commit 0d541e1e131a9d22cdc1410f6d9aebe271e771a6 Author: ModelHub XC Date: Mon Jun 15 08:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemmasutra-Mini-2B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a21a442 --- /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 +Gemmasutra-Mini-2B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-Mini-2B-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemmasutra-Mini-2B-v1.IQ4_XS.gguf b/Gemmasutra-Mini-2B-v1.IQ4_XS.gguf new file mode 100644 index 0000000..7f2cd38 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70172748621fce7698db42bdd2067d5d2b50e304de9e11e2af9ee439994a1e71 +size 1576204256 diff --git a/Gemmasutra-Mini-2B-v1.Q2_K.gguf b/Gemmasutra-Mini-2B-v1.Q2_K.gguf new file mode 100644 index 0000000..4313fb2 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0329b41a673424675e535d53c8579a06d945b6d7ca2a6417f4a068ac5defad +size 1229830112 diff --git a/Gemmasutra-Mini-2B-v1.Q3_K_L.gguf b/Gemmasutra-Mini-2B-v1.Q3_K_L.gguf new file mode 100644 index 0000000..0ffd85f --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f2d60863c1ea683b6c4aae392b10784c974c864611a9aa529d15a6fa0f65ce +size 1550436320 diff --git a/Gemmasutra-Mini-2B-v1.Q3_K_M.gguf b/Gemmasutra-Mini-2B-v1.Q3_K_M.gguf new file mode 100644 index 0000000..ce678f7 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aeb39efb4b24ecadc804ab0f332d1a55440ce77227155e566684d7c17acfc5f +size 1461667808 diff --git a/Gemmasutra-Mini-2B-v1.Q3_K_S.gguf b/Gemmasutra-Mini-2B-v1.Q3_K_S.gguf new file mode 100644 index 0000000..4dc1b04 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c0623fa895ac14476453e00a3a362ad7e95c20e52e322617fc5790ec5c4e059 +size 1360660448 diff --git a/Gemmasutra-Mini-2B-v1.Q4_K_M.gguf b/Gemmasutra-Mini-2B-v1.Q4_K_M.gguf new file mode 100644 index 0000000..c3bc4fd --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2486acf1b53a777449dd90414fad14cf320e651d3b0df61b015e228f01b19956 +size 1708582880 diff --git a/Gemmasutra-Mini-2B-v1.Q4_K_S.gguf b/Gemmasutra-Mini-2B-v1.Q4_K_S.gguf new file mode 100644 index 0000000..4ec113b --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f16bb32f7c743cb9c4a6383ba0e69693513227442ff9e8a5d31639234d35a8 +size 1638651872 diff --git a/Gemmasutra-Mini-2B-v1.Q5_K_M.gguf b/Gemmasutra-Mini-2B-v1.Q5_K_M.gguf new file mode 100644 index 0000000..9a5a5ad --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2151f781d6da1eb22ee0224aae67b2f896588845571c86a82d626c4803a794f +size 1923278816 diff --git a/Gemmasutra-Mini-2B-v1.Q5_K_S.gguf b/Gemmasutra-Mini-2B-v1.Q5_K_S.gguf new file mode 100644 index 0000000..aaf0954 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06207a603d08360e4e502746e2eb8ef102687452ceb9702226d4470897fbfb2 +size 1882544096 diff --git a/Gemmasutra-Mini-2B-v1.Q6_K.gguf b/Gemmasutra-Mini-2B-v1.Q6_K.gguf new file mode 100644 index 0000000..f8850bb --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270ad7888bbc70dcc6a8ba26d0f8ffae7bbe39ba4d340669df6ee46a87c2bc8a +size 2151393248 diff --git a/Gemmasutra-Mini-2B-v1.Q8_0.gguf b/Gemmasutra-Mini-2B-v1.Q8_0.gguf new file mode 100644 index 0000000..e881499 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9122b45fe66a9a5acf24e6787cdf3eeef9fb247d5c6a84f9c6d73129172f4a8d +size 2784495584 diff --git a/Gemmasutra-Mini-2B-v1.f16.gguf b/Gemmasutra-Mini-2B-v1.f16.gguf new file mode 100644 index 0000000..b14f812 --- /dev/null +++ b/Gemmasutra-Mini-2B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0391029f2918d23d5fce9bb7a9dd8854d8e591042ca27334bc56d15b655407d +size 5235214304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..621210b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: TheDrummer/Gemmasutra-Mini-2B-v1 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TheDrummer/Gemmasutra-Mini-2B-v1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-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/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-Mini-2B-v1-GGUF/resolve/main/Gemmasutra-Mini-2B-v1.f16.gguf) | f16 | 5.3 | 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. + +