commit 35f76b7e9d0285a5d2d6b5c15bedb407f4cfa064 Author: ModelHub XC Date: Fri May 1 00:12:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenHermes-2.5-Mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e3a8a21 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +OpenHermes-2.5-Mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenHermes-2.5-Mistral-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenHermes-2.5-Mistral-7B.IQ4_XS.gguf b/OpenHermes-2.5-Mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..268f65a --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be348f7b91efedf975c88c65aea6e8b2d7a56d250166fe09810617324062cab3 +size 3944400992 diff --git a/OpenHermes-2.5-Mistral-7B.Q2_K.gguf b/OpenHermes-2.5-Mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..13d4ab5 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328734fb0dc59f6e46e85b423aee112f728472f5c87842c7853559cef4968271 +size 2719252960 diff --git a/OpenHermes-2.5-Mistral-7B.Q3_K_L.gguf b/OpenHermes-2.5-Mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..8e6ab52 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb996253cd2c67fa55ba6eaa99cb090f5e2075d5ec2e566ef91222319d85d87 +size 3822036256 diff --git a/OpenHermes-2.5-Mistral-7B.Q3_K_M.gguf b/OpenHermes-2.5-Mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..8c4a932 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3d43d88f960e5e1a9dc116dc51a07cc9630b867888fd57093464b007bf5835 +size 3518997792 diff --git a/OpenHermes-2.5-Mistral-7B.Q3_K_S.gguf b/OpenHermes-2.5-Mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..846270b --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b2bbfc512f0b111025572be3cd0aab8e82292b6cb93e53af4400ac425d5cc6 +size 3164579104 diff --git a/OpenHermes-2.5-Mistral-7B.Q4_0_4_4.gguf b/OpenHermes-2.5-Mistral-7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..ccbd407 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd82a3df60f86f8eb958f2db2607713ce0d746e2d22b27958893bb13dd29ff7e +size 4108929376 diff --git a/OpenHermes-2.5-Mistral-7B.Q4_K_M.gguf b/OpenHermes-2.5-Mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..c12177a --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9c802c09991d65b5d76c9ed774bb0375ad5e7063fa10f78d7ef724ddec88ef +size 4368451936 diff --git a/OpenHermes-2.5-Mistral-7B.Q4_K_S.gguf b/OpenHermes-2.5-Mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..7cff2c8 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf86065c36ada8d9e4f51c944252edb6760ddda12ba3771c7ac1374cc9918d3 +size 4140386656 diff --git a/OpenHermes-2.5-Mistral-7B.Q5_K_M.gguf b/OpenHermes-2.5-Mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..f69ebe6 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21512fceeeb2ba06f59d105f72c74f1b21f71fb30ea28e1da027ff92b8c46aa6 +size 5131423072 diff --git a/OpenHermes-2.5-Mistral-7B.Q5_K_S.gguf b/OpenHermes-2.5-Mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..dc752cd --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c804558e2bbc5784e983fb93cdc7d0bf4eda872542e24e92c518be5931e3d2 +size 4997729632 diff --git a/OpenHermes-2.5-Mistral-7B.Q6_K.gguf b/OpenHermes-2.5-Mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..c3632fb --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554f38fb44d37fdb827b35bb5d0777e42630680505e11a98b5e74ac91a68bcff +size 5942079904 diff --git a/OpenHermes-2.5-Mistral-7B.Q8_0.gguf b/OpenHermes-2.5-Mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..bb0515e --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a95021470a20ea2a3599a47618c3a16e7927856a8f2793f15a78aecd49103db +size 7695876384 diff --git a/OpenHermes-2.5-Mistral-7B.f16.gguf b/OpenHermes-2.5-Mistral-7B.f16.gguf new file mode 100644 index 0000000..71e6978 --- /dev/null +++ b/OpenHermes-2.5-Mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8506702fbda461a6b45c30814f5c6c83b14142cb4b92e2215351af249f598e2 +size 14484765984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c836b2b --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: teknium/OpenHermes-2.5-Mistral-7B +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mistral +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +--- +## About + + + + + + +static quants of https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-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/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/OpenHermes-2.5-Mistral-7B.f16.gguf) | f16 | 14.6 | 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. + +