ling-lite-Q3_K_M.gguf new file mode 100644 index 0000000..783b04e --- /dev/null +++ b/inclusionAI_Ling-lite-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efb32be1803e84bd40c96cd330e3da6215a4e5d85fb32845571d1760f8f9b26 +size 8725149248 diff --git a/inclusionAI_Ling-lite-Q3_K_S.gguf b/inclusionAI_Ling-lite-Q3_K_S.gguf new file mode 100644 index 0000000..d788a1a --- /dev/null +++ b/inclusionAI_Ling-lite-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a58cbfdcb28f822df339f1554c45a38372d8fa2c2948629418257023a695c923 +size 8025765440 diff --git a/inclusionAI_Ling-lite-Q3_K_XL.gguf b/inclusionAI_Ling-lite-Q3_K_XL.gguf new file mode 100644 index 0000000..bd69010 --- /dev/null +++ b/inclusionAI_Ling-lite-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b3568b67c330ce88a3def05a285cba5e3ebc0dc9e8494da49bb4f8c84202b9 +size 9300751936 diff --git a/inclusionAI_Ling-lite-Q4_0.gguf b/inclusionAI_Ling-lite-Q4_0.gguf new file mode 100644 index 0000000..4176a6e --- /dev/null +++ b/inclusionAI_Ling-lite-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6072ade86e1c349fa6dca1ec472d150d19ef08519415b3a94768255f9e9650eb +size 9571767872 diff --git a/inclusionAI_Ling-lite-Q4_1.gguf b/inclusionAI_Ling-lite-Q4_1.gguf new file mode 100644 index 0000000..71e0d58 --- /dev/null +++ b/inclusionAI_Ling-lite-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cc02cbcb2fca7fa2195b57a08bac7772158d412e85329db68d78983a08ad00 +size 10569782848 diff --git a/inclusionAI_Ling-lite-Q4_K_L.gguf b/inclusionAI_Ling-lite-Q4_K_L.gguf new file mode 100644 index 0000000..4977a71 --- /dev/null +++ b/inclusionAI_Ling-lite-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75c3e5ddf9e6975b65cc4168ba54897f44f09442682c18ef1eb8dc3f022d4ed +size 11367716416 diff --git a/inclusionAI_Ling-lite-Q4_K_M.gguf b/inclusionAI_Ling-lite-Q4_K_M.gguf new file mode 100644 index 0000000..3626537 --- /dev/null +++ b/inclusionAI_Ling-lite-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9182f47d0e7ab90cc860da187b62c45c776a6912f697992e877027e67f9f6a +size 11175491136 diff --git a/inclusionAI_Ling-lite-Q4_K_S.gguf b/inclusionAI_Ling-lite-Q4_K_S.gguf new file mode 100644 index 0000000..35cb9b9 --- /dev/null +++ b/inclusionAI_Ling-lite-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a032d9b667b2b1788820ba6c7069955b57933e361f1beea3caae482320612db8 +size 10219296320 diff --git a/inclusionAI_Ling-lite-Q5_K_L.gguf b/inclusionAI_Ling-lite-Q5_K_L.gguf new file mode 100644 index 0000000..8926de8 --- /dev/null +++ b/inclusionAI_Ling-lite-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f9b886bbb302881f4d95ef803a3ba5a17366347821f33c9f61abe7fd9366bd +size 12906370624 diff --git a/inclusionAI_Ling-lite-Q5_K_M.gguf b/inclusionAI_Ling-lite-Q5_K_M.gguf new file mode 100644 index 0000000..bc092e7 --- /dev/null +++ b/inclusionAI_Ling-lite-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e46b55358fded2f16fe91921125a8304da52205b493849f8f20408db0e3a6e9 +size 12746520128 diff --git a/inclusionAI_Ling-lite-Q5_K_S.gguf b/inclusionAI_Ling-lite-Q5_K_S.gguf new file mode 100644 index 0000000..748e189 --- /dev/null +++ b/inclusionAI_Ling-lite-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c287b0ccd7344e45e7bc902220d3b1b927886f20b1cfae19ab86d2eed8cb9dd2 +size 11926443584 diff --git a/inclusionAI_Ling-lite-Q6_K.gguf b/inclusionAI_Ling-lite-Q6_K.gguf new file mode 100644 index 0000000..d228f4e --- /dev/null +++ b/inclusionAI_Ling-lite-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df15126163b24315f7341630151c81ab995b41f5bd8dfd69ce8d1333fd19527 +size 15051568704 diff --git a/inclusionAI_Ling-lite-Q6_K_L.gguf b/inclusionAI_Ling-lite-Q6_K_L.gguf new file mode 100644 index 0000000..90bc799 --- /dev/null +++ b/inclusionAI_Ling-lite-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d0ae5fe7ca0342c746e9ce58e40ffd274546e173b9e1f5d3fc96ca2e14aeb6 +size 15177020992 diff --git a/inclusionAI_Ling-lite-Q8_0.gguf b/inclusionAI_Ling-lite-Q8_0.gguf new file mode 100644 index 0000000..20c0e02 --- /dev/null +++ b/inclusionAI_Ling-lite-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d7db35040c2743a77a661a3669bbcdaeca4cebac0ea77a9944a92657b713f3 +size 17868404288 diff --git a/inclusionAI_Ling-lite-bf16.gguf b/inclusionAI_Ling-lite-bf16.gguf new file mode 100644 index 0000000..4b9a813 --- /dev/null +++ b/inclusionAI_Ling-lite-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db0a5120723673ffbbe3b5c16f8301048952b7811fe4330266ee9900541cfc3 +size 33616704832 diff --git a/inclusionAI_Ling-lite.imatrix b/inclusionAI_Ling-lite.imatrix new file mode 100644 index 0000000..4865f8d --- /dev/null +++ b/inclusionAI_Ling-lite.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dd96de53314e381a5f368c42b14af217cf464d551ee0ba804668d07a1f08f0 +size 41384946