commit e44fb39a74b59c0e419a6fb9e11c3d7eabf03fbd Author: ModelHub XC Date: Mon Jun 22 23:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3SOME-8B-v2d-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1e5d52 --- /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 +Llama-3SOME-8B-v2d.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3SOME-8B-v2d.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3SOME-8B-v2d.IQ3_M.gguf b/Llama-3SOME-8B-v2d.IQ3_M.gguf new file mode 100644 index 0000000..e49095e --- /dev/null +++ b/Llama-3SOME-8B-v2d.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615428498e014391c30a8e28ffc759c6c9b9ba5016566326b92f520ee0c79aad +size 3784823552 diff --git a/Llama-3SOME-8B-v2d.IQ3_S.gguf b/Llama-3SOME-8B-v2d.IQ3_S.gguf new file mode 100644 index 0000000..d26527e --- /dev/null +++ b/Llama-3SOME-8B-v2d.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af912e99977ea0a99a3ce55a6703939a5bccae31ed2dc8c886a526554eab466 +size 3682325248 diff --git a/Llama-3SOME-8B-v2d.IQ3_XS.gguf b/Llama-3SOME-8B-v2d.IQ3_XS.gguf new file mode 100644 index 0000000..3fd6ddd --- /dev/null +++ b/Llama-3SOME-8B-v2d.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae1da0fa70845ab58c1293ec2e69d877c449e57ebe4feb124da6e9485d1629e +size 3518747392 diff --git a/Llama-3SOME-8B-v2d.IQ4_XS.gguf b/Llama-3SOME-8B-v2d.IQ4_XS.gguf new file mode 100644 index 0000000..b8504cb --- /dev/null +++ b/Llama-3SOME-8B-v2d.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135df184d22472a9adeec8005e4d6c19022221486bd6c8e4599c255f99ac18ed +size 4484363008 diff --git a/Llama-3SOME-8B-v2d.Q2_K.gguf b/Llama-3SOME-8B-v2d.Q2_K.gguf new file mode 100644 index 0000000..6f4061c --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4875de01075575c1973655385a0bc3aaab6741b0ebfeb0943c607b5134ae36e7 +size 3179131648 diff --git a/Llama-3SOME-8B-v2d.Q3_K_L.gguf b/Llama-3SOME-8B-v2d.Q3_K_L.gguf new file mode 100644 index 0000000..233f93d --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d4a66d0661ea329b1e76c5b5491d5b66eaffd3b4c6820918ea482755b1689e +size 4321956608 diff --git a/Llama-3SOME-8B-v2d.Q3_K_M.gguf b/Llama-3SOME-8B-v2d.Q3_K_M.gguf new file mode 100644 index 0000000..7de7527 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af52c4e73589e33b69ee199c168ab15c3e0caeccefbe5a260a30b2e7cefa98c4 +size 4018918144 diff --git a/Llama-3SOME-8B-v2d.Q3_K_S.gguf b/Llama-3SOME-8B-v2d.Q3_K_S.gguf new file mode 100644 index 0000000..e32b4e4 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9777d9deba552127cc9e21ab1d51ae6381760fc58fcb16f6e263c7212161ed +size 3664499456 diff --git a/Llama-3SOME-8B-v2d.Q4_K_M.gguf b/Llama-3SOME-8B-v2d.Q4_K_M.gguf new file mode 100644 index 0000000..58aa90f --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2e13628a14312153c9891616261f2e179a983341d1e4ffe54d2d02ea76c2bd +size 4920734464 diff --git a/Llama-3SOME-8B-v2d.Q4_K_S.gguf b/Llama-3SOME-8B-v2d.Q4_K_S.gguf new file mode 100644 index 0000000..c58bd1a --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a865f8cef5e64a28da06db6816873ebc520229ec03499d5423b37aa14024b120 +size 4692669184 diff --git a/Llama-3SOME-8B-v2d.Q5_K_M.gguf b/Llama-3SOME-8B-v2d.Q5_K_M.gguf new file mode 100644 index 0000000..246d817 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748e68a969ed823741ecbc320c477f2def309392022570887696a55df106c88d +size 5732987648 diff --git a/Llama-3SOME-8B-v2d.Q5_K_S.gguf b/Llama-3SOME-8B-v2d.Q5_K_S.gguf new file mode 100644 index 0000000..8492f01 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b149c4fe726c804137d93377ff081ff008e25f42318421f5aa43cc6fadc152d +size 5599294208 diff --git a/Llama-3SOME-8B-v2d.Q6_K.gguf b/Llama-3SOME-8B-v2d.Q6_K.gguf new file mode 100644 index 0000000..1bf8b38 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c494b7e847889a26787c3518496967ea9095ba603e24b3210f075c55a9e09d24 +size 6596006656 diff --git a/Llama-3SOME-8B-v2d.Q8_0.gguf b/Llama-3SOME-8B-v2d.Q8_0.gguf new file mode 100644 index 0000000..26a0386 --- /dev/null +++ b/Llama-3SOME-8B-v2d.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79bb3354251d121a8e9d66fa4365ef17439c8b0e4345c9185dfb5fdb33b905f1 +size 8540771072 diff --git a/Llama-3SOME-8B-v2d.f16.gguf b/Llama-3SOME-8B-v2d.f16.gguf new file mode 100644 index 0000000..530bcf3 --- /dev/null +++ b/Llama-3SOME-8B-v2d.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e968c740ae4094055fde5e6e889000175183e348476885d2262f20a1d29aa5 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3512f4 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: BeaverAI/Llama-3SOME-8B-v2d +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BeaverAI/Llama-3SOME-8B-v2d + + +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/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2d-GGUF/resolve/main/Llama-3SOME-8B-v2d.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. + +