commit 019c7705c67e0c61347468960b6154246d329c5e Author: ModelHub XC Date: Mon May 4 21:30:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Malaysian-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75f6a1f --- /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 +Malaysian-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Malaysian-Llama-3.2-1B.IQ4_XS.gguf b/Malaysian-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..085bebb --- /dev/null +++ b/Malaysian-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1728d419f6d4ea88ce59551334f1e3b093d9e9070e601b097e434ef9bf094e59 +size 887926976 diff --git a/Malaysian-Llama-3.2-1B.Q2_K.gguf b/Malaysian-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..1b22236 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bdd14664a3d855f745106a30d148e36b0901092b9505869d992835201d7b34 +size 667062464 diff --git a/Malaysian-Llama-3.2-1B.Q3_K_L.gguf b/Malaysian-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..bd37874 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af0bdf43f4284494b0cd290fdd82d7e4256dc4dafbbe3a00f91341bd283f408 +size 845390016 diff --git a/Malaysian-Llama-3.2-1B.Q3_K_M.gguf b/Malaysian-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..113d32c --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aacb70293b2fbb7b4c787a6caa00a80462ec49b7fcc7e87f5b40cc1d8a627c5 +size 803709120 diff --git a/Malaysian-Llama-3.2-1B.Q3_K_S.gguf b/Malaysian-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..41f645a --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52ee877c52c66ee2b65b7193a14e46ad17e20670b3b367c37dc566f3c29da78 +size 754557120 diff --git a/Malaysian-Llama-3.2-1B.Q4_K_M.gguf b/Malaysian-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..1a2cafb --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23dd7ca96eb9d984aadb84b4a74ba85841a38cbcd3adb7e78f782ee9b118103a +size 955445440 diff --git a/Malaysian-Llama-3.2-1B.Q4_K_S.gguf b/Malaysian-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..c3aed0d --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5023e601008ca172cb094c153f7b5016b26c100f4bc276ff57b7a82592af4cc6 +size 923398336 diff --git a/Malaysian-Llama-3.2-1B.Q5_K_M.gguf b/Malaysian-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..c348396 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584581877e408a0880adb6c2901b696b9143f45d558022822c3a0e601ad02278 +size 1092088000 diff --git a/Malaysian-Llama-3.2-1B.Q5_K_S.gguf b/Malaysian-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..43c3379 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0ad471d387410858c375d099236ca803c07c2575c52bbf9beb94859ee8b0dc +size 1073148096 diff --git a/Malaysian-Llama-3.2-1B.Q6_K.gguf b/Malaysian-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..14968bd --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4700ba43b1f9df40ddef8d406df05f62be1f5754dcfd990dee91577761aba27b +size 1237270720 diff --git a/Malaysian-Llama-3.2-1B.Q8_0.gguf b/Malaysian-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..5c10464 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4a6d345ab9ec0bee3054552434e59c31b665a57a8edbb3738592bfb3b9d98e +size 1600168128 diff --git a/Malaysian-Llama-3.2-1B.f16.gguf b/Malaysian-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..27c69d6 --- /dev/null +++ b/Malaysian-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ecc7016661abe2a1a9be1afa6918e54deb7042a7d229eeeaaf3c01d15e24ef3 +size 3004932288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb5377b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mesolitica/Malaysian-Llama-3.2-1B-Instruct-v0.2 +datasets: +- mesolitica/Malaysian-SFT +language: +- ms +- en +- zh +- ta +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mesolitica/Malaysian-Llama-3.2-1B-Instruct-v0.2 + + +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/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.2-1B-GGUF/resolve/main/Malaysian-Llama-3.2-1B.f16.gguf) | f16 | 3.1 | 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. + +