commit 8a24bf2d7682eda1de6f8e93f76b67b46e7566b2 Author: ModelHub XC Date: Tue Sep 29 23:33:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Numina850K-ORM-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..526ab44 --- /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-Numina850K-ORM.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Numina850K-ORM.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Numina850K-ORM.IQ4_XS.gguf b/Llama3-Numina850K-ORM.IQ4_XS.gguf new file mode 100644 index 0000000..2e88a68 --- /dev/null +++ b/Llama3-Numina850K-ORM.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b57b52b5bd42ffa1d8d2cf4d3ccb5cf6be514303ddfb4ce606e07517dc8c98f +size 4484367744 diff --git a/Llama3-Numina850K-ORM.Q2_K.gguf b/Llama3-Numina850K-ORM.Q2_K.gguf new file mode 100644 index 0000000..b8dda47 --- /dev/null +++ b/Llama3-Numina850K-ORM.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407fdb5a7b541441d6d4d849313f1ec45630d1f7f56f5c391c9ad0d689a1c2bf +size 3179136384 diff --git a/Llama3-Numina850K-ORM.Q3_K_L.gguf b/Llama3-Numina850K-ORM.Q3_K_L.gguf new file mode 100644 index 0000000..a9a5bbb --- /dev/null +++ b/Llama3-Numina850K-ORM.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f6714968196fe3d43c8721f6b7c99ab4f6ad2248635c6d46e02666f2f22140 +size 4321961344 diff --git a/Llama3-Numina850K-ORM.Q3_K_M.gguf b/Llama3-Numina850K-ORM.Q3_K_M.gguf new file mode 100644 index 0000000..7498759 --- /dev/null +++ b/Llama3-Numina850K-ORM.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04d9734a5cee055638072fd55773039949916b68ac681e88b75efcb0e952187 +size 4018922880 diff --git a/Llama3-Numina850K-ORM.Q3_K_S.gguf b/Llama3-Numina850K-ORM.Q3_K_S.gguf new file mode 100644 index 0000000..050d021 --- /dev/null +++ b/Llama3-Numina850K-ORM.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73624c73eb8a9c3245ab88122d9edb815f5894f4580e50334d8f38997fa8143d +size 3664504192 diff --git a/Llama3-Numina850K-ORM.Q4_K_M.gguf b/Llama3-Numina850K-ORM.Q4_K_M.gguf new file mode 100644 index 0000000..3899e07 --- /dev/null +++ b/Llama3-Numina850K-ORM.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3631368813db85367b6083eb5379241e8289d27e4b3cb01027a826f17f424f55 +size 4920739200 diff --git a/Llama3-Numina850K-ORM.Q4_K_S.gguf b/Llama3-Numina850K-ORM.Q4_K_S.gguf new file mode 100644 index 0000000..9b04bcb --- /dev/null +++ b/Llama3-Numina850K-ORM.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f41ca7ce6b82c9eb2cc0d3be7a053c298a1a3e18cc9b11aef0752137cad10e +size 4692673920 diff --git a/Llama3-Numina850K-ORM.Q5_K_M.gguf b/Llama3-Numina850K-ORM.Q5_K_M.gguf new file mode 100644 index 0000000..eba8e4a --- /dev/null +++ b/Llama3-Numina850K-ORM.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149ea931ff20c3a860e455174a22447a7afda7f8fdd2e1e2fcdbab53f1f882b1 +size 5732992384 diff --git a/Llama3-Numina850K-ORM.Q5_K_S.gguf b/Llama3-Numina850K-ORM.Q5_K_S.gguf new file mode 100644 index 0000000..db939bc --- /dev/null +++ b/Llama3-Numina850K-ORM.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248ded79f3dba747a8f27ee8ed27bb9afe621bd5f413e7f1675da7f3fcc0a417 +size 5599298944 diff --git a/Llama3-Numina850K-ORM.Q6_K.gguf b/Llama3-Numina850K-ORM.Q6_K.gguf new file mode 100644 index 0000000..4b19d96 --- /dev/null +++ b/Llama3-Numina850K-ORM.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612ea1707f48089b600692149637a0048ca6c4401f7ca7cdd09eca3a1785ced0 +size 6596011392 diff --git a/Llama3-Numina850K-ORM.Q8_0.gguf b/Llama3-Numina850K-ORM.Q8_0.gguf new file mode 100644 index 0000000..56742ed --- /dev/null +++ b/Llama3-Numina850K-ORM.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a135e4f8bb02ff23ca984164792b1c41c19e6d0dd6ae87e312b0563ce05b1d11 +size 8540775808 diff --git a/Llama3-Numina850K-ORM.f16.gguf b/Llama3-Numina850K-ORM.f16.gguf new file mode 100644 index 0000000..9c232ab --- /dev/null +++ b/Llama3-Numina850K-ORM.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b143efda2824796b7b47ce662a4c4375b0503283bab9292ade4923bb2254ddac +size 16068896128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cae80e7 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: HanningZhang/Llama3-Numina850K-ORM +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/HanningZhang/Llama3-Numina850K-ORM + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3-Numina850K-ORM-GGUF).*** + +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/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Numina850K-ORM-GGUF/resolve/main/Llama3-Numina850K-ORM.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. + +