commit a843122ea2a33139b7dc5771bda22cd592dbf731 Author: ModelHub XC Date: Fri May 15 01:56:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sarvam-translate-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..02443b8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +sarvam-translate.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +sarvam-translate.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c5f89a --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: sarvamai/sarvam-translate +language: +- as +- bn +- brx +- doi +- gom +- gu +- en +- hi +- kn +- ks +- mai +- ml +- mni +- mr +- ne +- or +- pa +- sa +- sat +- sd +- ta +- te +- ur +library_name: transformers +license: gpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/sarvamai/sarvam-translate + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#sarvam-translate-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/sarvam-translate-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/sarvam-translate-GGUF/resolve/main/sarvam-translate.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/sarvam-translate-GGUF/resolve/main/sarvam-translate.f16.gguf) | f16 | 7.9 | 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/sarvam-translate.IQ4_XS.gguf b/sarvam-translate.IQ4_XS.gguf new file mode 100644 index 0000000..caa4945 --- /dev/null +++ b/sarvam-translate.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bebfeba8d939955eccdb5b0c52e9ca5c296dc5f7083b0f8fed7d71dd070a07 +size 2279626496 diff --git a/sarvam-translate.Q2_K.gguf b/sarvam-translate.Q2_K.gguf new file mode 100644 index 0000000..fa01a63 --- /dev/null +++ b/sarvam-translate.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145b0b1e4c6467615530056b79b73b28686fd36332442d490c7dd122c930d72e +size 1729165056 diff --git a/sarvam-translate.Q3_K_L.gguf b/sarvam-translate.Q3_K_L.gguf new file mode 100644 index 0000000..b45b883 --- /dev/null +++ b/sarvam-translate.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1bdb0e42c85d7be4f303db0768daf2732bdc0c7ca8ad64f434eed17e546d32 +size 2236086016 diff --git a/sarvam-translate.Q3_K_M.gguf b/sarvam-translate.Q3_K_M.gguf new file mode 100644 index 0000000..00dff7b --- /dev/null +++ b/sarvam-translate.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a00cb09a3382efb1a315aad9e5913d1b97f549b438188289df0323d559ca89 +size 2098460416 diff --git a/sarvam-translate.Q3_K_S.gguf b/sarvam-translate.Q3_K_S.gguf new file mode 100644 index 0000000..ed48212 --- /dev/null +++ b/sarvam-translate.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f248b0a565d2ef7f4a6935e199beeb49f4338eb021e8083e6abcb579bb0b605 +size 1937364736 diff --git a/sarvam-translate.Q4_K_M.gguf b/sarvam-translate.Q4_K_M.gguf new file mode 100644 index 0000000..66b61ae --- /dev/null +++ b/sarvam-translate.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc227399c100278d78ab9f292b42e61567ce4316b383205209fed4de66bb9893 +size 2489894656 diff --git a/sarvam-translate.Q4_K_S.gguf b/sarvam-translate.Q4_K_S.gguf new file mode 100644 index 0000000..07059d6 --- /dev/null +++ b/sarvam-translate.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb91b4a1d6d38eeef1816fb9dd5495f011c25859de87756cc2d40c727fa091c +size 2377930496 diff --git a/sarvam-translate.Q5_K_M.gguf b/sarvam-translate.Q5_K_M.gguf new file mode 100644 index 0000000..6faa4da --- /dev/null +++ b/sarvam-translate.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d74909160aa3e9b8e7a0cd460cd17ff64ef94673eb24995ebfde6e5f87456b2 +size 2829698816 diff --git a/sarvam-translate.Q5_K_S.gguf b/sarvam-translate.Q5_K_S.gguf new file mode 100644 index 0000000..440e027 --- /dev/null +++ b/sarvam-translate.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c65b1ad5223899fcf12709f1508a10017343f7f36b26b8a494941ed28e65b790 +size 2764592896 diff --git a/sarvam-translate.Q6_K.gguf b/sarvam-translate.Q6_K.gguf new file mode 100644 index 0000000..a7d6f02 --- /dev/null +++ b/sarvam-translate.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd551cab86a8c819738dd189755cc1f2af58213213a63aaf13c0848364d348d9 +size 3190740736 diff --git a/sarvam-translate.Q8_0.gguf b/sarvam-translate.Q8_0.gguf new file mode 100644 index 0000000..b646ac7 --- /dev/null +++ b/sarvam-translate.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0132a353972b534b84d8da1578ca4158d525d9ca223a97ee49cf946ede4fb524 +size 4130402816 diff --git a/sarvam-translate.f16.gguf b/sarvam-translate.f16.gguf new file mode 100644 index 0000000..afc6ac0 --- /dev/null +++ b/sarvam-translate.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6342e30bcb787404c5abd4a0a47c023c73576e03e8f9b04149d6574afbd073 +size 7767804416 diff --git a/sarvam-translate.mmproj-Q8_0.gguf b/sarvam-translate.mmproj-Q8_0.gguf new file mode 100644 index 0000000..751f48c --- /dev/null +++ b/sarvam-translate.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2155040ae0315090f69936c4903ee3536ed9451728316103a2b51bca7fc8d739 +size 591377952 diff --git a/sarvam-translate.mmproj-f16.gguf b/sarvam-translate.mmproj-f16.gguf new file mode 100644 index 0000000..d92acdf --- /dev/null +++ b/sarvam-translate.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc0d98a1a4ac38159c10cfd7fe7b723abd3ffbfdc2485911b556406498e4261 +size 851251872