commit 20a69ac52cbef26bd874dd2a98d403855e1a43f8 Author: ModelHub XC Date: Sun Oct 18 19:22:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7eba0fb --- /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 +EnnoAi-Pro-Llama-3-8B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EnnoAi-Pro-Llama-3-8B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_M.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..5627a34 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489c1dbe10019df358c7433f12d4f002560cace260c20cf6dc88d048e3a6a36d +size 3784988448 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_S.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..97439c0 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa10b20a1bb10941e4cdddbdcf48b15fc182adfd8c5ea6e88abc866c6ed19d30 +size 3682490144 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_XS.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..6f8dbbb --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6d1938e4ad76effc9bd5323ed1557cdf18026114fd80fea0f2c9e20017e9cc +size 3518912288 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.IQ4_XS.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..045667f --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4de0fb93f5a02d1d513ec315a7bce1bbf7555edea6797647b4c6c2a7e577b3d +size 4484541216 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q2_K.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..0571766 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a782ef6c16c913d68b54ee2cc71c84ba3205d0638d736d1c6853ccc71e2ee2 +size 3179283232 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_L.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..c283bf0 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f1343486839abc548b6a5ce59e3e51bb90d467c16afad0de2fbf7c9aa4af5c +size 4322121504 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_M.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..f2ccc7b --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d393725507b50bb88a77f200f572d7966d21b7afbb49160a716ecb200cd58ecd +size 4019083040 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_S.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..5c9e062 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227e99e2c8510bf23ef35d241b219c8f6921d7c4532e1ef91fe431b85b78ec7a +size 3664664352 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_M.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..4ced3cc --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01efca32d587f6b994be211e764fdd2c6de96a15ca2b1d5226c484c6685e9788 +size 4920916768 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_S.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..3b72615 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4395d8a7234c284094b615a50749021fc3b2aa219b53d63a22868345c03f130c +size 4692851488 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_M.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..19921a7 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3eaf45dd60929c886c5017be098b06364290c51663041fd02ccd882dd134984 +size 5733186336 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_S.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..b829aa6 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6c6cd3b0feec94565dccff8c9f19844e769b25a2209b7da098db0b032bff57 +size 5599492896 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q6_K.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..69aab0d --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52a979ed1c7debb13d6cb5f46234bb41d852f81b0ae5e183b99954f8f0b5744 +size 6596222752 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.Q8_0.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..da223bb --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23a2a4582c849e0572b9bdd73e390c69bf957645213396c5f104ad075966009 +size 8541050656 diff --git a/EnnoAi-Pro-Llama-3-8B-v0.1.f16.gguf b/EnnoAi-Pro-Llama-3-8B-v0.1.f16.gguf new file mode 100644 index 0000000..2937d03 --- /dev/null +++ b/EnnoAi-Pro-Llama-3-8B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bacc04f99deae1dcda615127f974cdf7cf34dd9214fd2529588aef2590ba34e8 +size 16069416736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9740e66 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.1 +language: +- en +- fr +library_name: transformers +license: bigscience-bloom-rail-1.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Enno-Ai/EnnoAi-Pro-Llama-3-8B-v0.1 + + +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/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EnnoAi-Pro-Llama-3-8B-v0.1-GGUF/resolve/main/EnnoAi-Pro-Llama-3-8B-v0.1.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. + +