commit 4b30f84ac9c0df97148c3e8c12843dd4661a9114 Author: ModelHub XC Date: Sat Jun 20 02:28:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47180ee --- /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 +Bangla-TinyLlama-1.1B-Distilled.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-TinyLlama-1.1B-Distilled.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bangla-TinyLlama-1.1B-Distilled.IQ4_XS.gguf b/Bangla-TinyLlama-1.1B-Distilled.IQ4_XS.gguf new file mode 100644 index 0000000..24969e1 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f99f8a0329f8a3075d3b3d1d197768941b5fce2f4f7a722b621f2ed1c5ee45d +size 609809248 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q2_K.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q2_K.gguf new file mode 100644 index 0000000..169e427 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e77bb8247e6e559069e82b65c4134e023c00cf86d68c1765ea5b45a284c718 +size 432132960 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q3_K_L.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_L.gguf new file mode 100644 index 0000000..2dd9225 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4252643407ec7e1b4b735445acef4ca26927d807aeecfd2b4589065e1baa7c20 +size 591528800 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q3_K_M.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_M.gguf new file mode 100644 index 0000000..cf77eac --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867374beca54335387af771e94185abc73351fff84af27299b250f84f8ef49bc +size 548406112 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q3_K_S.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_S.gguf new file mode 100644 index 0000000..8a07517 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485605d3c47f5fa9a7896f33f9e0bfead36b203b808de5ef770e0cf3c5cb7eba +size 499344224 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q4_K_M.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q4_K_M.gguf new file mode 100644 index 0000000..bc49c0b --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abd477b0a7d9fad7882b10e3b20c8f3e5e97695c66b6b26605735a4195033c9 +size 667816800 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q4_K_S.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q4_K_S.gguf new file mode 100644 index 0000000..e4a8ec2 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee17fc1b7f255e0a4506efea572f5172de49bd7b56928d601873748bf17e3a7 +size 639873888 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q5_K_M.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q5_K_M.gguf new file mode 100644 index 0000000..bc51ed8 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dae6ca12f45444b095ab55ae6c6132f848963d813bdf5456f63f7de11a44943 +size 782046048 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q5_K_S.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q5_K_S.gguf new file mode 100644 index 0000000..3410af0 --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1fffa8a1b9f33ab61174ddba5abda09687eb51b901ce38dfbc5de617b8b34d +size 766030688 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q6_K.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q6_K.gguf new file mode 100644 index 0000000..c25c05d --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963a810b718ab67cd2847ea2968559df0b3ae60ab347bb5ffafecf6ef5472dbc +size 903414624 diff --git a/Bangla-TinyLlama-1.1B-Distilled.Q8_0.gguf b/Bangla-TinyLlama-1.1B-Distilled.Q8_0.gguf new file mode 100644 index 0000000..61a1e1a --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fba7713bad53949e5404972cb1cb6bb1e5358b0d07bc4321c951ec964d625271 +size 1169810272 diff --git a/Bangla-TinyLlama-1.1B-Distilled.f16.gguf b/Bangla-TinyLlama-1.1B-Distilled.f16.gguf new file mode 100644 index 0000000..c7b9e0c --- /dev/null +++ b/Bangla-TinyLlama-1.1B-Distilled.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c312df08f0b57c717aca7102a18de1c101191d432496e845e18f8c6792ec12af +size 2201019232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1340244 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: tajshuvo/Bangla-TinyLlama-1.1B-Distilled +datasets: +- md-nishat-008/Bangla-Instruct +language: +- bn +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tajshuvo/Bangla-TinyLlama-1.1B-Distilled + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bangla-TinyLlama-1.1B-Distilled-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-TinyLlama-1.1B-Distilled-GGUF/resolve/main/Bangla-TinyLlama-1.1B-Distilled.f16.gguf) | f16 | 2.3 | 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. + +