commit 1240e3c726db5b6c4ed7838c19f1629d892ddfdb Author: ModelHub XC Date: Thu Jun 4 08:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3cea9e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-7B-Instruct-Function-Calling.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-7B-Instruct-Function-Calling.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-7B-Instruct-Function-Calling.IQ4_XS.gguf b/Gemma-7B-Instruct-Function-Calling.IQ4_XS.gguf new file mode 100644 index 0000000..9675b31 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb3840e1347421b6fc48781ac928d44d0b4a729961dbba261daeecbedfb1ab3 +size 4805013248 diff --git a/Gemma-7B-Instruct-Function-Calling.Q2_K.gguf b/Gemma-7B-Instruct-Function-Calling.Q2_K.gguf new file mode 100644 index 0000000..79d8b90 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8067c2ce517139425e276ad315b94e71353f11a618ff81c84d6850dd93632dd4 +size 3481448192 diff --git a/Gemma-7B-Instruct-Function-Calling.Q3_K_L.gguf b/Gemma-7B-Instruct-Function-Calling.Q3_K_L.gguf new file mode 100644 index 0000000..6a7fac0 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29187586e9cadc749e47df10742cbbb20e7cbf71c7479bdf7f5960228388fc4a +size 4709068544 diff --git a/Gemma-7B-Instruct-Function-Calling.Q3_K_M.gguf b/Gemma-7B-Instruct-Function-Calling.Q3_K_M.gguf new file mode 100644 index 0000000..0b3e9d8 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:accc29b5dcd841f4e5aa29a42c04fc1bf212480a2f3ae3c5d44f22ce868d3d27 +size 4369329920 diff --git a/Gemma-7B-Instruct-Function-Calling.Q3_K_S.gguf b/Gemma-7B-Instruct-Function-Calling.Q3_K_S.gguf new file mode 100644 index 0000000..dc83ea6 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de98e27c7d813bd00c38ce9875043d5d42943bcbd05c614d711f66a5f95748e6 +size 3982405376 diff --git a/Gemma-7B-Instruct-Function-Calling.Q4_K_M.gguf b/Gemma-7B-Instruct-Function-Calling.Q4_K_M.gguf new file mode 100644 index 0000000..6c67b14 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3df666d7c65e0d5b2fa757dfe48b0c28b870dd66ca46f4d4528d305c68af50 +size 5329760000 diff --git a/Gemma-7B-Instruct-Function-Calling.Q4_K_S.gguf b/Gemma-7B-Instruct-Function-Calling.Q4_K_S.gguf new file mode 100644 index 0000000..68cc0d1 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e57600fb8ca536d2b119099c48e8a997a61c17fa629f4d2b2b9d79755841009 +size 5046447872 diff --git a/Gemma-7B-Instruct-Function-Calling.Q5_K_M.gguf b/Gemma-7B-Instruct-Function-Calling.Q5_K_M.gguf new file mode 100644 index 0000000..f0dcd2c --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69db75d45bb95bd5e18b74e09dad6e7a77533449d89076ee2379376ad72ec5a1 +size 6144503552 diff --git a/Gemma-7B-Instruct-Function-Calling.Q5_K_S.gguf b/Gemma-7B-Instruct-Function-Calling.Q5_K_S.gguf new file mode 100644 index 0000000..ab96ece --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a59a452d4b091af20a859e9df89b68572eff1573af0ad02dd3952f608ff5ca8 +size 5980729088 diff --git a/Gemma-7B-Instruct-Function-Calling.Q6_K.gguf b/Gemma-7B-Instruct-Function-Calling.Q6_K.gguf new file mode 100644 index 0000000..b262be6 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3c45efc75e3266b5b952d5e0c4314729ea9ee8961ffdfced411f63be45dcf3 +size 7010168576 diff --git a/Gemma-7B-Instruct-Function-Calling.Q8_0.gguf b/Gemma-7B-Instruct-Function-Calling.Q8_0.gguf new file mode 100644 index 0000000..b969ac7 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f9d5d1316bcdf234b8fda8157b2a7319279c769194b11f938bb5efe2454656 +size 9077845760 diff --git a/Gemma-7B-Instruct-Function-Calling.f16.gguf b/Gemma-7B-Instruct-Function-Calling.f16.gguf new file mode 100644 index 0000000..4ae2511 --- /dev/null +++ b/Gemma-7B-Instruct-Function-Calling.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d522f2ac28ef0ae9d72a3f70420987da27bb51defcaaffe1ff03593b570ca1b1 +size 17081757440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6391d1 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: InterSync/Gemma-7B-Instruct-Function-Calling +language: +- en +library_name: transformers +license: cc +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/InterSync/Gemma-7B-Instruct-Function-Calling + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-7B-Instruct-Function-Calling-GGUF/resolve/main/Gemma-7B-Instruct-Function-Calling.f16.gguf) | f16 | 17.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +