commit 1a5482b8fa475a9598f0a51175f5b32273e59704 Author: ModelHub XC Date: Wed Sep 2 20:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..48dae9a --- /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 +Bagel-Hermes-2-Pro-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bagel-Hermes-2-Pro-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.IQ4_XS.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..d774360 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e34a3c62b1b7af4e14e5525dd5c450ddcfb2e1815b5b791eeadf502b8f01ba8 +size 4484363936 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q2_K.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..5083821 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a82ef9086068e146cfbc38c69bc90c9443b6bd97a98e7e53a052fc6df0590f +size 3179132576 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_L.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..fa6eb74 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892725c8349efa03b0efe2631c8d9883d0cc3aed5b055fade5bad04d5325c8e5 +size 4321957536 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_M.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..cd23c8a --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b00e7434e15b6364b0a97d4f90047d4db6178e075aff3eb2d92f494766f4419 +size 4018919072 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_S.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..e3fad1e --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aac78a0dad9746064dea5abd5ef7baf92f51e0f3146004f9af2a86407d98b73 +size 3664500384 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_M.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1dcf600 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614cf43c515539486c243975e433fd7279944cec0a8814feb762a2d404b892ee +size 4920735392 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_S.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..2a9b6d3 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e322a08c0d84aa3333a8396c5233b4c86fc9fc365edf6e346516dd450120f0a +size 4692670112 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_M.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..d6ec58b --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62e1b908afdcf92ce4f1bc5ce354e42fa5f9c6b7c5dfc573412cada7ea6b9f5 +size 5732988576 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_S.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1220305 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0024febbb48257d726265e7dcdc1f725192610e6472c373330b331d65eb7037 +size 5599295136 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q6_K.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..46b4c56 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb102eae025b49316ff952728df11b101ef907008ee4d75060575f9b330f10e0 +size 6596007584 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.Q8_0.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..e77991d --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea791ef943e24a44dbbe1ccf2b8bccfac474bfc611b1c7c6823a068d30c9fdb8 +size 8540772000 diff --git a/Bagel-Hermes-2-Pro-Llama3-8B.f16.gguf b/Bagel-Hermes-2-Pro-Llama3-8B.f16.gguf new file mode 100644 index 0000000..1989475 --- /dev/null +++ b/Bagel-Hermes-2-Pro-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4ffb2d885d8a3d9aa85b62b0e4002f9025e76fc22442e825c1c229e62c0f5a +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c8bc4af --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mrcuddle/Bagel-Hermes-2-Pro-Llama3-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mrcuddle/Bagel-Hermes-2-Pro-Llama3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bagel-Hermes-2-Pro-Llama3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-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/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF/resolve/main/Bagel-Hermes-2-Pro-Llama3-8B.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. + +