commit 498795da99a2d721d14b5ab6c34a2d717f02a4f9 Author: ModelHub XC Date: Fri Jul 10 09:08:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA3-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7fdeebf --- /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 +LLaMA3-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA3-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA3-SFT.IQ4_XS.gguf b/LLaMA3-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..a266c32 --- /dev/null +++ b/LLaMA3-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40bf7fcc6911147a60f4c8ede1d7566f838b0f8f3e8c31a926805ec0641ef901 +size 4484363072 diff --git a/LLaMA3-SFT.Q2_K.gguf b/LLaMA3-SFT.Q2_K.gguf new file mode 100644 index 0000000..94d65c7 --- /dev/null +++ b/LLaMA3-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e9ee3a8468bbfb897dc386a9daba4c9540167505bbb6d5bd5028fac47ad62f +size 3179131712 diff --git a/LLaMA3-SFT.Q3_K_L.gguf b/LLaMA3-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..44b7f33 --- /dev/null +++ b/LLaMA3-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9f4b2a20cf758e445ecd0ef86ecfd12827b6873485b4217400d4788b7b527f +size 4321956672 diff --git a/LLaMA3-SFT.Q3_K_M.gguf b/LLaMA3-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..eb31104 --- /dev/null +++ b/LLaMA3-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1670dea4a04e025931c3e2a4d00ea82151359ad0ca32b82a6ed2679395965c41 +size 4018918208 diff --git a/LLaMA3-SFT.Q3_K_S.gguf b/LLaMA3-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..8653a7b --- /dev/null +++ b/LLaMA3-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ab246dc7deba6e907036233f20b81d8619261dcc4c75594cff5b960d06df04 +size 3664499520 diff --git a/LLaMA3-SFT.Q4_K_M.gguf b/LLaMA3-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..a71b236 --- /dev/null +++ b/LLaMA3-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dcd2651254b043b5ecb8dfb2468c0dbb365eacc0f3daf95b043eda2183228fc +size 4920734528 diff --git a/LLaMA3-SFT.Q4_K_S.gguf b/LLaMA3-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..b0d6020 --- /dev/null +++ b/LLaMA3-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed2698c9186a30e172721a903ed50492299f1c6930f182cff788d47138efa8c +size 4692669248 diff --git a/LLaMA3-SFT.Q5_K_M.gguf b/LLaMA3-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..2167c8f --- /dev/null +++ b/LLaMA3-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c84c2cf8bbe94eeea066da11243e2367254fe568573a35c70409fd193606270b +size 5732987712 diff --git a/LLaMA3-SFT.Q5_K_S.gguf b/LLaMA3-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..ed7bf97 --- /dev/null +++ b/LLaMA3-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9530c82206c6e01f843bccd9ada0679060e07dfe6f5724a1f285343a07fbe6 +size 5599294272 diff --git a/LLaMA3-SFT.Q6_K.gguf b/LLaMA3-SFT.Q6_K.gguf new file mode 100644 index 0000000..86e63c0 --- /dev/null +++ b/LLaMA3-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e72745407b30a9e88b511f9c8e6274aebc3f856d5648943c8daaa19e53bbbbe +size 6596006720 diff --git a/LLaMA3-SFT.Q8_0.gguf b/LLaMA3-SFT.Q8_0.gguf new file mode 100644 index 0000000..9066b40 --- /dev/null +++ b/LLaMA3-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5831a4a128e0994d269e94c5272792f35a90366a12b944109f25bc5e710e5e5 +size 8540771136 diff --git a/LLaMA3-SFT.f16.gguf b/LLaMA3-SFT.f16.gguf new file mode 100644 index 0000000..7a85eef --- /dev/null +++ b/LLaMA3-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef85fe4477e5bd859e0631d281f7b53500c49d95d84abb86cab0e468f978025 +size 16068891456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b921575 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: RLHFlow/LLaMA3-SFT +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/RLHFlow/LLaMA3-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMA3-SFT-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/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-SFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA3-SFT-GGUF/resolve/main/LLaMA3-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. + +