commit 8a53006c72f8952c1eb17b200e2c08af905ca4b4 Author: ModelHub XC Date: Tue May 5 21:50:53 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/tamilan-2-27b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41eeb64 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +tamilan-2-27b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..99a3d94 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: mervinpraison/tamilan-2-27b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma2 +- trl +- sft +- praisonai +- praison +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/mervinpraison/tamilan-2-27b + + +static quants are available at https://huggingface.co/mradermacher/tamilan-2-27b-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/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | | +| [GGUF](https://huggingface.co/mradermacher/tamilan-2-27b-i1-GGUF/resolve/main/tamilan-2-27b.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..aeb81a2 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4256d5d65fa2fb0da2a09f84c40a8a782f49ce032552381abe376ffd8001b4b4 +size 11786683 diff --git a/tamilan-2-27b.i1-IQ1_M.gguf b/tamilan-2-27b.i1-IQ1_M.gguf new file mode 100644 index 0000000..18721af --- /dev/null +++ b/tamilan-2-27b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5722e8babcc442e64024e10c022f26271f3b7f19045e791fad8f7371a1c5992e +size 6692471456 diff --git a/tamilan-2-27b.i1-IQ1_S.gguf b/tamilan-2-27b.i1-IQ1_S.gguf new file mode 100644 index 0000000..fec1c73 --- /dev/null +++ b/tamilan-2-27b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b953e03b8329a60d55eee1924ea7408c9a7cdf672ac629be04f46033cddb52 +size 6132433568 diff --git a/tamilan-2-27b.i1-IQ2_M.gguf b/tamilan-2-27b.i1-IQ2_M.gguf new file mode 100644 index 0000000..3eb5128 --- /dev/null +++ b/tamilan-2-27b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2105e5fb04de463bec5e9e793b0b62583b61f6c1c8860dbcd736c84171ff9c20 +size 9398878880 diff --git a/tamilan-2-27b.i1-IQ2_S.gguf b/tamilan-2-27b.i1-IQ2_S.gguf new file mode 100644 index 0000000..a26e816 --- /dev/null +++ b/tamilan-2-27b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bc9f90b3e38738878ea51764e07f809a011bb24c524c3d6f454ff32406e824 +size 8652161696 diff --git a/tamilan-2-27b.i1-IQ2_XS.gguf b/tamilan-2-27b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..242c8d9 --- /dev/null +++ b/tamilan-2-27b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4edb9d5f61cbf8b1a526555419ae774e5d820c97f9faacfb9c4854f7a26a07 +size 8399717024 diff --git a/tamilan-2-27b.i1-IQ2_XXS.gguf b/tamilan-2-27b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..e548856 --- /dev/null +++ b/tamilan-2-27b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c8161a2917dc8175e4ea67f958571f414d1de79a06f44d01bfd4af1b7036f4 +size 7625867936 diff --git a/tamilan-2-27b.i1-IQ3_M.gguf b/tamilan-2-27b.i1-IQ3_M.gguf new file mode 100644 index 0000000..64038f6 --- /dev/null +++ b/tamilan-2-27b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5457361c0cdb36808d794ea84d3f54e091c0225f74d59971fb93b478c3a1d18e +size 12454830752 diff --git a/tamilan-2-27b.i1-IQ3_S.gguf b/tamilan-2-27b.i1-IQ3_S.gguf new file mode 100644 index 0000000..fa0b11d --- /dev/null +++ b/tamilan-2-27b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b3e0bcf70d4428ed93fa5614f4be9fe8313f54a4baf078df726b317f25fbb9 +size 12169061024 diff --git a/tamilan-2-27b.i1-IQ3_XS.gguf b/tamilan-2-27b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0537b0c --- /dev/null +++ b/tamilan-2-27b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8c742cac2abc94037fabcd52ee3be03977e24baf0f2d8d5b0a2ce658ed91ae +size 11550630560 diff --git a/tamilan-2-27b.i1-IQ3_XXS.gguf b/tamilan-2-27b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ced8ae3 --- /dev/null +++ b/tamilan-2-27b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72df8cb8f9a383475dd90830c8c666d81cb89a7659a7d61010a03ceab67a4fdb +size 10750755488 diff --git a/tamilan-2-27b.i1-IQ4_XS.gguf b/tamilan-2-27b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0f3abbc --- /dev/null +++ b/tamilan-2-27b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7664e65a9d4b32790b9047ea8e520a369d0afab73c3a675da6a511d36fac2dc0 +size 14814421664 diff --git a/tamilan-2-27b.i1-Q2_K.gguf b/tamilan-2-27b.i1-Q2_K.gguf new file mode 100644 index 0000000..1866219 --- /dev/null +++ b/tamilan-2-27b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7da0cee60b4c3b63600631bb26ef1eb484aff04d19d24ba704d3175fb498b2 +size 10449576608 diff --git a/tamilan-2-27b.i1-Q3_K_L.gguf b/tamilan-2-27b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2dbe3b0 --- /dev/null +++ b/tamilan-2-27b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9d38a8289ad801cc4232ec92f6297236c050ed38eaf41c14ae07efc98d8505 +size 14519362208 diff --git a/tamilan-2-27b.i1-Q3_K_M.gguf b/tamilan-2-27b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e0286ac --- /dev/null +++ b/tamilan-2-27b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf8651e03231c1ab972e67b5e7946c637cb49cc19f1504aa094331d2f0c7cc2 +size 13424648864 diff --git a/tamilan-2-27b.i1-Q3_K_S.gguf b/tamilan-2-27b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ec75142 --- /dev/null +++ b/tamilan-2-27b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e724389721c32dc8bc747d64bd031eecfa66a43ad5d1e77c5e51647b2fd49ca +size 12169061024 diff --git a/tamilan-2-27b.i1-Q4_0.gguf b/tamilan-2-27b.i1-Q4_0.gguf new file mode 100644 index 0000000..6f3ce15 --- /dev/null +++ b/tamilan-2-27b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34b18acf827863b8de0e5f33b6177e61c41793530cf9157567724caa9c6afee +size 15681462944 diff --git a/tamilan-2-27b.i1-Q4_K_M.gguf b/tamilan-2-27b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..923217e --- /dev/null +++ b/tamilan-2-27b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bff8ee92da1b924d0b135ffa1bbe8780895597e72c1a12919137f664736b0cf +size 16645382816 diff --git a/tamilan-2-27b.i1-Q4_K_S.gguf b/tamilan-2-27b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cbac958 --- /dev/null +++ b/tamilan-2-27b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95b4732d8a12f57c9c8aa304b866f716e51642fd80c73eab1d8db59e155afc4 +size 15739265696 diff --git a/tamilan-2-27b.i1-Q5_K_M.gguf b/tamilan-2-27b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f405901 --- /dev/null +++ b/tamilan-2-27b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8c85137c0c92fde61cbe67305d7f082f3c57bcf8b429adf56de13deb3799a1 +size 19408118432 diff --git a/tamilan-2-27b.i1-Q5_K_S.gguf b/tamilan-2-27b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..217467b --- /dev/null +++ b/tamilan-2-27b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd79012da06a58d1a6bcef4890e82390a20cbc6c4d4083d8daac35f530d03bf0 +size 18884207264 diff --git a/tamilan-2-27b.i1-Q6_K.gguf b/tamilan-2-27b.i1-Q6_K.gguf new file mode 100644 index 0000000..efc544a --- /dev/null +++ b/tamilan-2-27b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef6eed0211ec4864695719762c8e9acf9c2113dd18880d7383cbf16300339cf +size 22343525024