commit 0f8fbe0102833e7803a8325f6437dc2945339c6c Author: ModelHub XC Date: Tue Jun 23 20:56:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5e2c1e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-3-8B-Preview-16.5B-Brainstorm.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.IQ4_XS.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.IQ4_XS.gguf new file mode 100644 index 0000000..2962438 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a02f0dab6ac31fe1c8fcbd60744c1d0a4ea383724d2177359c17ff32761eec +size 9066765824 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q2_K.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q2_K.gguf new file mode 100644 index 0000000..6b523b7 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a516a0c6cca1d869702679cd6688bc1e47652957275a7ec3e4e9d84a958303f +size 6308863488 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_L.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_L.gguf new file mode 100644 index 0000000..29c512e --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b662b7e24526bd23f61e733268e63b9e7b63d3655acd95add3db878dbb36ba7 +size 8779480576 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_M.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_M.gguf new file mode 100644 index 0000000..0f76848 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9388a92edbf39a9d54744ff8af435ec37a644d4ebfa4fe157a7c0281a63c0d19 +size 8102624768 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_S.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_S.gguf new file mode 100644 index 0000000..6c466b4 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26f30a47bf7955601d1710e41c19cba9b97ce21b665e9eca1a43dfe476bc208 +size 7320747520 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_M.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_M.gguf new file mode 100644 index 0000000..ddd6436 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5278fd83aa20a93dd0954ed04397bfd231f5b0fc636519df05b376f9bf48a11 +size 10014875136 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_S.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_S.gguf new file mode 100644 index 0000000..4cdeb15 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d927160c684e385f1727f897485cc1390ddac474feb64a07eec730ee5b78b0a5 +size 9507986944 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_M.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_M.gguf new file mode 100644 index 0000000..a63ef40 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25a409a095c789fbca3b169fb05cd30d522393114f546966e891e0cbc292bc0 +size 11740962304 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_S.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_S.gguf new file mode 100644 index 0000000..c6ae7fa --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2769c790bfd662c1286aa8fafe550e0aef4ff83a6954ffffe3dde6233c091d3a +size 11448507904 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q6_K.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q6_K.gguf new file mode 100644 index 0000000..c76b663 --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa18b8e1bb0a79bd1f0c1f219ceeace3c7e30abaf8155c0f121ea00441acf6b3 +size 13574929920 diff --git a/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q8_0.gguf b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q8_0.gguf new file mode 100644 index 0000000..d6fe24a --- /dev/null +++ b/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7821e3b233f78112b59b8a15b857b83dec566dcaa8b9e85bb21b5e7b45340c +size 17579752960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c331044 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: DavidAU/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cognitivecomputations +- r1 +- cot +- deepseek +- Llama 3.1 +- Hermes +- DeepHermes +- 128k context +- fine tune +--- +## About + + + + + + +static quants of https://huggingface.co/DavidAU/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-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-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q2_K.gguf) | Q2_K | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_S.gguf) | Q3_K_S | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_M.gguf) | Q3_K_M | 8.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q3_K_L.gguf) | Q3_K_L | 8.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.IQ4_XS.gguf) | IQ4_XS | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_S.gguf) | Q4_K_S | 9.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q4_K_M.gguf) | Q4_K_M | 10.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_S.gguf) | Q5_K_S | 11.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q5_K_M.gguf) | Q5_K_M | 11.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q6_K.gguf) | Q6_K | 13.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm-GGUF/resolve/main/DeepHermes-3-Llama-3-8B-Preview-16.5B-Brainstorm.Q8_0.gguf) | Q8_0 | 17.7 | fast, best quality | + +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. + +