commit 852184f8e8b7c42132e06cff2f9c08b003d5354f Author: ModelHub XC Date: Wed Jul 22 03:33:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bahasa-4b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba78ef4 --- /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 +Bahasa-4b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bahasa-4b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bahasa-4b.IQ4_XS.gguf b/Bahasa-4b.IQ4_XS.gguf new file mode 100644 index 0000000..52617c2 --- /dev/null +++ b/Bahasa-4b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a1a53daf7672581874677da483b11c13d927f6f6e799c8258160af468702cc +size 2232630112 diff --git a/Bahasa-4b.Q2_K.gguf b/Bahasa-4b.Q2_K.gguf new file mode 100644 index 0000000..5d00aea --- /dev/null +++ b/Bahasa-4b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b08eb18229488c31f953de029988f3b3995fcac5ea8e28dc2ba41c2e4f8115 +size 1620631392 diff --git a/Bahasa-4b.Q3_K_L.gguf b/Bahasa-4b.Q3_K_L.gguf new file mode 100644 index 0000000..9fdef47 --- /dev/null +++ b/Bahasa-4b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d143ca77a7e2bf15954330eccea5a23806c9d4dd43d0914b757b7eeb614de986 +size 2174797152 diff --git a/Bahasa-4b.Q3_K_M.gguf b/Bahasa-4b.Q3_K_M.gguf new file mode 100644 index 0000000..497812a --- /dev/null +++ b/Bahasa-4b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23ea6bb12f5f99fa449566f466c4c667315c18af0fb802251053a88973111a4 +size 2026849632 diff --git a/Bahasa-4b.Q3_K_S.gguf b/Bahasa-4b.Q3_K_S.gguf new file mode 100644 index 0000000..7317da2 --- /dev/null +++ b/Bahasa-4b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8988400dcab88642cc29fb06755889bc5742dd26cd83d15c5febbf9c6ab3afca +size 1857152352 diff --git a/Bahasa-4b.Q4_K_M.gguf b/Bahasa-4b.Q4_K_M.gguf new file mode 100644 index 0000000..5035a38 --- /dev/null +++ b/Bahasa-4b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28d3aeef4ccdcc1961d250332b64121e9f8a114b103e2a7de0013aa1c7a58d1b +size 2455114592 diff --git a/Bahasa-4b.Q4_K_S.gguf b/Bahasa-4b.Q4_K_S.gguf new file mode 100644 index 0000000..9e16b3e --- /dev/null +++ b/Bahasa-4b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb152975ca3480941470942265e5c06a15ddb12e8ff85e52ffdb78c2881d121 +size 2344420192 diff --git a/Bahasa-4b.Q5_K_M.gguf b/Bahasa-4b.Q5_K_M.gguf new file mode 100644 index 0000000..f422b5e --- /dev/null +++ b/Bahasa-4b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55dbe9e2b445f96ab25d2c14730fb22f7dd82b8cc4c8ae43d55207407c0133c +size 2839606112 diff --git a/Bahasa-4b.Q5_K_S.gguf b/Bahasa-4b.Q5_K_S.gguf new file mode 100644 index 0000000..0e6d885 --- /dev/null +++ b/Bahasa-4b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adcaed57128e53e822c766c9b55d2448f1afc9443261ec63f9618601aa9da88 +size 2775196512 diff --git a/Bahasa-4b.Q6_K.gguf b/Bahasa-4b.Q6_K.gguf new file mode 100644 index 0000000..2ba438b --- /dev/null +++ b/Bahasa-4b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0300dc54863567dd9e69b99b55e76ca3b8fa412b641a528ec5b02629a309d8 +size 3248128352 diff --git a/Bahasa-4b.Q8_0.gguf b/Bahasa-4b.Q8_0.gguf new file mode 100644 index 0000000..370d714 --- /dev/null +++ b/Bahasa-4b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3850e35312aded9f3f1a53d8fdf48c69cd3985e7680487fa72b9808b2843aecd +size 4204733792 diff --git a/Bahasa-4b.f16.gguf b/Bahasa-4b.f16.gguf new file mode 100644 index 0000000..5da7112 --- /dev/null +++ b/Bahasa-4b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c12973a9e5f9305d2cc1f7382cc595f81898a447c485f662f121dde9e400662 +size 7907722592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2d48be --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: Bahasalab/Bahasa-4b +language: +- id +library_name: transformers +license: other +license_name: tongyi-qianwen +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Bahasalab/Bahasa-4b + + +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/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bahasa-4b-GGUF/resolve/main/Bahasa-4b.f16.gguf) | f16 | 8.0 | 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. 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. + +