commit 3b19930478d4384e9bdf75669e2b807a13966b07 Author: ModelHub XC Date: Sun Jun 21 14:38:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bedc9a4 --- /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 +Hermes-3-Llama-3.2-3B-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-3-Llama-3.2-3B-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.IQ4_XS.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..f5193f4 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d11b605318a1689438c9ab2f93040380d0af02a7286ca4a109149b3c5b4d0a +size 1840902848 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q2_K.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..cf1721c --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817707a3a441cda17c12e004fb6e64add2140335f9cb258a826e4be764dcc7c4 +size 1363931840 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_L.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..953e626 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba287724543f9dfbccfd65b109483105158d15dcc606ab8a2c44314caf1bbf5 +size 1815343808 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_M.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..3fe05ee --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183a027489e1b51c6a974da419a99f88a1b4f441787d39b4c547d6f9871d99d6 +size 1687155392 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_S.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..efc0602 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06f1273948c6c5b92a0beefead72a49ec8e2ab576f9170638376e5ee9aa70acd +size 1542845120 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_M.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..a61fccd --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876cdf48e11732a2365281939a50a70d34cafbf764ee016a6d5bd21e6c084bd4 +size 2019373760 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_S.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..747e29a --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787f1947060d75b2e2ed962c72305b87b7d9dde9d61627b73e3f4b488d345c3a +size 1928196800 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_M.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..51a1349 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c67a7c6e61d3b14319917571d2c65a4ea97be8964c5a7b21907fc95f1fe4da75 +size 2322150080 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_S.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..ae4c373 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c69918811d496458e94db7679c052fb2de381381968613f5651c4f8746c6755 +size 2269508288 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q6_K.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..4883fde --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca8bf8168ba8ddbacb89f2fe67fc3fc482aeffbaa7e3e162f589e0e8f0cba5f +size 2643849920 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.Q8_0.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..fb40439 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6230810047a3ae7d38e277f48fd0a835e3a524b9ad9e5692bf0ec864c9d495a +size 3421895360 diff --git a/Hermes-3-Llama-3.2-3B-Reasoning.f16.gguf b/Hermes-3-Llama-3.2-3B-Reasoning.f16.gguf new file mode 100644 index 0000000..37bdda5 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b899a23a6bc97f19eb73febb34ab04da920c2cbaa633fcaa9fcae339a79f6ec9 +size 6433684160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7575c0f --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ApatheticWithoutTheA/Hermes-3-Llama-3.2-3B-Reasoning +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- unsloth +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/ApatheticWithoutTheA/Hermes-3-Llama-3.2-3B-Reasoning + + +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/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-3-Llama-3.2-3B-Reasoning-GGUF/resolve/main/Hermes-3-Llama-3.2-3B-Reasoning.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. + +