commit 8b0b149dee9adbc13e7e18ca5df599b9377a1bcf Author: ModelHub XC Date: Thu Oct 1 14:15:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TwinLlama-3.1-8B-4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77937f4 --- /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-4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.f16.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TwinLlama-3.1-8B-4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2c12e62 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: mlabonne/TwinLlama-3.1-8B-4 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/TwinLlama-3.1-8B-4 + + +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-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TwinLlama-3.1-8B-4-GGUF/resolve/main/TwinLlama-3.1-8B-4.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-4.IQ3_M.gguf b/TwinLlama-3.1-8B-4.IQ3_M.gguf new file mode 100644 index 0000000..1833c68 --- /dev/null +++ b/TwinLlama-3.1-8B-4.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f970a94f9037d1178520f2d1083b9b791d285d3a8abf08ee9f7c5743a553dea8 +size 3784834176 diff --git a/TwinLlama-3.1-8B-4.IQ3_S.gguf b/TwinLlama-3.1-8B-4.IQ3_S.gguf new file mode 100644 index 0000000..c874944 --- /dev/null +++ b/TwinLlama-3.1-8B-4.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8238c584f02ad1fb7734d5cc9e01a5d606ef9133579ca193c599200ca6ee371a +size 3682335872 diff --git a/TwinLlama-3.1-8B-4.IQ3_XS.gguf b/TwinLlama-3.1-8B-4.IQ3_XS.gguf new file mode 100644 index 0000000..d578892 --- /dev/null +++ b/TwinLlama-3.1-8B-4.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d891dea53058d6f9fc4f47b7b9d6b8e3771a11d9e768d6a208d5675fba2a13bd +size 3518758016 diff --git a/TwinLlama-3.1-8B-4.IQ4_XS.gguf b/TwinLlama-3.1-8B-4.IQ4_XS.gguf new file mode 100644 index 0000000..7efe701 --- /dev/null +++ b/TwinLlama-3.1-8B-4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e416acdedafb11d892328c2d7bb0201a3c0c418e13b1c36590ae1c452ed416c0 +size 4484374464 diff --git a/TwinLlama-3.1-8B-4.Q2_K.gguf b/TwinLlama-3.1-8B-4.Q2_K.gguf new file mode 100644 index 0000000..3f1e3d4 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68728d50ed1c62fe01df04813690a9362cdec541d62f3bf13b1525dfcca1897 +size 3179141440 diff --git a/TwinLlama-3.1-8B-4.Q3_K_L.gguf b/TwinLlama-3.1-8B-4.Q3_K_L.gguf new file mode 100644 index 0000000..e91d6b5 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2dca4a37dc690b3ce652a65e95d74b14d9d2437ca2a1fc21274fdd06654775f +size 4321967232 diff --git a/TwinLlama-3.1-8B-4.Q3_K_M.gguf b/TwinLlama-3.1-8B-4.Q3_K_M.gguf new file mode 100644 index 0000000..611e48b --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55efc1d00c6d4798596c8a283ac41c77d9d4a451c83187203ba1941bf9aee1f +size 4018928768 diff --git a/TwinLlama-3.1-8B-4.Q3_K_S.gguf b/TwinLlama-3.1-8B-4.Q3_K_S.gguf new file mode 100644 index 0000000..b9a1037 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c55f27bed597d379048556f4fe590ef1b857b34f2760673a68c1424a20c2dbea +size 3664510080 diff --git a/TwinLlama-3.1-8B-4.Q4_K_M.gguf b/TwinLlama-3.1-8B-4.Q4_K_M.gguf new file mode 100644 index 0000000..299f9a9 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9a0eda074a732df34f4fe2e43943eb86806ad4316b0f4e82d431e7afdd3172 +size 4920746176 diff --git a/TwinLlama-3.1-8B-4.Q4_K_S.gguf b/TwinLlama-3.1-8B-4.Q4_K_S.gguf new file mode 100644 index 0000000..dd05cde --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223bafe94b33eb2297093d4592bdf7313f1d31790caf542be7a781c8cf24f1bc +size 4692680896 diff --git a/TwinLlama-3.1-8B-4.Q5_K_M.gguf b/TwinLlama-3.1-8B-4.Q5_K_M.gguf new file mode 100644 index 0000000..6f5b1a9 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff590b79a9233084fbca85be06432d4c2168a81546a1bee6a4099c35f228af7 +size 5733000384 diff --git a/TwinLlama-3.1-8B-4.Q5_K_S.gguf b/TwinLlama-3.1-8B-4.Q5_K_S.gguf new file mode 100644 index 0000000..d9ad64b --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38912eaf4f2ab012eab792bb3d835e71112139dcc9969a0615b5cd4aec39065 +size 5599306944 diff --git a/TwinLlama-3.1-8B-4.Q6_K.gguf b/TwinLlama-3.1-8B-4.Q6_K.gguf new file mode 100644 index 0000000..2bf56ce --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e92c67ab716bb284881f94fd3cc0b0f9a66ea3feafaffe06d8f06201589851 +size 6596020480 diff --git a/TwinLlama-3.1-8B-4.Q8_0.gguf b/TwinLlama-3.1-8B-4.Q8_0.gguf new file mode 100644 index 0000000..e97cf82 --- /dev/null +++ b/TwinLlama-3.1-8B-4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7493b1be5b11127f1ad8e5f61b410bccc87d16c89a62809b10a38d7a14808bed +size 8540788864 diff --git a/TwinLlama-3.1-8B-4.f16.gguf b/TwinLlama-3.1-8B-4.f16.gguf new file mode 100644 index 0000000..392a28b --- /dev/null +++ b/TwinLlama-3.1-8B-4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c69970861fb7a6e21c9c51aaa19c53bbbb9ee453254baa79955cecafd9c551 +size 16068924544