commit bd64506743c2e9b5006291ebe5a029e2b896d1a4 Author: ModelHub XC Date: Tue May 5 08:33:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bangla-AI-1.7B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c6bef5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Bangla-AI-1.7B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-AI-1.7B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bangla-AI-1.7B.i1-IQ1_M.gguf b/Bangla-AI-1.7B.i1-IQ1_M.gguf new file mode 100644 index 0000000..3d2bf5b --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ac7f5aa6b5ffd9ec1ea40cc913369a41b969bc17599c06d9011eb091f1e545 +size 543794112 diff --git a/Bangla-AI-1.7B.i1-IQ1_S.gguf b/Bangla-AI-1.7B.i1-IQ1_S.gguf new file mode 100644 index 0000000..96f95cc --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e385cc2004a3e5e9ceeaca150055830d02a10418fb2de271b192f24a13f19a +size 515777472 diff --git a/Bangla-AI-1.7B.i1-IQ2_M.gguf b/Bangla-AI-1.7B.i1-IQ2_M.gguf new file mode 100644 index 0000000..bf2eccb --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86ebc74902f09e2a4988837eedd1e84634f048c3e02cc9ac2400f2540785656 +size 695182272 diff --git a/Bangla-AI-1.7B.i1-IQ2_S.gguf b/Bangla-AI-1.7B.i1-IQ2_S.gguf new file mode 100644 index 0000000..3f66a79 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7fbdd35c62671f1e358d217f4217ca16813efccf64d7dffc6152211dfeae05 +size 657826752 diff --git a/Bangla-AI-1.7B.i1-IQ2_XS.gguf b/Bangla-AI-1.7B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..81f5b14 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a574a3b5e7705086d263fb28404c036c5c2094ac66a469958e375545646c48 +size 631514048 diff --git a/Bangla-AI-1.7B.i1-IQ2_XXS.gguf b/Bangla-AI-1.7B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b0da5c7 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e355420f449ba7b4e61afb1f6e64f596f5243b29d6638df213f79e58607665fb +size 590488512 diff --git a/Bangla-AI-1.7B.i1-IQ3_M.gguf b/Bangla-AI-1.7B.i1-IQ3_M.gguf new file mode 100644 index 0000000..803de88 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3eb6eece958030b5238045a2f25c08f6b55e3bb0cf3162494937a3d1a040058 +size 895663040 diff --git a/Bangla-AI-1.7B.i1-IQ3_S.gguf b/Bangla-AI-1.7B.i1-IQ3_S.gguf new file mode 100644 index 0000000..59c7bd8 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20647656d6c22a7c0e0978ce506f4884890d0ba29c7dc6e7f2db164eb62d5a16 +size 867253184 diff --git a/Bangla-AI-1.7B.i1-IQ3_XS.gguf b/Bangla-AI-1.7B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..639e0ef --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42867ab8a36a70ec01e122f4588840974fb4786a374dfe4d2d0e47c6b76c68e1 +size 834223040 diff --git a/Bangla-AI-1.7B.i1-IQ3_XXS.gguf b/Bangla-AI-1.7B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..308df4b --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca65282a1e9b9c17fbe9d48076ed144cfc3811af3351a127b1118c65fada241 +size 754361280 diff --git a/Bangla-AI-1.7B.i1-IQ4_NL.gguf b/Bangla-AI-1.7B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..225ab32 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4e7168ce5b73acbe808f1b3eb02d1774ad7b618c9660d00afb888faee07c8c +size 1054424000 diff --git a/Bangla-AI-1.7B.i1-IQ4_XS.gguf b/Bangla-AI-1.7B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4600b95 --- /dev/null +++ b/Bangla-AI-1.7B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31433f63524688dcd685c25af6855e25398f2e00b05496438c0e6c277ce43cd +size 1010383808 diff --git a/Bangla-AI-1.7B.i1-Q2_K.gguf b/Bangla-AI-1.7B.i1-Q2_K.gguf new file mode 100644 index 0000000..a60c301 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6565454bd62d0551b3c9d618ef11c9f954e24dbee9f11bd4ec2413b0ae3ee2b3 +size 777796544 diff --git a/Bangla-AI-1.7B.i1-Q2_K_S.gguf b/Bangla-AI-1.7B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dad0170 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7a878302697577c2cfbe2bcd800bfed7d6fe707a90a0cf56fc6efaf04f83bf +size 732969920 diff --git a/Bangla-AI-1.7B.i1-Q3_K_L.gguf b/Bangla-AI-1.7B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..33cf714 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded2fe5e65a8926d78312cd893f5d9fc6a1365933320e06b3aab8182a0e65294 +size 1003502528 diff --git a/Bangla-AI-1.7B.i1-Q3_K_M.gguf b/Bangla-AI-1.7B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..9bee534 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195cf778a9905ed9df9c8f5a78f115af2c749aa355f5869ac221359091fc2a1b +size 939539392 diff --git a/Bangla-AI-1.7B.i1-Q3_K_S.gguf b/Bangla-AI-1.7B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..fe56e7d --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24148a97f6565afef8ddda66f2eab3dbcf4f8416784b8458db17e027d9570cfe +size 867253184 diff --git a/Bangla-AI-1.7B.i1-Q4_0.gguf b/Bangla-AI-1.7B.i1-Q4_0.gguf new file mode 100644 index 0000000..5b3bffa --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00941222e80e62134567bc4a9378959938db4751fe5a955aadc28fe0a544a65f +size 1056783296 diff --git a/Bangla-AI-1.7B.i1-Q4_1.gguf b/Bangla-AI-1.7B.i1-Q4_1.gguf new file mode 100644 index 0000000..c5a02cf --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77ebbac0cd468a0a07f6b1e23cf21c45e87b36a9edf4f3e74d22b34129be088 +size 1142504384 diff --git a/Bangla-AI-1.7B.i1-Q4_K_M.gguf b/Bangla-AI-1.7B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0499be7 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474d50c37557aa44426e5c7f10f43043555d0d8e1907c568c85866eed9f9d5ca +size 1107409856 diff --git a/Bangla-AI-1.7B.i1-Q4_K_S.gguf b/Bangla-AI-1.7B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9272cff --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcab1495fd17fc627f9440b82a2854738f9081ea1be1ece87f1d28727d8afd8d +size 1060191168 diff --git a/Bangla-AI-1.7B.i1-Q5_K_M.gguf b/Bangla-AI-1.7B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4a7ebef --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f33f562a89b409a58c8723a7b10df79bf8c1ce185f96153b1174ebb46e3ecf +size 1257880512 diff --git a/Bangla-AI-1.7B.i1-Q5_K_S.gguf b/Bangla-AI-1.7B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..71b8631 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd5e7c7d73cd6cec92bdf134cd80c6d008a2504e1fc764e08d1bb5b35d00221 +size 1230584768 diff --git a/Bangla-AI-1.7B.i1-Q6_K.gguf b/Bangla-AI-1.7B.i1-Q6_K.gguf new file mode 100644 index 0000000..97a5fd2 --- /dev/null +++ b/Bangla-AI-1.7B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666ac23b11c3ede3e1d443ec1823cb1a1b4bfa1bef12b90baef8cff967b3ee28 +size 1417755584 diff --git a/Bangla-AI-1.7B.imatrix.gguf b/Bangla-AI-1.7B.imatrix.gguf new file mode 100644 index 0000000..5a27d70 --- /dev/null +++ b/Bangla-AI-1.7B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f2048530bff0dc157e7370707098c61a3de1c720754805fa7c97ce95d56e7c +size 2094560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7496c11 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: swapnillo/Bangla-AI-1.7B +datasets: +- md-nishat-008/Bangla-Instruct +language: +- en +- bn +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/swapnillo/Bangla-AI-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bangla-AI-1.7B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Bangla-AI-1.7B-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/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q4_1.gguf) | i1-Q4_1 | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-AI-1.7B-i1-GGUF/resolve/main/Bangla-AI-1.7B.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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. + +