commit 8b3b715c26b985bb36ba6ae25c3cadc91a0f8f97 Author: ModelHub XC Date: Fri Sep 25 07:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d1cae7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3-8b-instruct-16k-post.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.f16.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-instruct-16k-post.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d836d69 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mesolitica/malaysian-llama-3-8b-instruct-16k-post +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mesolitica/malaysian-llama-3-8b-instruct-16k-post + + +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-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-instruct-16k-post-GGUF/resolve/main/malaysian-llama-3-8b-instruct-16k-post.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. + + diff --git a/malaysian-llama-3-8b-instruct-16k-post.IQ3_M.gguf b/malaysian-llama-3-8b-instruct-16k-post.IQ3_M.gguf new file mode 100644 index 0000000..e5176ff --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a46e3ed8e804153bc85c52a82f68f9547d0ebd0f36c08b0a188998bb23a34c +size 3784823520 diff --git a/malaysian-llama-3-8b-instruct-16k-post.IQ3_S.gguf b/malaysian-llama-3-8b-instruct-16k-post.IQ3_S.gguf new file mode 100644 index 0000000..4e6aa62 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d5c8f9119f818d87bc6fb46580438d756133799b6b6fde05388b5084019c12d +size 3682325216 diff --git a/malaysian-llama-3-8b-instruct-16k-post.IQ3_XS.gguf b/malaysian-llama-3-8b-instruct-16k-post.IQ3_XS.gguf new file mode 100644 index 0000000..a82f849 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdcb1dc3ddd63c16113a62f08c9e3b8cd76cbe03f06b666f9ab702cf9a623ae +size 3518747360 diff --git a/malaysian-llama-3-8b-instruct-16k-post.IQ4_XS.gguf b/malaysian-llama-3-8b-instruct-16k-post.IQ4_XS.gguf new file mode 100644 index 0000000..f61c0ef --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38192108181e02747ba3fbe9041c9e726fa07ef33ef598829fd8611d677f1efc +size 4484362976 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q2_K.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q2_K.gguf new file mode 100644 index 0000000..bb96a33 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e14854df29938d41a47c634382509707cbfa4bf85051b2aca1f9afc2b4647de +size 3179131616 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q3_K_L.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_L.gguf new file mode 100644 index 0000000..de66dfb --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba3ef43f758c175187158b7d2bba3d0678af63e2f6ae1bcf22647aae5b4d57f +size 4321956576 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q3_K_M.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_M.gguf new file mode 100644 index 0000000..0323719 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23d5d872a0e2fbba45b7bfb6361c49c752ffcf507b5b22e2a3eb610b2657b4d +size 4018918112 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q3_K_S.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_S.gguf new file mode 100644 index 0000000..c0982da --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a41b7f4ad243cf8a253e54b90f9576bac8275335d666279a432282ba5fbb163 +size 3664499424 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q4_K_M.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q4_K_M.gguf new file mode 100644 index 0000000..2bbf4d5 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4255c4c9d822b15733f73a3ae9e72354789c74752f2dcb67ab8794dab3fd3e +size 4920734432 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q4_K_S.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q4_K_S.gguf new file mode 100644 index 0000000..1c4cebb --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8d4d4a3dfe586ae2ab5e934eec9c596b6ba1fa82305e1b7c27ecced7c2a359 +size 4692669152 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q5_K_M.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q5_K_M.gguf new file mode 100644 index 0000000..07ff38a --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b966ed44760f6339a66018349a80512773c0f34a4634be0cbac2cb463c7e5c0c +size 5732987616 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q5_K_S.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q5_K_S.gguf new file mode 100644 index 0000000..a7478eb --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae2ffec81521a0066f831524774ff2e664cd857744d634b37360bf22b57091f +size 5599294176 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q6_K.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q6_K.gguf new file mode 100644 index 0000000..ade432f --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5742355e391798c8e792da9d4ed1393fb8b6c92d5b4e4b58ba7b89a1f5d80bd +size 6596006624 diff --git a/malaysian-llama-3-8b-instruct-16k-post.Q8_0.gguf b/malaysian-llama-3-8b-instruct-16k-post.Q8_0.gguf new file mode 100644 index 0000000..0cbb4b9 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629dcd4db85a2b5c7d9f7c4529f4399e8c1713aa13155063363514cb8dc6d365 +size 8540771040 diff --git a/malaysian-llama-3-8b-instruct-16k-post.f16.gguf b/malaysian-llama-3-8b-instruct-16k-post.f16.gguf new file mode 100644 index 0000000..0d097f3 --- /dev/null +++ b/malaysian-llama-3-8b-instruct-16k-post.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ca031c30e18b7a5909a9b731fb3cfe952f99061a569d2eb7447983f820e516 +size 16068891360