commit 8520ab79bf23e68b4a9bf9930e1ad7d11b869633 Author: ModelHub XC Date: Fri Jun 5 23:54:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d364d73 --- /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-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.f16.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-Llama-3.2-1B-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..b597f77 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mesolitica/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mesolitica/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-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-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf) | IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_S.gguf) | IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_M.gguf) | IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k-GGUF/resolve/main/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.f16.gguf) | f16 | 2.6 | 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-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_M.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_M.gguf new file mode 100644 index 0000000..6f24001 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34d582796e49465071845c90db5f34bf9989510dd0436bad7dcea392b0f8629 +size 657289344 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_S.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_S.gguf new file mode 100644 index 0000000..33a6ac7 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad13585abd095ae395e7c1aec1c2d81af102d93b5971ab68caffd1c77636d7d +size 643920000 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf new file mode 100644 index 0000000..195ea45 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4b3b0054abd4148d0f12d5bb9a2ec4951f6f2cb47961f04e1b2c904344b7dd +size 621113472 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf new file mode 100644 index 0000000..1f09a75 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c02fe2d52b18e12dab65db893a140389bf5996aeefb7a2a37e0edab8cc78956 +size 748384384 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q2_K.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q2_K.gguf new file mode 100644 index 0000000..5b2520e --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24504e0df831ff87149f3945cec386486e2ec163ce8246878250cd8949f24745 +size 580874368 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf new file mode 100644 index 0000000..8df0701 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9306e00e34a5133927572d209470002780e9c37869737ecaffc66c40c775480c +size 732524672 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf new file mode 100644 index 0000000..dd0e210 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9052409211d68230c20485a30640f9e6bed5112efd41c012330f7d7e86096f8f +size 690843776 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf new file mode 100644 index 0000000..d0d5cbc --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:866ba042c1fc5ad80286cad7cb735f7f186377496cf8a69bdafc7e338e1cd7c9 +size 641691776 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf new file mode 100644 index 0000000..4a97685 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ac2864010874c73321669cf3e9351f8c3b5cb104d252d1fe246bf985593b56 +size 807694464 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf new file mode 100644 index 0000000..a24b9ec --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280dce95489d6bda803e3219ffbc8729e8a33e4506910ca32c9be0db344f7648 +size 775647360 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf new file mode 100644 index 0000000..5e8767a --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc076018da085d5eb1f5f0bb7dc2ed2171a29767a177472407a07e6fc58d478a +size 911503488 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf new file mode 100644 index 0000000..22c2d3d --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e6505c66df4f72fce173d13942ca309be17af8e03cabc976ff0708adb2f64f +size 892563584 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q6_K.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q6_K.gguf new file mode 100644 index 0000000..3def534 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:541c672cbca77f395fe176a9bcb86bcf751c4c480aa46bf9c3ba1b7a178159df +size 1021800576 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q8_0.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q8_0.gguf new file mode 100644 index 0000000..19fb7d7 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9372c223b852718ec38576f5d131ba515d4c6ef3663658444b4b67f9d09860e6 +size 1321083008 diff --git a/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.f16.gguf b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.f16.gguf new file mode 100644 index 0000000..b9a6891 --- /dev/null +++ b/meta-llama-Llama-3.2-1B-Instruct-qlora-malaysian-16k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3bcca0650ca1dd8d92fa0c947b21a184460fdb6f305eab9d94d69406f19148 +size 2479595648