commit 429104dfc018d834774150ec00ecc804f3de59d4 Author: ModelHub XC Date: Sat Sep 19 10:48:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..13045d7 --- /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-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.f16.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-3B-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..9b85f4d --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mesolitica/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mesolitica/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-i1-GGUF +## 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-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.f16.gguf) | f16 | 6.5 | 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-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_M.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_M.gguf new file mode 100644 index 0000000..f2abbf4 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be07212bf2fe8ca379fdedba5c54f34eaa13f65e8124d5dd972c51653c59409b +size 1599668800 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_S.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_S.gguf new file mode 100644 index 0000000..44bbaa2 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365fcd491bf2504e3f0a52f32f0ba7d8db1058e652cc8740465c41eed5aaee7e +size 1542849088 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf new file mode 100644 index 0000000..8d2ff2d --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc44f1e8addd64f4023716021fe7cd8321f7cf1bc5bd0b6194c8cd3cb39906e +size 1476788800 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf new file mode 100644 index 0000000..ae563d1 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa23008bb2091ea019c085268f7518ee0f3bbb3b3a102bc2400d697d2739f34 +size 1840906816 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q2_K.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q2_K.gguf new file mode 100644 index 0000000..4184ba0 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6ba5e9bc78da3626464756976d086cf4cc87e1497d99c67e983f624b892f22 +size 1363935808 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf new file mode 100644 index 0000000..802e511 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687ea425f1e95b5c9a0cb4c1c922cd9a3692d241735bf7eca4900ac51aa19d2d +size 1815347776 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf new file mode 100644 index 0000000..cf3fe5b --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52999ecde36fce2321edf935d19a8975f5b46ce4b463c4d1e0890d1517d0fecb +size 1687159360 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf new file mode 100644 index 0000000..579d79d --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecc36051c84801d1b360ba0300161f970aba75fe4924af19ba4254945891ba5d +size 1542849088 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf new file mode 100644 index 0000000..5aa28b0 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a615a00a66dcb4a741d71e13740d1bb87dc924e84b5ab2dca0760c7547bb60da +size 2019377728 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf new file mode 100644 index 0000000..7199244 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbd0b3cc24b33b24c3313d9ad064cef6c4d256ec9dd03d109a7bd4ddf84602d +size 1928200768 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf new file mode 100644 index 0000000..9418c7d --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46375d0391832a07dd2b1962450b6caaaf16026f5160613c7d9856e71fa1768 +size 2322154048 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf new file mode 100644 index 0000000..85c8b5c --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0bbf7e86e9e4012ed3b0f3a4678e14cbd6a7cace3847988d7f6fa13f9cadaa1 +size 2269512256 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q6_K.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q6_K.gguf new file mode 100644 index 0000000..284c77d --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21eb2394a860410ada0afa45e7c517d21386f6eb8afd5975897efc9c2db1b608 +size 2643853888 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q8_0.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q8_0.gguf new file mode 100644 index 0000000..4baf0e3 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4147e9e502d3f2fd9cea58d1967a7a882becc836352dcd1a3bd5aded4c3cdb54 +size 3421899328 diff --git a/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.f16.gguf b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.f16.gguf new file mode 100644 index 0000000..38902c5 --- /dev/null +++ b/meta-llama-Llama-3.2-3B-Instruct-qlora-malaysian-16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60e719f3f0bfcd8559f53a843a92e2c95727d8fdcb9ed2c081038124174d32f +size 6433688128