commit accfd976eefa31db4c628eae68ed8ab3f135c0a1 Author: ModelHub XC Date: Sat May 16 02:53:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nb-llama-3.1-8B-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8d124e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +nb-llama-3.1-8B-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nb-llama-3.1-8B-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6501d83 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: NbAiLab/nb-llama-3.1-8B-sft +language: +- no +- nb +- nn +- en +- sv +- da +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- norwegian +- bokmål +- nynorsk +- swedish +- danish +- multilingual +- text-generation +--- +## About + + + + + + +static quants of https://huggingface.co/NbAiLab/nb-llama-3.1-8B-sft + + +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/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nb-llama-3.1-8B-sft-GGUF/resolve/main/nb-llama-3.1-8B-sft.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/nb-llama-3.1-8B-sft.IQ4_XS.gguf b/nb-llama-3.1-8B-sft.IQ4_XS.gguf new file mode 100644 index 0000000..5502add --- /dev/null +++ b/nb-llama-3.1-8B-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608e5747d7a9a03d798c82445ba7b04afb9cee0a23a9f0cd06a3ab23631398f3 +size 4484368064 diff --git a/nb-llama-3.1-8B-sft.Q2_K.gguf b/nb-llama-3.1-8B-sft.Q2_K.gguf new file mode 100644 index 0000000..be2d182 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6812325160f72abe204bf99e27acad359c283777492c2d4c6f1cbee048172d +size 3179136704 diff --git a/nb-llama-3.1-8B-sft.Q3_K_L.gguf b/nb-llama-3.1-8B-sft.Q3_K_L.gguf new file mode 100644 index 0000000..2129b75 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb3c6614d5fd75ffa7526a4d25f3221c12b57666d5959b17d8ccece26b5aca2 +size 4321961664 diff --git a/nb-llama-3.1-8B-sft.Q3_K_M.gguf b/nb-llama-3.1-8B-sft.Q3_K_M.gguf new file mode 100644 index 0000000..0bb6033 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e105f19c74a544dd81b37434b6a44c6d7e66f8ffc3f1270b57be537b0d2e3388 +size 4018923200 diff --git a/nb-llama-3.1-8B-sft.Q3_K_S.gguf b/nb-llama-3.1-8B-sft.Q3_K_S.gguf new file mode 100644 index 0000000..6b30c65 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7182a86448412a1afdb974403e178af79558987cd5167b2a953b0247aa8ec12b +size 3664504512 diff --git a/nb-llama-3.1-8B-sft.Q4_K_M.gguf b/nb-llama-3.1-8B-sft.Q4_K_M.gguf new file mode 100644 index 0000000..2991720 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9fab26ba88ec3e4a39eed746ba95d294ae64c1f30e8106b926d432009d0cac +size 4920739520 diff --git a/nb-llama-3.1-8B-sft.Q4_K_S.gguf b/nb-llama-3.1-8B-sft.Q4_K_S.gguf new file mode 100644 index 0000000..0347f2c --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51dfd312d493ea6a66757912dbb48083e51dd050da2b9aab80dd082b9a7c2be +size 4692674240 diff --git a/nb-llama-3.1-8B-sft.Q5_K_M.gguf b/nb-llama-3.1-8B-sft.Q5_K_M.gguf new file mode 100644 index 0000000..6185faa --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590f6b4de7e8d1f87f0ad05d6708d9f772b1e25beee5eaa9a9e482a0a6a1da7a +size 5732992704 diff --git a/nb-llama-3.1-8B-sft.Q5_K_S.gguf b/nb-llama-3.1-8B-sft.Q5_K_S.gguf new file mode 100644 index 0000000..bc361fe --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:874c35eb68f83ace2f66ecce2c39bff1606f4e845943d70f931e09d3d488f6b1 +size 5599299264 diff --git a/nb-llama-3.1-8B-sft.Q6_K.gguf b/nb-llama-3.1-8B-sft.Q6_K.gguf new file mode 100644 index 0000000..28ed691 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04532a2e06e138469fefce38f91c5bf076129050e4e39236023cb5904e6c339 +size 6596011712 diff --git a/nb-llama-3.1-8B-sft.Q8_0.gguf b/nb-llama-3.1-8B-sft.Q8_0.gguf new file mode 100644 index 0000000..b245353 --- /dev/null +++ b/nb-llama-3.1-8B-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21dab358ab697bf9e9ff430a33655a2d5788bd5183174db96b6691f4a47135e +size 8540776128 diff --git a/nb-llama-3.1-8B-sft.f16.gguf b/nb-llama-3.1-8B-sft.f16.gguf new file mode 100644 index 0000000..6497917 --- /dev/null +++ b/nb-llama-3.1-8B-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e777454fc707fcd8641f340318d1a9492831f842737efe8310497959384f4579 +size 16068896448