commit 9184e8c4cbb021f85e6b54c339c843a1f467deeb Author: ModelHub XC Date: Tue Jun 30 14:09:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/gemma-2-9b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..787cce5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 +gemma-2-9b-it-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-f32.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it.imatrix filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K-Q8.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q6_K-f32.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q3_K_L-Q8.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q4_K_M-fp16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-Q8_0-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdc07b3 --- /dev/null +++ b/README.md @@ -0,0 +1,115 @@ +--- +base_model: google/gemma-2-9b-it +library_name: transformers +license: gemma +pipeline_tag: text-generation +tags: +- conversational +quantized_by: bartowski +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +extra_gated_button_content: Acknowledge license +--- + +## Llamacpp imatrix Quantizations of gemma-2-9b-it + +Using llama.cpp release b3389 for quantization. + +Original model: https://huggingface.co/google/gemma-2-9b-it + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +## Prompt format + +``` +user +{prompt} +model + +model + +``` + +Note that this model does not support a System prompt. + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [gemma-2-9b-it-f32.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-f32.gguf) | f32 | 36.97GB | false | Full F32 weights. | +| [gemma-2-9b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q8_0.gguf) | Q8_0 | 9.83GB | false | Extremely high quality, generally unneeded but max available quant. | +| [gemma-2-9b-it-Q6_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K_L.gguf) | Q6_K_L | 7.81GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [gemma-2-9b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q6_K.gguf) | Q6_K | 7.59GB | false | Very high quality, near perfect, *recommended*. | +| [gemma-2-9b-it-Q5_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_L.gguf) | Q5_K_L | 6.87GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [gemma-2-9b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_M.gguf) | Q5_K_M | 6.65GB | false | High quality, *recommended*. | +| [gemma-2-9b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q5_K_S.gguf) | Q5_K_S | 6.48GB | false | High quality, *recommended*. | +| [gemma-2-9b-it-Q4_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_L.gguf) | Q4_K_L | 5.98GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [gemma-2-9b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_M.gguf) | Q4_K_M | 5.76GB | false | Good quality, default size for must use cases, *recommended*. | +| [gemma-2-9b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q4_K_S.gguf) | Q4_K_S | 5.48GB | false | Slightly lower quality with more space savings, *recommended*. | +| [gemma-2-9b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ4_XS.gguf) | IQ4_XS | 5.18GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [gemma-2-9b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_L.gguf) | Q3_K_L | 5.13GB | false | Lower quality but usable, good for low RAM availability. | +| [gemma-2-9b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_M.gguf) | Q3_K_M | 4.76GB | false | Low quality. | +| [gemma-2-9b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_M.gguf) | IQ3_M | 4.49GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [gemma-2-9b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q3_K_S.gguf) | Q3_K_S | 4.34GB | false | Low quality, not recommended. | +| [gemma-2-9b-it-IQ3_XS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XS.gguf) | IQ3_XS | 4.14GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [gemma-2-9b-it-Q2_K_L.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K_L.gguf) | Q2_K_L | 4.03GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [gemma-2-9b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-Q2_K.gguf) | Q2_K | 3.81GB | false | Very low quality but surprisingly usable. | +| [gemma-2-9b-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ3_XXS.gguf) | IQ3_XXS | 3.80GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [gemma-2-9b-it-IQ2_M.gguf](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF/blob/main/gemma-2-9b-it-IQ2_M.gguf) | IQ2_M | 3.43GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## 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 + +## Downloading using huggingface-cli + +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/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-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/gemma-2-9b-it-GGUF --include "gemma-2-9b-it-Q8_0.gguf/*" --local-dir gemma-2-9b-it-Q8_0 +``` + +You can either specify a new local-dir (gemma-2-9b-it-Q8_0) or download them all in place (./) + +## Which file should I choose? + +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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. + +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/gemma-2-9b-it-IQ2_M.gguf b/gemma-2-9b-it-IQ2_M.gguf new file mode 100644 index 0000000..77fd436 --- /dev/null +++ b/gemma-2-9b-it-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e152459c333bc687d3829e551e9c9c3f51abc087ba9f87d82033847e48db3df4 +size 3434668992 diff --git a/gemma-2-9b-it-IQ2_S.gguf b/gemma-2-9b-it-IQ2_S.gguf new file mode 100644 index 0000000..23f7d2a --- /dev/null +++ b/gemma-2-9b-it-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0725ca79e7415d9a23d0cdcd3f2376c1b989777dd07cd8c088af23bb4fc1fa28 +size 3211487104 diff --git a/gemma-2-9b-it-IQ2_XS.gguf b/gemma-2-9b-it-IQ2_XS.gguf new file mode 100644 index 0000000..5fd3394 --- /dev/null +++ b/gemma-2-9b-it-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010fb98c74fd5b413008adb14f62a0a6886883936dbc5693f45fd389b54bfd40 +size 3067381632 diff --git a/gemma-2-9b-it-IQ3_M.gguf b/gemma-2-9b-it-IQ3_M.gguf new file mode 100644 index 0000000..c646fc6 --- /dev/null +++ b/gemma-2-9b-it-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d117938c5ebd91f0cbe1962236d04b42a716b03ebf54560196773f51bd1b2acb +size 4494615488 diff --git a/gemma-2-9b-it-IQ3_XS.gguf b/gemma-2-9b-it-IQ3_XS.gguf new file mode 100644 index 0000000..eda7d27 --- /dev/null +++ b/gemma-2-9b-it-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379fb78fa6453222a54d85ed04cb376663ccc838347412eccab587290c8df1b9 +size 4144989120 diff --git a/gemma-2-9b-it-IQ3_XXS.gguf b/gemma-2-9b-it-IQ3_XXS.gguf new file mode 100644 index 0000000..52e24d8 --- /dev/null +++ b/gemma-2-9b-it-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a57501217fee57586ec916fe196cce8e0f98d9a493eb817f3f27ea75b4904c9 +size 3796739008 diff --git a/gemma-2-9b-it-IQ4_XS.gguf b/gemma-2-9b-it-IQ4_XS.gguf new file mode 100644 index 0000000..137e448 --- /dev/null +++ b/gemma-2-9b-it-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c79966f200495368e8d1d4fecefbfdd0176327ec76968522c6fe13c397ad5d58 +size 5183030208 diff --git a/gemma-2-9b-it-Q2_K.gguf b/gemma-2-9b-it-Q2_K.gguf new file mode 100644 index 0000000..c23e5d8 --- /dev/null +++ b/gemma-2-9b-it-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efce51c0d774a47c247c07ec6f109f670e3da4f4eec0f9322d72e3635622403 +size 3805397952 diff --git a/gemma-2-9b-it-Q2_K_L.gguf b/gemma-2-9b-it-Q2_K_L.gguf new file mode 100644 index 0000000..08518ae --- /dev/null +++ b/gemma-2-9b-it-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0c08d499a7a491f50bf68c6b925a27134a98f6a1fbcfbdeec558297884ea72 +size 4027605952 diff --git a/gemma-2-9b-it-Q3_K_L-Q8.gguf b/gemma-2-9b-it-Q3_K_L-Q8.gguf new file mode 100644 index 0000000..7d4e106 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_L-Q8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a45c72fee34ade31f7fcd2eec5e7eaafb51d7e1e80fe1762eff1a33e83d2fc +size 5354661760 diff --git a/gemma-2-9b-it-Q3_K_L.gguf b/gemma-2-9b-it-Q3_K_L.gguf new file mode 100644 index 0000000..a9d556b --- /dev/null +++ b/gemma-2-9b-it-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38fbe0303ac54882c72fd28f636abf731e4bd813809c7a1cffc829980391bcb3 +size 5132452800 diff --git a/gemma-2-9b-it-Q3_K_M.gguf b/gemma-2-9b-it-Q3_K_M.gguf new file mode 100644 index 0000000..e5b3452 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5cb881500b1f72d456784a70214c8e49b7b3f49dae4fe524ca2c19e650b18b +size 4761781184 diff --git a/gemma-2-9b-it-Q3_K_S.gguf b/gemma-2-9b-it-Q3_K_S.gguf new file mode 100644 index 0000000..322d0a0 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594a305f4806f982808a07e0271e6e9354e4557c2a1a72383005b41b200830d8 +size 4337664960 diff --git a/gemma-2-9b-it-Q3_K_XL.gguf b/gemma-2-9b-it-Q3_K_XL.gguf new file mode 100644 index 0000000..73b27a4 --- /dev/null +++ b/gemma-2-9b-it-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6609cc2ebba6311806ee84116af44e7fb26762f116572a8181aad4a5da5c9e95 +size 5354660768 diff --git a/gemma-2-9b-it-Q4_K_L.gguf b/gemma-2-9b-it-Q4_K_L.gguf new file mode 100644 index 0000000..b1ce12c --- /dev/null +++ b/gemma-2-9b-it-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8573f0d1e3ca58e471498fd162a65d4f4253dffdec28a7ba394fdcae92f1f3 +size 5983265728 diff --git a/gemma-2-9b-it-Q4_K_M-fp16.gguf b/gemma-2-9b-it-Q4_K_M-fp16.gguf new file mode 100644 index 0000000..d46d2d2 --- /dev/null +++ b/gemma-2-9b-it-Q4_K_M-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0452e54ba9b6c5b2e466fbd7f28c089fefb7c3dceddcc2b75becab6b16cae523 +size 6843425696 diff --git a/gemma-2-9b-it-Q4_K_M.gguf b/gemma-2-9b-it-Q4_K_M.gguf new file mode 100644 index 0000000..da83fd7 --- /dev/null +++ b/gemma-2-9b-it-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b2a7b4115bbd0900162edcebe476da1ba1fc24e718e8b40d32f6e300f56dfe +size 5761057728 diff --git a/gemma-2-9b-it-Q4_K_S.gguf b/gemma-2-9b-it-Q4_K_S.gguf new file mode 100644 index 0000000..e7257fb --- /dev/null +++ b/gemma-2-9b-it-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fd8af95257d1e39fa3bab7f4e4f7af65812f4fe017a808913f3c1c7151d33a +size 5478925248 diff --git a/gemma-2-9b-it-Q5_K_L.gguf b/gemma-2-9b-it-Q5_K_L.gguf new file mode 100644 index 0000000..0d6b7dd --- /dev/null +++ b/gemma-2-9b-it-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcff2482f87cf4ba5bf0dca01cbde26abc9c77aa0caac0a792636219ce827e75 +size 6869574592 diff --git a/gemma-2-9b-it-Q5_K_M.gguf b/gemma-2-9b-it-Q5_K_M.gguf new file mode 100644 index 0000000..a94d642 --- /dev/null +++ b/gemma-2-9b-it-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b0b55ce809a09baaefb789b0046ac77ecd502aba8aeb2ed63cc237d9f40ce7 +size 6647366592 diff --git a/gemma-2-9b-it-Q5_K_S.gguf b/gemma-2-9b-it-Q5_K_S.gguf new file mode 100644 index 0000000..af6aa76 --- /dev/null +++ b/gemma-2-9b-it-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca83ab1d6a8df1f2b82ba2889dfeae77b878386ba60b8f55bad8cd370e2cc738 +size 6483592128 diff --git a/gemma-2-9b-it-Q6_K-Q8.gguf b/gemma-2-9b-it-Q6_K-Q8.gguf new file mode 100644 index 0000000..c417ffa --- /dev/null +++ b/gemma-2-9b-it-Q6_K-Q8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e000b337787bd1cf2f07bbcf31709e6ff4fad7f383156741e674027d4038277 +size 7811278720 diff --git a/gemma-2-9b-it-Q6_K-f32.gguf b/gemma-2-9b-it-Q6_K-f32.gguf new file mode 100644 index 0000000..4face57 --- /dev/null +++ b/gemma-2-9b-it-Q6_K-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b36d8f25b92b38a3c193f8e382f3df13699db42f65b124948db74b1f0a6b21b +size 10506446720 diff --git a/gemma-2-9b-it-Q6_K.gguf b/gemma-2-9b-it-Q6_K.gguf new file mode 100644 index 0000000..b414dc9 --- /dev/null +++ b/gemma-2-9b-it-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ea6fe1a4a8005ef6a0b379a87d271028cfa1b0be5fa2848e30419653d717a4 +size 7589069760 diff --git a/gemma-2-9b-it-Q6_K_L.gguf b/gemma-2-9b-it-Q6_K_L.gguf new file mode 100644 index 0000000..e4c603e --- /dev/null +++ b/gemma-2-9b-it-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497f1c006183cd186fb3503d90b80ba9a4518d8f6146a1f8e69615b20511c678 +size 7811277760 diff --git a/gemma-2-9b-it-Q8_0-f16.gguf b/gemma-2-9b-it-Q8_0-f16.gguf new file mode 100644 index 0000000..9357cd7 --- /dev/null +++ b/gemma-2-9b-it-Q8_0-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9cfe355265a0f78c4942e1a6cc6b7113ddb75748f7f1267490abfb34b0abc4 +size 10687308704 diff --git a/gemma-2-9b-it-Q8_0.gguf b/gemma-2-9b-it-Q8_0.gguf new file mode 100644 index 0000000..9c17e0f --- /dev/null +++ b/gemma-2-9b-it-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ac9ec01217d7bf2976a3a0dbf564a91b6957f94ab2ad30671eb6100f64bc2b +size 9827148736 diff --git a/gemma-2-9b-it-Q8_0_L.gguf b/gemma-2-9b-it-Q8_0_L.gguf new file mode 100644 index 0000000..f392175 --- /dev/null +++ b/gemma-2-9b-it-Q8_0_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19cb326ba857bec47383ada7af3b0fd965605a44e0a3b6ab0b1e080a541597a +size 10687309696 diff --git a/gemma-2-9b-it-f32.gguf b/gemma-2-9b-it-f32.gguf new file mode 100644 index 0000000..97b36af --- /dev/null +++ b/gemma-2-9b-it-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2d53301d4e91f0c3a1835df213af9334eaccb08be76afd694ec2101b57bdaa +size 36972880544 diff --git a/gemma-2-9b-it.imatrix b/gemma-2-9b-it.imatrix new file mode 100644 index 0000000..896565f --- /dev/null +++ b/gemma-2-9b-it.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f30bcab948c839ffd9855c98ec76bffb7f5cae8d301d556ee8a96f5832058b +size 6116900