commit 08e3ece7bdcd08dd79dd0e9785cc1d8681936862 Author: ModelHub XC Date: Sat Jun 20 05:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16e9f20 --- /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 +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLama-3-8b-Bangla2B-base-v0.0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.IQ4_XS.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.IQ4_XS.gguf new file mode 100644 index 0000000..f347c41 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a107f4a0e0cc641b9c9ab70c087b0b37ee2f1987b17078fd48451684fe3ffb3 +size 4484363424 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q2_K.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q2_K.gguf new file mode 100644 index 0000000..fff4c4f --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd40232954d82dd1bddeb48fa5a928c7cc17d53df312e962ac7b7ba4510f4061 +size 3179132064 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_L.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_L.gguf new file mode 100644 index 0000000..7cd10ab --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb7e842680343a69c9340268272c2ee8f0d2ae2018877d3897788a6a8ae6252 +size 4321957024 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_M.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_M.gguf new file mode 100644 index 0000000..987cc32 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7df617c765d7f050d3022f3e47b338296517e16b5ffc73cf73b169a339d9839 +size 4018918560 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_S.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_S.gguf new file mode 100644 index 0000000..4353eab --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d410865a27ee9f820c50ab1139df6569fdee061d793c0eab560789df6c978f +size 3664499872 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_M.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_M.gguf new file mode 100644 index 0000000..6b1f901 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78935b37f99b90320b6d2a97a11529fb86eebe556ca9e8f263c0dde6a6029131 +size 4920734880 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_S.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_S.gguf new file mode 100644 index 0000000..80932c9 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a0bc20cc8d579c2ad6a49fd1a3db1b64ce72c82e4f1ab42928a7891f993d57 +size 4692669600 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_M.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_M.gguf new file mode 100644 index 0000000..556c549 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d434bedc1131cc099a696d41438a57b1aee70c54ef61a467c76b8cb99961f39 +size 5732988064 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_S.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_S.gguf new file mode 100644 index 0000000..c1cd96b --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7a25527de89a549b4473aa801fd87e3b5326bef757058fea2ee9dabb55260a +size 5599294624 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q6_K.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q6_K.gguf new file mode 100644 index 0000000..7a8f3f7 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825530d1b12f85ae3104354f6646dd1eaeed0b12e2e2a4bafbe640995d50f55e +size 6596007072 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q8_0.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q8_0.gguf new file mode 100644 index 0000000..de6f42c --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6d86996201e8a4cf1670d70863a9bfc41fcd01f492ec49a697d61e7e96aab0 +size 8540771488 diff --git a/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.f16.gguf b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.f16.gguf new file mode 100644 index 0000000..7cf5702 --- /dev/null +++ b/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0389abc1a8e4018f7e0e27d5bee6da8e832e0d6c4f3605a18163ea0d20e6f35 +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b57125d --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: BanglaLLM/BanglaLLama-3-8b-Bangla2B-base-v0.0.1 +language: +- bn +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- bengali +- bangalnlp +- nlp +- bangla +- bangladesh +- transformer +- LLama +- banglallama +--- +## About + + + + + + +static quants of https://huggingface.co/BanglaLLM/BanglaLLama-3-8b-Bangla2B-base-v0.0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BanglaLLama-3-8b-Bangla2B-base-v0.0.1-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/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLama-3-8b-Bangla2B-base-v0.0.1-GGUF/resolve/main/BanglaLLama-3-8b-Bangla2B-base-v0.0.1.f16.gguf) | f16 | 16.2 | 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. + +