commit bf3407e2b05a4e7b91e02831ac15bd0376b3eeec Author: ModelHub XC Date: Tue Sep 8 00:38:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Smaug-8B-OAS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6d448a4 --- /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-3-Smaug-8B-OAS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Smaug-8B-OAS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Smaug-8B-OAS.IQ3_M.gguf b/Llama-3-Smaug-8B-OAS.IQ3_M.gguf new file mode 100644 index 0000000..2cbf535 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6365b9a64e3f16469535a51ca393b92ff239516a2c862766f6bcc5c810d806 +size 3784823584 diff --git a/Llama-3-Smaug-8B-OAS.IQ3_S.gguf b/Llama-3-Smaug-8B-OAS.IQ3_S.gguf new file mode 100644 index 0000000..93b93be --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85af52001348b95ef80fb97b43a6ebb3c87ffe4d00f55294bc384b8b24f68555 +size 3682325280 diff --git a/Llama-3-Smaug-8B-OAS.IQ3_XS.gguf b/Llama-3-Smaug-8B-OAS.IQ3_XS.gguf new file mode 100644 index 0000000..8cfff3e --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a332510d04e01548feaf9a3db484aaf9176224bbf072d121f5715cd4e59c919 +size 3518747424 diff --git a/Llama-3-Smaug-8B-OAS.IQ4_XS.gguf b/Llama-3-Smaug-8B-OAS.IQ4_XS.gguf new file mode 100644 index 0000000..973a6da --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40113acf3c205d35e3c683c0d1a370c1820c9688de7fae27ea40ccd8ececfa39 +size 4484363040 diff --git a/Llama-3-Smaug-8B-OAS.Q2_K.gguf b/Llama-3-Smaug-8B-OAS.Q2_K.gguf new file mode 100644 index 0000000..2a4ef0c --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083aa3c0a4c3f866112a3ec9b825d25effef455ee2e1e338d8f1d0d385a6989f +size 3179131680 diff --git a/Llama-3-Smaug-8B-OAS.Q3_K_L.gguf b/Llama-3-Smaug-8B-OAS.Q3_K_L.gguf new file mode 100644 index 0000000..12e80a3 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bb23ae5736b30dac40c245ae199c2789f0d1d868528c969c191f0ecf97f8b7 +size 4321956640 diff --git a/Llama-3-Smaug-8B-OAS.Q3_K_M.gguf b/Llama-3-Smaug-8B-OAS.Q3_K_M.gguf new file mode 100644 index 0000000..9ca50be --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a770e60bf81cd8e358c16dfcb56e166d572e24927f311544219c100cba85352b +size 4018918176 diff --git a/Llama-3-Smaug-8B-OAS.Q3_K_S.gguf b/Llama-3-Smaug-8B-OAS.Q3_K_S.gguf new file mode 100644 index 0000000..cd43b8f --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7432a084eff12f2637c37f5482e64699ab03877c7deec878d0e7d06202049d93 +size 3664499488 diff --git a/Llama-3-Smaug-8B-OAS.Q4_K_M.gguf b/Llama-3-Smaug-8B-OAS.Q4_K_M.gguf new file mode 100644 index 0000000..4ae7cc8 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71534a41fef7593640f929568690e353bd12040096207ff435a0e8a14cad46e +size 4920734496 diff --git a/Llama-3-Smaug-8B-OAS.Q4_K_S.gguf b/Llama-3-Smaug-8B-OAS.Q4_K_S.gguf new file mode 100644 index 0000000..d04a0f6 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d7cc8be9f31cd2981a9c9243d376322f5596c68020876c32bb9463b068f63c +size 4692669216 diff --git a/Llama-3-Smaug-8B-OAS.Q5_K_M.gguf b/Llama-3-Smaug-8B-OAS.Q5_K_M.gguf new file mode 100644 index 0000000..9f28de0 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12b900ebba77d711694f6523d5576949bf351d20f48427d8d94af0e51bfd87c1 +size 5732987680 diff --git a/Llama-3-Smaug-8B-OAS.Q5_K_S.gguf b/Llama-3-Smaug-8B-OAS.Q5_K_S.gguf new file mode 100644 index 0000000..a597f26 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30117bc658dc7bdaa7861ebb358aa434f355d200d37ad9afe1204989c1364775 +size 5599294240 diff --git a/Llama-3-Smaug-8B-OAS.Q6_K.gguf b/Llama-3-Smaug-8B-OAS.Q6_K.gguf new file mode 100644 index 0000000..4b80df4 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c62e5ac51f99f7d3a6180a000ef19fbd77c8ca85c93eef19e2e393a3461caac +size 6596006688 diff --git a/Llama-3-Smaug-8B-OAS.Q8_0.gguf b/Llama-3-Smaug-8B-OAS.Q8_0.gguf new file mode 100644 index 0000000..c0d1037 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20dd17134d126b21253edd16566e27b480cd922a7726a9b3bd6cf2247ef10b69 +size 8540771104 diff --git a/Llama-3-Smaug-8B-OAS.f16.gguf b/Llama-3-Smaug-8B-OAS.f16.gguf new file mode 100644 index 0000000..5aa6896 --- /dev/null +++ b/Llama-3-Smaug-8B-OAS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb62db58d9646d11a254dc194729acaf2986d91ce6d8d43cf8470d7338739f25 +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..394afb5 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: AliceThirty/Llama-3-Smaug-8B-OAS +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AliceThirty/Llama-3-Smaug-8B-OAS + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-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/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Smaug-8B-OAS-GGUF/resolve/main/Llama-3-Smaug-8B-OAS.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. + +