commit d13e3a9f205484cc5109d68062f42d485dc97329 Author: ModelHub XC Date: Mon Sep 7 08:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..57740c4 --- /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 +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.f16.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9960fc6 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mesolitica/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mesolitica/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k + + +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/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.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/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_M.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_M.gguf new file mode 100644 index 0000000..70901f1 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda9aeabf83a627dfd228d8b68955126d2ece50c6fbbb40cce31885de7fe45c0 +size 3784828288 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_S.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_S.gguf new file mode 100644 index 0000000..98e5aa3 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1999702b1e2069421143e81cbee6116362f73a568942a58e1e7af5ee2d43a37d +size 3682329984 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf new file mode 100644 index 0000000..50a5299 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e10504988dde5bc550fc9acdb00a8df49a5ea2c25f43bba67cd39ee3564cf1 +size 3518752128 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf new file mode 100644 index 0000000..1aadcac --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f04e85fdb5e1b94e9513440c8ff2b15bc3d96d5418353eda708820421a890fb +size 4484367744 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q2_K.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q2_K.gguf new file mode 100644 index 0000000..529c08f --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507be9d36ccea6e9e8c115df76fde7b83bfe38a92fecf5f9fc41e1be2b57b6cd +size 3179136384 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf new file mode 100644 index 0000000..49f8b62 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594a99b9c6a2236020cc423769e404be6e65bdb05c745b06fa2d438ab90c9e11 +size 4321961344 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf new file mode 100644 index 0000000..484a77a --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc39205065abcde17256bbd229e419bae518376861a57f53b710bce9a5d3c96d +size 4018922880 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf new file mode 100644 index 0000000..fe5db2a --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9909f9b0d153bd96a31fc1dd0ef2ecf491e75a1f89a9462f67825aa417c6c5bc +size 3664504192 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf new file mode 100644 index 0000000..5609d66 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cb766136e0770aaea6c55080ba3c9066124ce222ce16bf313fa225e552debfe +size 4920739200 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf new file mode 100644 index 0000000..aa93f2f --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03e1927a94879d2333a3da923b763b85d969b8a5fab4a03a891c527d642a8a6 +size 4692673920 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf new file mode 100644 index 0000000..15c9e99 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d9b18bc9e31b81e436b540e6e479a76b9507797c5a7f3f8b2cb7c3aeb78fe7 +size 5732992384 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf new file mode 100644 index 0000000..d126687 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c84b44d40f356426da5803cd7f06f6705b04032c4325ca9938224919d39bc9 +size 5599298944 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q6_K.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q6_K.gguf new file mode 100644 index 0000000..674e0f5 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39639dc0f6ba790185a17af3432f12fd80901908d6d60203d0209654f7756eca +size 6596011392 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q8_0.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q8_0.gguf new file mode 100644 index 0000000..c12c8b5 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954d744f38bacce7957df17e74b672ef85d553fceea757a7450c8f16c01d8ca0 +size 8540775808 diff --git a/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.f16.gguf b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.f16.gguf new file mode 100644 index 0000000..6b15dc2 --- /dev/null +++ b/meta-llama-Llama-3.1-8B-Instruct-qlora-malaysian-16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e431b8b1a91bbd5e165cdbb733aa60da65fd88aea8d5aeed0eb2574091e7ff +size 16068896128