commit 918cc3fc1e50d36391e4691eda6d060bb30b5e2d Author: ModelHub XC Date: Tue Jun 2 13:08:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..670f2e5 --- /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 +DeepHermes-3-Llama-3-3B-Preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-3B-Preview.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepHermes-3-Llama-3-3B-Preview.IQ4_XS.gguf b/DeepHermes-3-Llama-3-3B-Preview.IQ4_XS.gguf new file mode 100644 index 0000000..e16473d --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82049d9e02894d7094d1048e7bf593e8e84e44db6b5bf61e42e2ceb548a4b502 +size 1840909248 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q2_K.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q2_K.gguf new file mode 100644 index 0000000..2a78ff9 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607a70717acb57ac9e5cda13937c5354d74233b031725b7bcae59d5574093d59 +size 1363938240 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q3_K_L.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_L.gguf new file mode 100644 index 0000000..1bd1fa6 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d697f66b8d16cec8979aca36f112e3089a92c27ac1c538a592a041eac1e6a0 +size 1815350208 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q3_K_M.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_M.gguf new file mode 100644 index 0000000..0e26487 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608a9ebe2919150e8cfc037f4e177eeb1280ed8f5449e3be76d71f371c598690 +size 1687161792 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q3_K_S.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_S.gguf new file mode 100644 index 0000000..bbf1e6c --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff42c722c4af06a6bbe50856aa279b700ba8304f45aadfd14d3ceb447ec3746f +size 1542851520 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q4_K_M.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q4_K_M.gguf new file mode 100644 index 0000000..8749651 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f0983137335e423498393fc4dbf2b8bba5f23f50212f36409abd3f382ecb698 +size 2019380160 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q4_K_S.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q4_K_S.gguf new file mode 100644 index 0000000..1f2c9bb --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f59b445e0a6f907222fee904196cc346729af38edea90dab53881679ac9b86 +size 1928203200 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q5_K_M.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q5_K_M.gguf new file mode 100644 index 0000000..6ef22c1 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5d4a38e4655666203e4ca9eac43d5269200647cbcf8df64eac14192561fa96f +size 2322156480 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q5_K_S.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q5_K_S.gguf new file mode 100644 index 0000000..8100997 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c2f7a6bec45b45dd329a095ac9098e637387e1cfb14c525c2a6325b5a5c430 +size 2269514688 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q6_K.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q6_K.gguf new file mode 100644 index 0000000..184a8ec --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02d2e6834bcfc19e754a3ce9509dbdec92082e0875603eb5919a4c091e41565 +size 2643856320 diff --git a/DeepHermes-3-Llama-3-3B-Preview.Q8_0.gguf b/DeepHermes-3-Llama-3-3B-Preview.Q8_0.gguf new file mode 100644 index 0000000..48ef4c3 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db31047613b587af824363adbf3ad6487fafa7cf3e4499cc66f0183cb465d53 +size 3421901760 diff --git a/DeepHermes-3-Llama-3-3B-Preview.f16.gguf b/DeepHermes-3-Llama-3-3B-Preview.f16.gguf new file mode 100644 index 0000000..e2d7302 --- /dev/null +++ b/DeepHermes-3-Llama-3-3B-Preview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f758a1dcbd4bfc0ba5758b8cc32873ca331d22014a376a1c6d650e92a09f8a89 +size 6433690560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff13b87 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: NousResearch/DeepHermes-3-Llama-3-3B-Preview +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Llama-3 +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +- function calling +- json mode +- axolotl +- roleplaying +- chat +- reasoning +- r1 +- vllm +--- +## About + + + + + + +static quants of https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-3B-Preview + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepHermes-3-Llama-3-3B-Preview-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-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/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-3B-Preview-GGUF/resolve/main/DeepHermes-3-Llama-3-3B-Preview.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. + +