commit f9ceac5e539d7dbddd645997a98d65c833a6ada6 Author: ModelHub XC Date: Tue May 26 10:46:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94325b6 --- /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-3.1-8B-Instruct-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Malaysian-Llama-3.1-8B-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.IQ4_XS.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..9d2625b --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c993917a5f1119c6dc91db3156dc0a61b8b7798d508f326462482555016c8faf +size 4484368288 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q2_K.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..1148cd6 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2839c523ec466bcd4c9a59a44280284a108331203c3a1a0e1a308b24371d268a +size 3179136928 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_L.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..056027a --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018200ecffed1fdb4a19412449de7058b1c86e1119b60f407e42c4cd0abc6813 +size 4321961888 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_M.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..9a52ad1 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0123f2cf65b8db90029365257a14fec7a24a8074391a5a512ddae1ed16f849e2 +size 4018923424 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_S.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..070dea8 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80dfa491c32c035a5879fc76cd5d16da734639a51c35be8418bf5684a52397fe +size 3664504736 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_M.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..59a274d --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475a169b90ae04a335fcbd4b47da7d7b9316be04ff09f11e559ac5ae9dee78c7 +size 4920739744 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_S.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..d03a2fc --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128bde2976fab102cd5812968efe5d927b5d655fc08831f7cc14bc7112e5843b +size 4692674464 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_M.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..fe53bc6 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad35b0d978662df76195494351e0c39ac4ffb805d895b9cd7ad8ef7518fde4f1 +size 5732992928 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_S.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..b1634ba --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41edfc9cd8adeb8ef84fc5fe883885a1aea09b289b610ea5f9ee6a730b60c6a +size 5599299488 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q6_K.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..160ce29 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249a28f0837ae551882891b4562a36ccf72fba268c44548021ecf2d576995243 +size 6596011936 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q8_0.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..4b19dad --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263ebb5f26e7d8424c58a825db93d60ca34c7a79564d2c2257d900638374d974 +size 8540776352 diff --git a/Malaysian-Llama-3.1-8B-Instruct-v0.1.f16.gguf b/Malaysian-Llama-3.1-8B-Instruct-v0.1.f16.gguf new file mode 100644 index 0000000..5a38d79 --- /dev/null +++ b/Malaysian-Llama-3.1-8B-Instruct-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b0f1e8605b619d84d551c323c53abebb0dcfccdc92dee1ae10dc9f0263718b +size 16068896672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec4e866 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: mesolitica/Malaysian-Llama-3.1-8B-Instruct-v0.1 +datasets: +- mesolitica/Malaysian-SFT +language: +- ms +- en +- zh +- ta +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mesolitica/Malaysian-Llama-3.1-8B-Instruct-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Malaysian-Llama-3.1-8B-Instruct-v0.1-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/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Malaysian-Llama-3.1-8B-Instruct-v0.1-GGUF/resolve/main/Malaysian-Llama-3.1-8B-Instruct-v0.1.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. + +