commit 434fe4521ef6af3b52f9403ad1031b1f6aaf0427 Author: ModelHub XC Date: Fri Jul 10 05:56:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Malaysian-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e33b23 --- /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 +Llama-3.2-3B-Malaysian.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Malaysian.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Malaysian.IQ4_XS.gguf b/Llama-3.2-3B-Malaysian.IQ4_XS.gguf new file mode 100644 index 0000000..967a0b5 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d73d40f8fb9f3f872b91a529550fd141763ca7119cda4b8000b4aab293849e7 +size 2050220672 diff --git a/Llama-3.2-3B-Malaysian.Q2_K.gguf b/Llama-3.2-3B-Malaysian.Q2_K.gguf new file mode 100644 index 0000000..c16d978 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f315938c1e1d624163c0c41cc2265c7ffbc4bd5c396b9d70af99ae421557da +size 1493217920 diff --git a/Llama-3.2-3B-Malaysian.Q3_K_L.gguf b/Llama-3.2-3B-Malaysian.Q3_K_L.gguf new file mode 100644 index 0000000..233e750 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95711533797850f286c8af01a202369e3c50d780503e73f869b3582bd1c597b +size 1984645760 diff --git a/Llama-3.2-3B-Malaysian.Q3_K_M.gguf b/Llama-3.2-3B-Malaysian.Q3_K_M.gguf new file mode 100644 index 0000000..b3b8ca5 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cae66f2afb3dd165099961a1d86725f97399f44961dc5add4df8233a6c27a8a +size 1856457344 diff --git a/Llama-3.2-3B-Malaysian.Q3_K_S.gguf b/Llama-3.2-3B-Malaysian.Q3_K_S.gguf new file mode 100644 index 0000000..05282e0 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67bea5da67715430d7b2ec4d91605856b48118f9b497def9f4eb916e945a761f +size 1712147072 diff --git a/Llama-3.2-3B-Malaysian.Q4_K_M.gguf b/Llama-3.2-3B-Malaysian.Q4_K_M.gguf new file mode 100644 index 0000000..88e1dda --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d038751effd2a6d810cf341ffed11fb2148387f51efa6504c9286a541f72f4a7 +size 2241004160 diff --git a/Llama-3.2-3B-Malaysian.Q4_K_S.gguf b/Llama-3.2-3B-Malaysian.Q4_K_S.gguf new file mode 100644 index 0000000..f5a21e5 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf77cd286ecb4fa87e3cb68d661605a31ddf9b37c5b02d58d12f9d0d36c0a0c +size 2149827200 diff --git a/Llama-3.2-3B-Malaysian.Q5_K_M.gguf b/Llama-3.2-3B-Malaysian.Q5_K_M.gguf new file mode 100644 index 0000000..2f288e8 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c00aee1b203def76c2c6e0410d7fe30d3c8af7fce2ab9e82254d7c3591f7a8d +size 2593030784 diff --git a/Llama-3.2-3B-Malaysian.Q5_K_S.gguf b/Llama-3.2-3B-Malaysian.Q5_K_S.gguf new file mode 100644 index 0000000..de23370 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0598a1e5e2a2a0c32c3db17264362db26614ce05dcf9b82538a6fa4d2783845d +size 2540388992 diff --git a/Llama-3.2-3B-Malaysian.Q6_K.gguf b/Llama-3.2-3B-Malaysian.Q6_K.gguf new file mode 100644 index 0000000..9654e27 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21c49a1b2d9509502caa52375d856e32765f45e2a4b3167f22997f6a5628996 +size 2967059072 diff --git a/Llama-3.2-3B-Malaysian.Q8_0.gguf b/Llama-3.2-3B-Malaysian.Q8_0.gguf new file mode 100644 index 0000000..5be4d97 --- /dev/null +++ b/Llama-3.2-3B-Malaysian.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adb7bafd0d32510a4e8273318046e63a3241d3bcc6c999592b603c3e5328f75a +size 3840526976 diff --git a/Llama-3.2-3B-Malaysian.f16.gguf b/Llama-3.2-3B-Malaysian.f16.gguf new file mode 100644 index 0000000..27aac0b --- /dev/null +++ b/Llama-3.2-3B-Malaysian.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd78907e547433a16613b7415da5142ab3eb4257d354373450d3d054d08dd88c +size 7221693056 diff --git a/README.md b/README.md new file mode 100644 index 0000000..596152e --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: mesolitica/Malaysian-Llama-3.2-3B-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-3.2-3B-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/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Malaysian-GGUF/resolve/main/Llama-3.2-3B-Malaysian.f16.gguf) | f16 | 7.3 | 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. + +