commit bb076dfa89585a8240ecb10b752512aec91a9067 Author: ModelHub XC Date: Sat Sep 5 09:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/malaysian-llama-3-8b-262k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5160836 --- /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-262k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.f16.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +malaysian-llama-3-8b-262k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8be83f7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mesolitica/malaysian-llama-3-8b-262k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + +static quants of https://huggingface.co/mesolitica/malaysian-llama-3-8b-262k + + +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-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.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-262k.IQ3_M.gguf b/malaysian-llama-3-8b-262k.IQ3_M.gguf new file mode 100644 index 0000000..b68f0bb --- /dev/null +++ b/malaysian-llama-3-8b-262k.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec1477e7d6deb4a0d64fd4b14839c5035f23c0d8aac3a97af3246319e10c07e +size 3784823104 diff --git a/malaysian-llama-3-8b-262k.IQ3_S.gguf b/malaysian-llama-3-8b-262k.IQ3_S.gguf new file mode 100644 index 0000000..5bb4382 --- /dev/null +++ b/malaysian-llama-3-8b-262k.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9dc13b803996a99591409aea95df12f1bd5e51411a9a2428f027700606d9d10 +size 3682324800 diff --git a/malaysian-llama-3-8b-262k.IQ3_XS.gguf b/malaysian-llama-3-8b-262k.IQ3_XS.gguf new file mode 100644 index 0000000..ad49421 --- /dev/null +++ b/malaysian-llama-3-8b-262k.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207a98104ffe909ca15c6f47636626d4b9647250106a7bc05399ac83e0821cc4 +size 3518746944 diff --git a/malaysian-llama-3-8b-262k.IQ4_XS.gguf b/malaysian-llama-3-8b-262k.IQ4_XS.gguf new file mode 100644 index 0000000..e2f23df --- /dev/null +++ b/malaysian-llama-3-8b-262k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ef710e7799e2445984b836da829bcc3d649e7b5a4fde9244ac1a902ca9490a +size 4484362560 diff --git a/malaysian-llama-3-8b-262k.Q2_K.gguf b/malaysian-llama-3-8b-262k.Q2_K.gguf new file mode 100644 index 0000000..203f5f1 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf6fbdcbc9f6978e896b03bebb5ef2223c3c5f4ad66d7c22e0cebf690050be1 +size 3179131200 diff --git a/malaysian-llama-3-8b-262k.Q3_K_L.gguf b/malaysian-llama-3-8b-262k.Q3_K_L.gguf new file mode 100644 index 0000000..c3b4037 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d8a46f37516e5404773f8e41140e8768f42f82e2ce7c7fe814cde2519dce5c +size 4321956160 diff --git a/malaysian-llama-3-8b-262k.Q3_K_M.gguf b/malaysian-llama-3-8b-262k.Q3_K_M.gguf new file mode 100644 index 0000000..072d2a6 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0571ab73242c0f7711fc52ad3706a682429c5ed6b2cbeab891f8bdfb7ada1c6b +size 4018917696 diff --git a/malaysian-llama-3-8b-262k.Q3_K_S.gguf b/malaysian-llama-3-8b-262k.Q3_K_S.gguf new file mode 100644 index 0000000..be9b8ff --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7f595df857a9fdf656fe142a9506acea6e320679452483a7a30b10c961fc03 +size 3664499008 diff --git a/malaysian-llama-3-8b-262k.Q4_K_M.gguf b/malaysian-llama-3-8b-262k.Q4_K_M.gguf new file mode 100644 index 0000000..f7e3b91 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb74a7c0dec474ed779a27fef468aac70e1eb4a4129dc3bfa7ee1e1b25678c3b +size 4920734016 diff --git a/malaysian-llama-3-8b-262k.Q4_K_S.gguf b/malaysian-llama-3-8b-262k.Q4_K_S.gguf new file mode 100644 index 0000000..1f9f03f --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385e31770fff647453c4a570f8ae9c6d2fcd5a89fd8ef3b59a2409ed6f4971b5 +size 4692668736 diff --git a/malaysian-llama-3-8b-262k.Q5_K_M.gguf b/malaysian-llama-3-8b-262k.Q5_K_M.gguf new file mode 100644 index 0000000..778a93b --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e07a6a0dbaaceb1c736add0f0ec5fbac985e106011b81a7978e10ebf23e9aab +size 5732987200 diff --git a/malaysian-llama-3-8b-262k.Q5_K_S.gguf b/malaysian-llama-3-8b-262k.Q5_K_S.gguf new file mode 100644 index 0000000..a76f175 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7786c208fc631b08eb524414b2bac85349a7f1e3a29d964292e866753673e33b +size 5599293760 diff --git a/malaysian-llama-3-8b-262k.Q6_K.gguf b/malaysian-llama-3-8b-262k.Q6_K.gguf new file mode 100644 index 0000000..3b0c914 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c726754dfb4d35444c09a7fe7b142a1c9e02e40f3d437f6592eb358ff62ac6a +size 6596006208 diff --git a/malaysian-llama-3-8b-262k.Q8_0.gguf b/malaysian-llama-3-8b-262k.Q8_0.gguf new file mode 100644 index 0000000..bb9e618 --- /dev/null +++ b/malaysian-llama-3-8b-262k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c612b7acccea42c81e05521c5dee0af3cc5b78f79c51327ab356f604b47915f +size 8540770624 diff --git a/malaysian-llama-3-8b-262k.f16.gguf b/malaysian-llama-3-8b-262k.f16.gguf new file mode 100644 index 0000000..36eb3f8 --- /dev/null +++ b/malaysian-llama-3-8b-262k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b22f77342ad109ec3504bc7e187a49a6643900477d12ffc04c6d7e76a1d94d +size 16068890944