commit dfc80a758f7b0ecbd4add6da5a435b25c0793004 Author: ModelHub XC Date: Tue May 26 21:56:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/inferless-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d1757e --- /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 +inferless-Llama-3-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +inferless-Llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b4d98f9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: rbgo/inferless-Llama-3-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/rbgo/inferless-Llama-3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#inferless-Llama-3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/inferless-Llama-3-8B-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/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/inferless-Llama-3-8B-GGUF/resolve/main/inferless-Llama-3-8B.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/inferless-Llama-3-8B.IQ3_M.gguf b/inferless-Llama-3-8B.IQ3_M.gguf new file mode 100644 index 0000000..339f91c --- /dev/null +++ b/inferless-Llama-3-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b580beebf4b3ccc8f0154835d39a9d34c73b2a5e2559e6ee041fd30b05e76e59 +size 3784833824 diff --git a/inferless-Llama-3-8B.IQ3_S.gguf b/inferless-Llama-3-8B.IQ3_S.gguf new file mode 100644 index 0000000..70e8871 --- /dev/null +++ b/inferless-Llama-3-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4866d487a49f693c34c54fcfb5d6de32357bee76728df85ae612e9e6df55c6bb +size 3682335520 diff --git a/inferless-Llama-3-8B.IQ3_XS.gguf b/inferless-Llama-3-8B.IQ3_XS.gguf new file mode 100644 index 0000000..c3d0f20 --- /dev/null +++ b/inferless-Llama-3-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2476f4190b7d9ce807c6a4368dbb7d14d807d7c928bda979fd3b99f3a488bf11 +size 3518757664 diff --git a/inferless-Llama-3-8B.IQ4_XS.gguf b/inferless-Llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..669868c --- /dev/null +++ b/inferless-Llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb614de44eb3f3d9b633372ea389a963b83de8617ed28085c05756e124fa35d +size 4484374112 diff --git a/inferless-Llama-3-8B.Q2_K.gguf b/inferless-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..1080787 --- /dev/null +++ b/inferless-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b731ff92c4a7fafce4fdc2d41470439887fa4b6ad647d04a2c6593c94a36fba5 +size 3179141088 diff --git a/inferless-Llama-3-8B.Q3_K_L.gguf b/inferless-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..c8768f4 --- /dev/null +++ b/inferless-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f9770b4e42e988bb6d3a5d6555456c64539ae6bc20cbdcb01d6fad06f99069 +size 4321966880 diff --git a/inferless-Llama-3-8B.Q3_K_M.gguf b/inferless-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..f97af3c --- /dev/null +++ b/inferless-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5a4908ac42fde91b7c34fdb60420a3f20cf89139a1f86b313eb70239bd57b1 +size 4018928416 diff --git a/inferless-Llama-3-8B.Q3_K_S.gguf b/inferless-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9ffd82c --- /dev/null +++ b/inferless-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad46a10aa44296fa0d38ccc615f6a1021db101d57884893646ee7871bf23c16 +size 3664509728 diff --git a/inferless-Llama-3-8B.Q4_K_M.gguf b/inferless-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..54ae2be --- /dev/null +++ b/inferless-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9ef53a79a02c1841ae987192c29defa0d63dccab21de03aa1d908227141918 +size 4920745824 diff --git a/inferless-Llama-3-8B.Q4_K_S.gguf b/inferless-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..e945e4b --- /dev/null +++ b/inferless-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5201c5d073fcdf0fe1493cf037e92176faac1708b654f0ca85595886aa45fc0 +size 4692680544 diff --git a/inferless-Llama-3-8B.Q5_K_M.gguf b/inferless-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6c407a9 --- /dev/null +++ b/inferless-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc974d73619b2b9172727abfeba48821cc0faed80c1f24eb5d6bf895316ac30 +size 5733000032 diff --git a/inferless-Llama-3-8B.Q5_K_S.gguf b/inferless-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..00e1d1e --- /dev/null +++ b/inferless-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e2f68beab053deeab0e87c16b25845280e90dbacc3a632e44c7540676772ca9 +size 5599306592 diff --git a/inferless-Llama-3-8B.Q6_K.gguf b/inferless-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..c9687e5 --- /dev/null +++ b/inferless-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a7139cee2bf84e64dcabdd5ada3219fcdd4d36810dfeed54f81bdcfdec13e4 +size 6596020128 diff --git a/inferless-Llama-3-8B.Q8_0.gguf b/inferless-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..a01ddca --- /dev/null +++ b/inferless-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f1b6511cc53ff21fa0bfbc8d0639c4397a9311cefd46e2e572948c19859122 +size 8540788512 diff --git a/inferless-Llama-3-8B.f16.gguf b/inferless-Llama-3-8B.f16.gguf new file mode 100644 index 0000000..1342445 --- /dev/null +++ b/inferless-Llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e35cd9a0c80072f5e8eef4797254ca18e15c13617ec924265ec106844a73e7 +size 16068924192