commit 376b2a4bb1932834e83426b9e062d4973aac44ee Author: ModelHub XC Date: Mon Jun 15 08:46:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-7b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3cfd48 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +gemma-7b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..da95713 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: google/gemma-7b-it +extra_gated_button_content: Acknowledge license +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. +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/google/gemma-7b-it + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-7b-it-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-it-GGUF/resolve/main/gemma-7b-it.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.1 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.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. + + diff --git a/gemma-7b-it.IQ4_XS.gguf b/gemma-7b-it.IQ4_XS.gguf new file mode 100644 index 0000000..3bee157 --- /dev/null +++ b/gemma-7b-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2efb1ed6be3c90bb1a53233b7d532f8516549757e786ba57c05cb80f3a967ca6 +size 4805013472 diff --git a/gemma-7b-it.Q2_K.gguf b/gemma-7b-it.Q2_K.gguf new file mode 100644 index 0000000..9dba403 --- /dev/null +++ b/gemma-7b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e3e787b5e108161b5772b13bd7e0a44ed59e17e012841fbfaa81f42d136bac +size 3481448416 diff --git a/gemma-7b-it.Q3_K_L.gguf b/gemma-7b-it.Q3_K_L.gguf new file mode 100644 index 0000000..bb99409 --- /dev/null +++ b/gemma-7b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0378d0c7f7e55c840ab6d2b799e742a32bbf380c6b8fab6d8eff2633c54cbf09 +size 4709068768 diff --git a/gemma-7b-it.Q3_K_M.gguf b/gemma-7b-it.Q3_K_M.gguf new file mode 100644 index 0000000..3b069a4 --- /dev/null +++ b/gemma-7b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a2c62156641e991c8538157f4b86be12edf8abcd9e190c107bd4971b87ee81 +size 4369330144 diff --git a/gemma-7b-it.Q3_K_S.gguf b/gemma-7b-it.Q3_K_S.gguf new file mode 100644 index 0000000..bba0332 --- /dev/null +++ b/gemma-7b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8b46e330d8526b04551ece106ec41beb15803d4962516911887d4027566718 +size 3982405600 diff --git a/gemma-7b-it.Q4_0_4_4.gguf b/gemma-7b-it.Q4_0_4_4.gguf new file mode 100644 index 0000000..fc7bc0a --- /dev/null +++ b/gemma-7b-it.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78eb18540a2a1e536987a82bd8a30f91e3554f1f46b53f08fe52b7ffbe3481eb +size 5011845088 diff --git a/gemma-7b-it.Q4_K_M.gguf b/gemma-7b-it.Q4_K_M.gguf new file mode 100644 index 0000000..20ec3ca --- /dev/null +++ b/gemma-7b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38017dc7383bebef2ab5b1de7adda471ec9fe1d1ad02d94e84d4f87f3aae3ca6 +size 5329760224 diff --git a/gemma-7b-it.Q4_K_S.gguf b/gemma-7b-it.Q4_K_S.gguf new file mode 100644 index 0000000..d5288f5 --- /dev/null +++ b/gemma-7b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7afb017a1a385aea28e175f7518fb8e4d14fca189a5389f4b39730221941210 +size 5046448096 diff --git a/gemma-7b-it.Q5_K_M.gguf b/gemma-7b-it.Q5_K_M.gguf new file mode 100644 index 0000000..5646ab2 --- /dev/null +++ b/gemma-7b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afee2f3626f83ce79c9b68ac342851cb06a607bc17ca1ddd3cab30afecec067c +size 6144503776 diff --git a/gemma-7b-it.Q5_K_S.gguf b/gemma-7b-it.Q5_K_S.gguf new file mode 100644 index 0000000..b1e23aa --- /dev/null +++ b/gemma-7b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcfb51d70c85a5a05a31effa7665b321c3b3cf8c68f4f024e30609cb5421b23 +size 5980729312 diff --git a/gemma-7b-it.Q6_K.gguf b/gemma-7b-it.Q6_K.gguf new file mode 100644 index 0000000..0a0fb3a --- /dev/null +++ b/gemma-7b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18288784e5aa61319ec78738564b8c019a8cb2f7e2daee5994a3bfcc6499791b +size 7010168800 diff --git a/gemma-7b-it.Q8_0.gguf b/gemma-7b-it.Q8_0.gguf new file mode 100644 index 0000000..2c4887c --- /dev/null +++ b/gemma-7b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162a52743579f38107fcbda332d45d8dc9504d9f9557a2df2562a79c88212771 +size 9077845984 diff --git a/gemma-7b-it.f16.gguf b/gemma-7b-it.f16.gguf new file mode 100644 index 0000000..438b84a --- /dev/null +++ b/gemma-7b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a8d5eb7f898acd6dc5f980b79ab0eeb2ac32f1ed3f6c7fbf698daedc01845b +size 17081757664