commit a8e78d127eb2fb80b099299223b5027bcd2f0ef4 Author: ModelHub XC Date: Mon Oct 5 21:15:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/marathi-gpt-gemma-2b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bf0abc0 --- /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 +marathi-gpt-gemma-2b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +marathi-gpt-gemma-2b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3bcf4f --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: l3cube-pune/marathi-gpt-gemma-2b +language: mr +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/l3cube-pune/marathi-gpt-gemma-2b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#marathi-gpt-gemma-2b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-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/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/marathi-gpt-gemma-2b-GGUF/resolve/main/marathi-gpt-gemma-2b.f16.gguf) | f16 | 5.1 | 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/marathi-gpt-gemma-2b.IQ4_XS.gguf b/marathi-gpt-gemma-2b.IQ4_XS.gguf new file mode 100644 index 0000000..a4a4c65 --- /dev/null +++ b/marathi-gpt-gemma-2b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888e425ff3a5ff02bbf5edf4388b2112ed128ebbfb5f4625ce8e242da0c981d2 +size 1501218752 diff --git a/marathi-gpt-gemma-2b.Q2_K.gguf b/marathi-gpt-gemma-2b.Q2_K.gguf new file mode 100644 index 0000000..938117c --- /dev/null +++ b/marathi-gpt-gemma-2b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcde36a3e8052761579ea7a30a5fb2a855cccc246ab251539a91aca2e3b718da +size 1157924800 diff --git a/marathi-gpt-gemma-2b.Q3_K_L.gguf b/marathi-gpt-gemma-2b.Q3_K_L.gguf new file mode 100644 index 0000000..fa952b6 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30759e7030375f61f3ae750c974e8021be51b899f9dae65cd5b6c53d51e9ad00 +size 1465591744 diff --git a/marathi-gpt-gemma-2b.Q3_K_M.gguf b/marathi-gpt-gemma-2b.Q3_K_M.gguf new file mode 100644 index 0000000..9cf97d5 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b156048d30e9ee97585f86ea154af60801ba259120e48098107c8b9d2b38b280 +size 1383802816 diff --git a/marathi-gpt-gemma-2b.Q3_K_S.gguf b/marathi-gpt-gemma-2b.Q3_K_S.gguf new file mode 100644 index 0000000..eaa8386 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a52101c4c4674c9785a6878cbdf4bdc52c9ae8a7f1ba664e007bb353dbb33d1 +size 1287980992 diff --git a/marathi-gpt-gemma-2b.Q4_K_M.gguf b/marathi-gpt-gemma-2b.Q4_K_M.gguf new file mode 100644 index 0000000..268ddc3 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41ae09742ea3c0ae17390fbdf6b5edf013ef8316bbe1c75ee7bdd1c5cff7dee9 +size 1630263232 diff --git a/marathi-gpt-gemma-2b.Q4_K_S.gguf b/marathi-gpt-gemma-2b.Q4_K_S.gguf new file mode 100644 index 0000000..dd1dbe7 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70abcb9b28b668fdb05e29c828c70613dab31167da83238283ab7d72a23a7e0 +size 1559840704 diff --git a/marathi-gpt-gemma-2b.Q5_K_M.gguf b/marathi-gpt-gemma-2b.Q5_K_M.gguf new file mode 100644 index 0000000..7af8467 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1bc4eb2f3072dc4d4b0905708ce8607c194a6442edb3a9c58931004a908a4d3 +size 1839650752 diff --git a/marathi-gpt-gemma-2b.Q5_K_S.gguf b/marathi-gpt-gemma-2b.Q5_K_S.gguf new file mode 100644 index 0000000..b26d24a --- /dev/null +++ b/marathi-gpt-gemma-2b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:484759a0a40095ea821eaf32d8be4fb25e9a7ae51a2a6a64ed98bcfcf07cad7e +size 1798916032 diff --git a/marathi-gpt-gemma-2b.Q6_K.gguf b/marathi-gpt-gemma-2b.Q6_K.gguf new file mode 100644 index 0000000..69348bc --- /dev/null +++ b/marathi-gpt-gemma-2b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d7aa6c9521c710f6307988c987376542f89b4f059f4e99f6a0a2d091cc9b88 +size 2062124992 diff --git a/marathi-gpt-gemma-2b.Q8_0.gguf b/marathi-gpt-gemma-2b.Q8_0.gguf new file mode 100644 index 0000000..b508994 --- /dev/null +++ b/marathi-gpt-gemma-2b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3ebf17e7e03ce855deb479d9811b231c707f2aa9b438060b8a230bfee1076f +size 2669070272 diff --git a/marathi-gpt-gemma-2b.f16.gguf b/marathi-gpt-gemma-2b.f16.gguf new file mode 100644 index 0000000..9de511e --- /dev/null +++ b/marathi-gpt-gemma-2b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199027c0db672c863aad926f522848afec1464f82f1907c13075eff514f2cc8b +size 5018535872