commit 4e1e605db507c563ee619372ab85aeb36a64e8f5 Author: ModelHub XC Date: Tue Jun 30 03:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes3-R1-Llama3.2-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2023074 --- /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 +Hermes3-R1-Llama3.2-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes3-R1-Llama3.2-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes3-R1-Llama3.2-3b.IQ4_XS.gguf b/Hermes3-R1-Llama3.2-3b.IQ4_XS.gguf new file mode 100644 index 0000000..acbb394 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d7ef15cdf996a72fbb35de8fc6976af0745f0decf005fff54e590c853309e3 +size 1840903328 diff --git a/Hermes3-R1-Llama3.2-3b.Q2_K.gguf b/Hermes3-R1-Llama3.2-3b.Q2_K.gguf new file mode 100644 index 0000000..ef3178b --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87869847646188e04cb18ca00028da9d91b6ac1babab4791a131346c1c20ca39 +size 1363932320 diff --git a/Hermes3-R1-Llama3.2-3b.Q3_K_L.gguf b/Hermes3-R1-Llama3.2-3b.Q3_K_L.gguf new file mode 100644 index 0000000..4584180 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfb92454cedb596898d7b449e020512f1ec5d5b510d5284ef2702b03ae122af +size 1815344288 diff --git a/Hermes3-R1-Llama3.2-3b.Q3_K_M.gguf b/Hermes3-R1-Llama3.2-3b.Q3_K_M.gguf new file mode 100644 index 0000000..5739f00 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f8b6b8e12ca597a70dcf90626b12ec6cb44f7e3d2101a2557b4a062e54431b +size 1687155872 diff --git a/Hermes3-R1-Llama3.2-3b.Q3_K_S.gguf b/Hermes3-R1-Llama3.2-3b.Q3_K_S.gguf new file mode 100644 index 0000000..d4bb63f --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90463220f62f3c4556d6836c8780b7bab1062a5dab26d03e1a6aec88e6716026 +size 1542845600 diff --git a/Hermes3-R1-Llama3.2-3b.Q4_K_M.gguf b/Hermes3-R1-Llama3.2-3b.Q4_K_M.gguf new file mode 100644 index 0000000..32c0e7e --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5117837c34ab5a2a6960015eb2134ae2d7c26b9193e8a7057a64a41d21c678c3 +size 2019374240 diff --git a/Hermes3-R1-Llama3.2-3b.Q4_K_S.gguf b/Hermes3-R1-Llama3.2-3b.Q4_K_S.gguf new file mode 100644 index 0000000..1e4e5f0 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6541b787767367d8910853ed7697d1a0c535276714361b7583739042449af807 +size 1928197280 diff --git a/Hermes3-R1-Llama3.2-3b.Q5_K_M.gguf b/Hermes3-R1-Llama3.2-3b.Q5_K_M.gguf new file mode 100644 index 0000000..8a3a413 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a18da69837949f7208d28256a4227f198aa41ed77a8d3e583590ced22fe9c6d9 +size 2322150560 diff --git a/Hermes3-R1-Llama3.2-3b.Q5_K_S.gguf b/Hermes3-R1-Llama3.2-3b.Q5_K_S.gguf new file mode 100644 index 0000000..6f0c601 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66566c75cd48522d8213fa332aeb07a1f2b3aa984a736a1ccd67dbd8448a107d +size 2269508768 diff --git a/Hermes3-R1-Llama3.2-3b.Q6_K.gguf b/Hermes3-R1-Llama3.2-3b.Q6_K.gguf new file mode 100644 index 0000000..4a2cd3a --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61fac64af397372aa4f8e66914e845d5926cfe9c477bf4e066685dbfdfa643a1 +size 2643850400 diff --git a/Hermes3-R1-Llama3.2-3b.Q8_0.gguf b/Hermes3-R1-Llama3.2-3b.Q8_0.gguf new file mode 100644 index 0000000..869bdd6 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a5d69ba4ae1a09f384c39ca9eebecc6bcbc0587f731562bf8f8321fde0888e +size 3421895840 diff --git a/Hermes3-R1-Llama3.2-3b.f16.gguf b/Hermes3-R1-Llama3.2-3b.f16.gguf new file mode 100644 index 0000000..05c4f76 --- /dev/null +++ b/Hermes3-R1-Llama3.2-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a858c0e87221a4266d330f161fd69e95e25e59ef03a57d52435ad38230dfe02 +size 6433684640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..470e0fb --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Triangle104/Hermes3-R1-Llama3.2-3b +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Triangle104/Hermes3-R1-Llama3.2-3b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-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/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes3-R1-Llama3.2-3b-GGUF/resolve/main/Hermes3-R1-Llama3.2-3b.f16.gguf) | f16 | 6.5 | 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. + +