commit 140a855d3ebefb9ba166cc602cba9e3c3e044f18 Author: ModelHub XC Date: Sat Sep 19 10:49:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.1-8B-12-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32df935 --- /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 +TwinLlama-3.1-8B-12.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.f16.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-12.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f0d752 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mlabonne/TwinLlama-3.1-8B-12 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/TwinLlama-3.1-8B-12 + + +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/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-12-GGUF/resolve/main/TwinLlama-3.1-8B-12.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/TwinLlama-3.1-8B-12.IQ3_M.gguf b/TwinLlama-3.1-8B-12.IQ3_M.gguf new file mode 100644 index 0000000..2f6d797 --- /dev/null +++ b/TwinLlama-3.1-8B-12.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f298b186d7450501c844ae237cd4921c897b55a7d7f01ac102ad812b76c9860 +size 3784834144 diff --git a/TwinLlama-3.1-8B-12.IQ3_S.gguf b/TwinLlama-3.1-8B-12.IQ3_S.gguf new file mode 100644 index 0000000..214c0a4 --- /dev/null +++ b/TwinLlama-3.1-8B-12.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d30e64849dc3eaa35c5e9bf8f74b2a296523db2d73b6b207310249d7a7ac379 +size 3682335840 diff --git a/TwinLlama-3.1-8B-12.IQ3_XS.gguf b/TwinLlama-3.1-8B-12.IQ3_XS.gguf new file mode 100644 index 0000000..ec94aca --- /dev/null +++ b/TwinLlama-3.1-8B-12.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f22d48e95a7e6e945705e59a22ca046e28cdf9ba2593d05c4f103da2b3d647 +size 3518757984 diff --git a/TwinLlama-3.1-8B-12.IQ4_XS.gguf b/TwinLlama-3.1-8B-12.IQ4_XS.gguf new file mode 100644 index 0000000..007667c --- /dev/null +++ b/TwinLlama-3.1-8B-12.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86aed8f64a1d095c117226e665594fd43ca89308eeca88b46710c3f60855f53a +size 4484374432 diff --git a/TwinLlama-3.1-8B-12.Q2_K.gguf b/TwinLlama-3.1-8B-12.Q2_K.gguf new file mode 100644 index 0000000..1d230ca --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7fe817cbd6fe0444827d37641385898adc651107082edb8bd1b5a4b14fdb7b9 +size 3179141408 diff --git a/TwinLlama-3.1-8B-12.Q3_K_L.gguf b/TwinLlama-3.1-8B-12.Q3_K_L.gguf new file mode 100644 index 0000000..a869f59 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd50ae7e46dd7b54b7c4d428e5d4dc6b64b45784720c9397a189e83258ad7a8 +size 4321967200 diff --git a/TwinLlama-3.1-8B-12.Q3_K_M.gguf b/TwinLlama-3.1-8B-12.Q3_K_M.gguf new file mode 100644 index 0000000..64b6d36 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3211d74943f1c2e63ff9fb612cf184b0b2df8500bff6f26b62d2bd0f3260e3f3 +size 4018928736 diff --git a/TwinLlama-3.1-8B-12.Q3_K_S.gguf b/TwinLlama-3.1-8B-12.Q3_K_S.gguf new file mode 100644 index 0000000..6b9eebd --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee347b04e0ce310d640b0373eaa7bb9a5a8f9f277b4b7cbd435968c210356cb +size 3664510048 diff --git a/TwinLlama-3.1-8B-12.Q4_K_M.gguf b/TwinLlama-3.1-8B-12.Q4_K_M.gguf new file mode 100644 index 0000000..17a02e3 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3321784065c6f56eab5302744056ba9fdb3c28e6ef8f01f83a425fcf96c324be +size 4920746144 diff --git a/TwinLlama-3.1-8B-12.Q4_K_S.gguf b/TwinLlama-3.1-8B-12.Q4_K_S.gguf new file mode 100644 index 0000000..47684e8 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37135a97bb50c84c5edf8c1660f162838489b095a334add1e8917f11041acaa8 +size 4692680864 diff --git a/TwinLlama-3.1-8B-12.Q5_K_M.gguf b/TwinLlama-3.1-8B-12.Q5_K_M.gguf new file mode 100644 index 0000000..b39eaf4 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f31da0245c20f36efcb6f6dfe7e715c10e24f5dae1835790a828f44737e17a +size 5733000352 diff --git a/TwinLlama-3.1-8B-12.Q5_K_S.gguf b/TwinLlama-3.1-8B-12.Q5_K_S.gguf new file mode 100644 index 0000000..26b839b --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53be962f8073569a53f7e1a5ffc7200305b663a461be12009e2e1e66348d746 +size 5599306912 diff --git a/TwinLlama-3.1-8B-12.Q6_K.gguf b/TwinLlama-3.1-8B-12.Q6_K.gguf new file mode 100644 index 0000000..00eefe6 --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca114ca9490bbf029da7941bf105dc68a850f06a42acb294d33fe67df316958c +size 6596020448 diff --git a/TwinLlama-3.1-8B-12.Q8_0.gguf b/TwinLlama-3.1-8B-12.Q8_0.gguf new file mode 100644 index 0000000..ed93d0a --- /dev/null +++ b/TwinLlama-3.1-8B-12.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9754ccfd3b66c6bb18903e8d1ebb7c4094d386aa55dff46f60a1fa689f929e6c +size 8540788832 diff --git a/TwinLlama-3.1-8B-12.f16.gguf b/TwinLlama-3.1-8B-12.f16.gguf new file mode 100644 index 0000000..9436bfa --- /dev/null +++ b/TwinLlama-3.1-8B-12.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29bcf549a83a9f52ec923b37e085a058a28de11ed2e8a9146a5db085d88ed458 +size 16068924512