commit f45980d5634ad9403492aec1195dbd346821f35f Author: ModelHub XC Date: Mon Jul 6 02:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..187b7a5 --- /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 +NeuralHermes-2.5-Mistral-7B_Mar24.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B_Mar24.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.IQ4_XS.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.IQ4_XS.gguf new file mode 100644 index 0000000..a637f36 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19fd73e66c898b43aa4c0974d1d6e77aa993a12c4ee7d03236062eb3ae3a4f8 +size 3944400512 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q2_K.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q2_K.gguf new file mode 100644 index 0000000..5a51690 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6797b0ed7aa5f4cd0ebeea49e26ecf91e12a33ed57ae078c4df01fb4fd41a0eb +size 2719252480 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_L.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_L.gguf new file mode 100644 index 0000000..d46f284 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e1029dd4567226b6f6a7a96a8f3b789e3e07b4b11038c5a8673d80e72a3998 +size 3822035776 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_M.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_M.gguf new file mode 100644 index 0000000..8d999b6 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d7d03f4eac3e04aeae458fbc78e5d77efd7d89c8e11e9d4f7a5350acea8791 +size 3518997312 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_S.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_S.gguf new file mode 100644 index 0000000..a6e82f3 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128fdc906a572ab090b36c426ffa9f0dbcae6680dacad77beb664306febc8097 +size 3164578624 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_M.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_M.gguf new file mode 100644 index 0000000..d373ee6 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d276626dd33a671460db1b06a7ecc568065bcb58bf7ddefd3ff95749abfca3 +size 4368451456 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_S.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_S.gguf new file mode 100644 index 0000000..64e751a --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fc16ee55053ea3b3a23fdce01d01ce0eb7f6c7a916ea28222a36f30cd71d7e +size 4140386176 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_M.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_M.gguf new file mode 100644 index 0000000..acf738d --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dda8fe27545c0fd89019147ed97714b4ad989dde019cc8507a7411a7a95a21c +size 5131422592 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_S.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_S.gguf new file mode 100644 index 0000000..8f2ae78 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a12e5151d2d12cfb07ddb97bfcfa6134dcbf8459a2e70b16be30c18a6a9d8ee +size 4997729152 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q6_K.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q6_K.gguf new file mode 100644 index 0000000..53f4565 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926c71d61abe6195aeff66c2a329a666158ab2161297cc95ae1464b68f2657e2 +size 5942079424 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.Q8_0.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.Q8_0.gguf new file mode 100644 index 0000000..abac35d --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b647fe20c1c8f71b289b251b7fa0317ec7c84b03409186a3588a4ad70049f1 +size 7695875904 diff --git a/NeuralHermes-2.5-Mistral-7B_Mar24.f16.gguf b/NeuralHermes-2.5-Mistral-7B_Mar24.f16.gguf new file mode 100644 index 0000000..5d3cf63 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B_Mar24.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fff0577ab1787162b280d42f437a6bc386daaf634ba1a01e2c3c4b4695262d +size 14484765504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f093b27 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: satendra4u2022/NeuralHermes-2.5-Mistral-7B_Mar24 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/satendra4u2022/NeuralHermes-2.5-Mistral-7B_Mar24 + + +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/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B_Mar24-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B_Mar24.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. + +