commit b1f958215bf8e78a14c8a10a1188a32f9b3544ee Author: ModelHub XC Date: Fri Sep 4 03:50:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/google_functiongemma-270m-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7401284 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,72 @@ +*.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 + +google_functiongemma-270m-it-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +google_functiongemma-270m-it-Q3_K_S.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..7ea730f --- /dev/null +++ b/README.md @@ -0,0 +1,181 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +extra_gated_prompt: To access FunctionGemma 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. +tags: +- gemma3 +- gemma +- google +- functiongemma +extra_gated_heading: Access Gemma on Hugging Face +license: gemma +extra_gated_button_content: Acknowledge license +base_model: google/functiongemma-270m-it +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of functiongemma-270m-it by google + +Using llama.cpp release b7429 for quantization. + +Original model: https://huggingface.co/google/functiongemma-270m-it + +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 + +``` +developer +{system_prompt} +user +{prompt} +model +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [functiongemma-270m-it-bf16.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-bf16.gguf) | bf16 | 0.54GB | false | Full BF16 weights. | +| [functiongemma-270m-it-Q8_0.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q8_0.gguf) | Q8_0 | 0.29GB | false | Extremely high quality, generally unneeded but max available quant. | +| [functiongemma-270m-it-Q6_K_L.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q6_K_L.gguf) | Q6_K_L | 0.28GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [functiongemma-270m-it-Q6_K.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q6_K.gguf) | Q6_K | 0.28GB | false | Very high quality, near perfect, *recommended*. | +| [functiongemma-270m-it-Q5_K_L.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q5_K_L.gguf) | Q5_K_L | 0.26GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [functiongemma-270m-it-Q5_K_M.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q5_K_M.gguf) | Q5_K_M | 0.26GB | false | High quality, *recommended*. | +| [functiongemma-270m-it-Q5_K_S.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q5_K_S.gguf) | Q5_K_S | 0.26GB | false | High quality, *recommended*. | +| [functiongemma-270m-it-Q4_K_L.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q4_K_L.gguf) | Q4_K_L | 0.25GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [functiongemma-270m-it-Q4_K_M.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q4_K_M.gguf) | Q4_K_M | 0.25GB | false | Good quality, default size for most use cases, *recommended*. | +| [functiongemma-270m-it-Q4_K_S.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q4_K_S.gguf) | Q4_K_S | 0.25GB | false | Slightly lower quality with more space savings, *recommended*. | +| [functiongemma-270m-it-Q4_1.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q4_1.gguf) | Q4_1 | 0.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [functiongemma-270m-it-Q3_K_XL.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q3_K_XL.gguf) | Q3_K_XL | 0.25GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [functiongemma-270m-it-Q3_K_L.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q3_K_L.gguf) | Q3_K_L | 0.25GB | false | Lower quality but usable, good for low RAM availability. | +| [functiongemma-270m-it-Q4_0.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q4_0.gguf) | Q4_0 | 0.24GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [functiongemma-270m-it-IQ4_NL.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ4_NL.gguf) | IQ4_NL | 0.24GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [functiongemma-270m-it-IQ4_XS.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ4_XS.gguf) | IQ4_XS | 0.24GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [functiongemma-270m-it-Q3_K_M.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q3_K_M.gguf) | Q3_K_M | 0.24GB | false | Low quality. | +| [functiongemma-270m-it-IQ3_M.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ3_M.gguf) | IQ3_M | 0.24GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [functiongemma-270m-it-Q3_K_S.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q3_K_S.gguf) | Q3_K_S | 0.24GB | false | Low quality, not recommended. | +| [functiongemma-270m-it-IQ3_XS.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ3_XS.gguf) | IQ3_XS | 0.24GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [functiongemma-270m-it-IQ3_XXS.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ3_XXS.gguf) | IQ3_XXS | 0.24GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [functiongemma-270m-it-Q2_K_L.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q2_K_L.gguf) | Q2_K_L | 0.24GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [functiongemma-270m-it-Q2_K.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-Q2_K.gguf) | Q2_K | 0.24GB | false | Very low quality but surprisingly usable. | +| [functiongemma-270m-it-IQ2_M.gguf](https://huggingface.co/bartowski/google_functiongemma-270m-it-GGUF/blob/main/google_functiongemma-270m-it-IQ2_M.gguf) | IQ2_M | 0.23GB | 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/google_functiongemma-270m-it-GGUF --include "google_functiongemma-270m-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/google_functiongemma-270m-it-GGUF --include "google_functiongemma-270m-it-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (google_functiongemma-270m-it-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/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/google_functiongemma-270m-it-IQ2_M.gguf b/google_functiongemma-270m-it-IQ2_M.gguf new file mode 100644 index 0000000..0c521ae --- /dev/null +++ b/google_functiongemma-270m-it-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c700c44871cff98e5a9a2a2e7d4594e9116ba78f4bf056efa80e5aa9490b037 +size 234797792 diff --git a/google_functiongemma-270m-it-IQ3_M.gguf b/google_functiongemma-270m-it-IQ3_M.gguf new file mode 100644 index 0000000..9b95d9e --- /dev/null +++ b/google_functiongemma-270m-it-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e3235af07eff8b58929fbaa15420bc52df42abb36dd844b8dcf251ac83c41e +size 239006432 diff --git a/google_functiongemma-270m-it-IQ3_XS.gguf b/google_functiongemma-270m-it-IQ3_XS.gguf new file mode 100644 index 0000000..86a51f3 --- /dev/null +++ b/google_functiongemma-270m-it-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e119f64e9e02790fd5f3f8196967f52b664092c8baa86a95e9b4ba81dcf423b7 +size 237091552 diff --git a/google_functiongemma-270m-it-IQ3_XXS.gguf b/google_functiongemma-270m-it-IQ3_XXS.gguf new file mode 100644 index 0000000..09f811c --- /dev/null +++ b/google_functiongemma-270m-it-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c187ca1f86acd5cc2f56d480c5325c47abebfa7eeaf92b06988c6f441cdce2 +size 235985632 diff --git a/google_functiongemma-270m-it-IQ4_NL.gguf b/google_functiongemma-270m-it-IQ4_NL.gguf new file mode 100644 index 0000000..77c3370 --- /dev/null +++ b/google_functiongemma-270m-it-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9062ad9d4adc11b8b22906876bb2158b43b9c54f706b62a80c2fe247004a6ce +size 241976032 diff --git a/google_functiongemma-270m-it-IQ4_XS.gguf b/google_functiongemma-270m-it-IQ4_XS.gguf new file mode 100644 index 0000000..b0a00da --- /dev/null +++ b/google_functiongemma-270m-it-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:927f5c5a1b6b19b9414c13ae10b9df801d7b49790014c984e10108d23433f355 +size 240870112 diff --git a/google_functiongemma-270m-it-Q2_K.gguf b/google_functiongemma-270m-it-Q2_K.gguf new file mode 100644 index 0000000..4e643a2 --- /dev/null +++ b/google_functiongemma-270m-it-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb968e0f46fc2f1a6e283595f9e2dfe4aaa362b551298ce26a97cd3fd3b24fb +size 237091552 diff --git a/google_functiongemma-270m-it-Q2_K_L.gguf b/google_functiongemma-270m-it-Q2_K_L.gguf new file mode 100644 index 0000000..4e643a2 --- /dev/null +++ b/google_functiongemma-270m-it-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb968e0f46fc2f1a6e283595f9e2dfe4aaa362b551298ce26a97cd3fd3b24fb +size 237091552 diff --git a/google_functiongemma-270m-it-Q3_K_L.gguf b/google_functiongemma-270m-it-Q3_K_L.gguf new file mode 100644 index 0000000..1fe89ff --- /dev/null +++ b/google_functiongemma-270m-it-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afa4b6d742f527fb9f21af9624a786f3723eccaa4f2a4e9c7582f52d2a0e7d8 +size 246399712 diff --git a/google_functiongemma-270m-it-Q3_K_M.gguf b/google_functiongemma-270m-it-Q3_K_M.gguf new file mode 100644 index 0000000..b8182ee --- /dev/null +++ b/google_functiongemma-270m-it-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae407957d5d408dcbbb5e415e3f76a6752ee97e1028823e2a615877b4a6d375 +size 241976032 diff --git a/google_functiongemma-270m-it-Q3_K_S.gguf b/google_functiongemma-270m-it-Q3_K_S.gguf new file mode 100644 index 0000000..59b0806 --- /dev/null +++ b/google_functiongemma-270m-it-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3139e40bd44efd62ebba699df53b0617df27acb0793cff5d4e75285e8c613b +size 236722912 diff --git a/google_functiongemma-270m-it-Q3_K_XL.gguf b/google_functiongemma-270m-it-Q3_K_XL.gguf new file mode 100644 index 0000000..1fe89ff --- /dev/null +++ b/google_functiongemma-270m-it-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afa4b6d742f527fb9f21af9624a786f3723eccaa4f2a4e9c7582f52d2a0e7d8 +size 246399712 diff --git a/google_functiongemma-270m-it-Q4_0.gguf b/google_functiongemma-270m-it-Q4_0.gguf new file mode 100644 index 0000000..7c150b7 --- /dev/null +++ b/google_functiongemma-270m-it-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f873c26827d1741362a5577062d7ee35a0a31f49a5259ff2dd98a2c5e388e1 +size 241586912 diff --git a/google_functiongemma-270m-it-Q4_1.gguf b/google_functiongemma-270m-it-Q4_1.gguf new file mode 100644 index 0000000..ad699b7 --- /dev/null +++ b/google_functiongemma-270m-it-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b630a8c2e043966d3349cc5cc2a9e00bfc9f82a1440cf8f61ee98091f7b08a +size 247689952 diff --git a/google_functiongemma-270m-it-Q4_K_L.gguf b/google_functiongemma-270m-it-Q4_K_L.gguf new file mode 100644 index 0000000..4b556e4 --- /dev/null +++ b/google_functiongemma-270m-it-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321e83ac555d43b7d045f563413acef9e094ba26290360e656e7fd9ae6c6bb94 +size 253127392 diff --git a/google_functiongemma-270m-it-Q4_K_M.gguf b/google_functiongemma-270m-it-Q4_K_M.gguf new file mode 100644 index 0000000..4b556e4 --- /dev/null +++ b/google_functiongemma-270m-it-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321e83ac555d43b7d045f563413acef9e094ba26290360e656e7fd9ae6c6bb94 +size 253127392 diff --git a/google_functiongemma-270m-it-Q4_K_S.gguf b/google_functiongemma-270m-it-Q4_K_S.gguf new file mode 100644 index 0000000..2e7e603 --- /dev/null +++ b/google_functiongemma-270m-it-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3742d67c449bbbcf50e9a5c3385de49f8a231b5d6803728951d889fb1d8cc4 +size 249901792 diff --git a/google_functiongemma-270m-it-Q5_K_L.gguf b/google_functiongemma-270m-it-Q5_K_L.gguf new file mode 100644 index 0000000..52ed80d --- /dev/null +++ b/google_functiongemma-270m-it-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9fc8d567f0a381d9cb77ea0e31c3e186db126aa754c0457f268962ca3e738b +size 260039392 diff --git a/google_functiongemma-270m-it-Q5_K_M.gguf b/google_functiongemma-270m-it-Q5_K_M.gguf new file mode 100644 index 0000000..52ed80d --- /dev/null +++ b/google_functiongemma-270m-it-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9fc8d567f0a381d9cb77ea0e31c3e186db126aa754c0457f268962ca3e738b +size 260039392 diff --git a/google_functiongemma-270m-it-Q5_K_S.gguf b/google_functiongemma-270m-it-Q5_K_S.gguf new file mode 100644 index 0000000..c0afa91 --- /dev/null +++ b/google_functiongemma-270m-it-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22668455e6cbcd392aa4eb345e320067c0f27abd0d61b3e0ae84e5f46ebc8091 +size 258011872 diff --git a/google_functiongemma-270m-it-Q6_K.gguf b/google_functiongemma-270m-it-Q6_K.gguf new file mode 100644 index 0000000..a6b5406 --- /dev/null +++ b/google_functiongemma-270m-it-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:217134569926b42cf0efe741ee5a08136bfbdfa9fb810c8844b4fd9a7dc9b2c8 +size 282987232 diff --git a/google_functiongemma-270m-it-Q6_K_L.gguf b/google_functiongemma-270m-it-Q6_K_L.gguf new file mode 100644 index 0000000..a6b5406 --- /dev/null +++ b/google_functiongemma-270m-it-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:217134569926b42cf0efe741ee5a08136bfbdfa9fb810c8844b4fd9a7dc9b2c8 +size 282987232 diff --git a/google_functiongemma-270m-it-Q8_0.gguf b/google_functiongemma-270m-it-Q8_0.gguf new file mode 100644 index 0000000..f4fec16 --- /dev/null +++ b/google_functiongemma-270m-it-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f50fbac8552d090863d5fefa983d24ac1ca37df23b1c77e3bbbd80aeb3b208c4 +size 291558112 diff --git a/google_functiongemma-270m-it-bf16.gguf b/google_functiongemma-270m-it-bf16.gguf new file mode 100644 index 0000000..35a17ad --- /dev/null +++ b/google_functiongemma-270m-it-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44090e534ddb3cfc683b696f2825b4056f413ad1e7963d69bd5196d5b3ae7ee6 +size 542847392 diff --git a/google_functiongemma-270m-it-imatrix.gguf b/google_functiongemma-270m-it-imatrix.gguf new file mode 100644 index 0000000..9474587 Binary files /dev/null and b/google_functiongemma-270m-it-imatrix.gguf differ