commit 80b58e07512e5863c34c5716470b672ffa928d6a Author: ModelHub XC Date: Wed Oct 14 04:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1c7f93 --- /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-Instruct-v0.2-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.2-DPO.IQ4_XS.gguf b/Mistral-7B-Instruct-v0.2-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..61fe2bd --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5e9401479014fc830d2b6506e6a7878d58b42fd55f9a5f1e1f82408ef51b70 +size 3944390464 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q2_K.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q2_K.gguf new file mode 100644 index 0000000..ca5bdf9 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0520baab4cb41295b8fe2930bcc4a3ca6736a500aafe181aeaeaf514293a107c +size 2719244096 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q3_K_L.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..d83565c --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:301f32059d63df0394cc0613acc6938b0ef49baf49d2e9ca8183cef88392afec +size 3822026560 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q3_K_M.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..d28934a --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d2ec8ea2adfc03398dcc6dcbff76dd72e44d50f0dcd318541e2d194ae998d8 +size 3518988096 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q3_K_S.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..2534c53 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b994ceec9854426d1d9991c5e171dd7258fee0485fb490c30249c4ec14a512 +size 3164569408 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q4_K_M.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..2c0f4dc --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faba0c7b4c03d06ea217402ac82fa92b2aa2d80b9295c014987abd020a0a24dc +size 4368441152 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q4_K_S.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..6588a0d --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3b743b73c5e8b444e6e01cccc76db7ddbb160fb216bd135246c56d2938fa25 +size 4140375872 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q5_K_M.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..1169adb --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d67719cf8da284193453d9b316b63beba4c0d6a6ba51c18407d5508ab2a50c5 +size 5131411264 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q5_K_S.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..d0a8e86 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58781b01995e6eecf3b77d1685cf35832165e8dc7b2f7f6306cf96c27fd4ea45 +size 4997717824 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q6_K.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q6_K.gguf new file mode 100644 index 0000000..6f122ab --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90b87b94fb9190f219036e4725ee52b4fc5e72f00726079e02f59c2dfd497b2 +size 5942067008 diff --git a/Mistral-7B-Instruct-v0.2-DPO.Q8_0.gguf b/Mistral-7B-Instruct-v0.2-DPO.Q8_0.gguf new file mode 100644 index 0000000..a26bd12 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d92385996fb57a00cd1740072e70b30d626f1c3293bfee0e5176e2dea3e5e24a +size 7695859520 diff --git a/Mistral-7B-Instruct-v0.2-DPO.f16.gguf b/Mistral-7B-Instruct-v0.2-DPO.f16.gguf new file mode 100644 index 0000000..75fb78a --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def1d86f6a67248f2b9af9cb7c8b6d8854103cb12d4eb7c6b3b3590c34a2b9b8 +size 14484733760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..50f7da8 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: AmberYifan/Mistral-7B-Instruct-v0.2-DPO +datasets: +- Dahoas/full-hh-rlhf +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Mistral-7B-Instruct-v0.2-DPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-Instruct-v0.2-DPO-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-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-DPO-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-DPO.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. + +