commit b5f4ab53c9153bbe0003c39ad2780bf0d3380a02 Author: ModelHub XC Date: Fri Oct 2 17:15:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d7a9587 --- /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 +Mistral-7B-v0.1-chat-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.1-chat-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-v0.1-chat-ORPO.IQ4_XS.gguf b/Mistral-7B-v0.1-chat-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..869acb4 --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f89e2ed31026bca5e9ab1813329e0c9f2c5a51ae58448d6913a467202236886 +size 3944389888 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q2_K.gguf b/Mistral-7B-v0.1-chat-ORPO.Q2_K.gguf new file mode 100644 index 0000000..522740b --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9f7705d9915f9e2083aecf82a9347babbf4ca41dc9a42efabac48f870a5096 +size 2719243520 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q3_K_L.gguf b/Mistral-7B-v0.1-chat-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..a5680e4 --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942049ac95be1c9713d99ad4c50916fb725b1dda348525814356be74985c2bb3 +size 3822025984 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q3_K_M.gguf b/Mistral-7B-v0.1-chat-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..398540b --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c005a87e78cac1860f263171d67d629c3f8c3b4edf21e21ac1520f4f9fc3f1ae +size 3518987520 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q3_K_S.gguf b/Mistral-7B-v0.1-chat-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..23c273b --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10704943dd5d6c24979843d9d3a004c844faa432a7c53b5f3902ae973cec4074 +size 3164568832 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q4_K_M.gguf b/Mistral-7B-v0.1-chat-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..4a3c7fc --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33de29eaedf29b869800ed20ef4112de0d8669fa980f156291900cd9fdd3e882 +size 4368440576 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q4_K_S.gguf b/Mistral-7B-v0.1-chat-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..650419b --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c2780bb9adddce041242957fd8df35a82b34cc5ba4c505833d14e6043d30977 +size 4140375296 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q5_K_M.gguf b/Mistral-7B-v0.1-chat-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..bd68715 --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d20e5c47132a4c96f0a51a6205d9579215b6d81497698b6bec7a247590e84ef +size 5131410688 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q5_K_S.gguf b/Mistral-7B-v0.1-chat-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..a5a5ea6 --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfbde469c7bfaaeff77ba1e2cbbc9a1c493d93c1451ac0544bef6fdde3bd4f60 +size 4997717248 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q6_K.gguf b/Mistral-7B-v0.1-chat-ORPO.Q6_K.gguf new file mode 100644 index 0000000..58914cf --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275bfd21dc48b6b86c7317172df79c746b3d237f5950611a95c009d9b7c945f5 +size 5942066432 diff --git a/Mistral-7B-v0.1-chat-ORPO.Q8_0.gguf b/Mistral-7B-v0.1-chat-ORPO.Q8_0.gguf new file mode 100644 index 0000000..ccbd01a --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c68eb7d50d1d209ef80ab966904606b0003f2049c09e2e97835eec65bdb724 +size 7695858944 diff --git a/Mistral-7B-v0.1-chat-ORPO.f16.gguf b/Mistral-7B-v0.1-chat-ORPO.f16.gguf new file mode 100644 index 0000000..af60f5a --- /dev/null +++ b/Mistral-7B-v0.1-chat-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44703d4d59c5156216d67656cc3accf747c8fa07ab78da0f01e47f39fd857775 +size 14484733184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..03646c5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Trelis/Mistral-7B-v0.1-chat-ORPO +datasets: +- argilla/dpo-mix-7k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- pretrained +--- +## About + + + + + + +static quants of https://huggingface.co/Trelis/Mistral-7B-v0.1-chat-ORPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-v0.1-chat-ORPO-GGUF).*** + +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/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.1-chat-ORPO-GGUF/resolve/main/Mistral-7B-v0.1-chat-ORPO.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. + +