commit 619116c95b2784a46af185f98efaa4dfa01096d3 Author: ModelHub XC Date: Mon Jun 1 09:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..500114c --- /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 +NeuralHermes-2.5-Mistral-7B-laser.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.f16.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NeuralHermes-2.5-Mistral-7B-laser.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralHermes-2.5-Mistral-7B-laser.IQ4_XS.gguf b/NeuralHermes-2.5-Mistral-7B-laser.IQ4_XS.gguf new file mode 100644 index 0000000..c464c77 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0726317f32f58c9a445848a11b2ac2d2c7f02e8f12cfbb641c5600c2ee13e888 +size 3944401024 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q2_K.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q2_K.gguf new file mode 100644 index 0000000..14d6324 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554999aa87e4cf0df222744f7b1c07693d92149200e94585b0ff0580f29da878 +size 2719252992 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_L.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_L.gguf new file mode 100644 index 0000000..49abb55 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:765746d5416e719b86a994e557250004972a832d3bc7203ff0ac9d8426a65394 +size 3822036288 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_M.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_M.gguf new file mode 100644 index 0000000..10fcc1a --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57869d72cc73ad7c3b4b9e6524fe37b3391f85743a1fbf28a1346faa7ccd3fbe +size 3518997824 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_S.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_S.gguf new file mode 100644 index 0000000..e52a2ed --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8b0b06cd518242147c7efc7828499aa5633afc92b04fe691c2b3cd9068764a +size 3164579136 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q4_0_4_4.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q4_0_4_4.gguf new file mode 100644 index 0000000..625262d --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2aed666e597e710c95381a8472450a246ba8405bb04825c1094ab6806f73a4 +size 4108929408 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_M.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_M.gguf new file mode 100644 index 0000000..836b341 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ed5cd88191447a788a3fd3c82f3d20c4bfb9ea6c645bb5bd7dc8b3723d5aaa +size 4368451968 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_S.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_S.gguf new file mode 100644 index 0000000..55810c4 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa202b8bad3d2016ab4431ad8dad1c34db47d25e3c0ab2a609b8725f4531afd +size 4140386688 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_M.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_M.gguf new file mode 100644 index 0000000..2626ca6 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6390261cee996450bbc62d86a6ed55116e24a2098cba5e529644e3246f9a7452 +size 5131423104 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_S.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_S.gguf new file mode 100644 index 0000000..3bae19d --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f975c3f22eb1d05d427744c7556faf0802350b136c4ae86d00c13d2cd3adea70 +size 4997729664 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q6_K.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q6_K.gguf new file mode 100644 index 0000000..2b36dd5 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d20516280281df51e0397925848d9a4ceee2ac166c2ec8e62098b91501671b +size 5942079936 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.Q8_0.gguf b/NeuralHermes-2.5-Mistral-7B-laser.Q8_0.gguf new file mode 100644 index 0000000..cd74fd8 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e6fa6679971c33885950226af7dcad0b510cc5908216793e163b6fb5e237a6 +size 7695876416 diff --git a/NeuralHermes-2.5-Mistral-7B-laser.f16.gguf b/NeuralHermes-2.5-Mistral-7B-laser.f16.gguf new file mode 100644 index 0000000..0257fa5 --- /dev/null +++ b/NeuralHermes-2.5-Mistral-7B-laser.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2c8c72c9d7d7c9b56a9d7e577949977f5f810b4292db5a94e82258ed6ec37e +size 14484766016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4252d8 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: mlabonne/NeuralHermes-2.5-Mistral-7B-laser +datasets: +- mlabonne/chatml_dpo_pairs +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mistral +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- distillation +- dpo +- rlhf +- laser +--- +## About + + + + + + +static quants of https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B-laser + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-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/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NeuralHermes-2.5-Mistral-7B-laser-GGUF/resolve/main/NeuralHermes-2.5-Mistral-7B-laser.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. + +