commit 6825d77467986562ffe1a043a3bae8577524c2f9 Author: ModelHub XC Date: Mon Sep 14 08:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/flammen12-mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c27d2e7 --- /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 +flammen12-mistral-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +flammen12-mistral-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d29c048 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: flammenai/flammen12-mistral-7B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/flammenai/flammen12-mistral-7B + + +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/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/flammen12-mistral-7B-GGUF/resolve/main/flammen12-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. + + diff --git a/flammen12-mistral-7B.IQ4_XS.gguf b/flammen12-mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..e5f35ec --- /dev/null +++ b/flammen12-mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34239b99fc43a65bd36629aff2681cf97100c381afec6aad76df2afb82ceeb44 +size 3944389664 diff --git a/flammen12-mistral-7B.Q2_K.gguf b/flammen12-mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..41dc51d --- /dev/null +++ b/flammen12-mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2892643ba08ae40e606f67131aac5923494392b6d04dc75f19f5de2790d1b0e +size 2719243296 diff --git a/flammen12-mistral-7B.Q3_K_L.gguf b/flammen12-mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..8362a85 --- /dev/null +++ b/flammen12-mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c06e9bb0d6f90499a93eb52292b0f36ea258897561bbcd819cb4140fd413e4e +size 3822025760 diff --git a/flammen12-mistral-7B.Q3_K_M.gguf b/flammen12-mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..736f08d --- /dev/null +++ b/flammen12-mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cac3a32d0d286aca8cc407256a0a479a1a373c9ac4bb57698052076727f090 +size 3518987296 diff --git a/flammen12-mistral-7B.Q3_K_S.gguf b/flammen12-mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..0b5a7e5 --- /dev/null +++ b/flammen12-mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4b7d4a382489fa9dc837a97b9d32580e4c273224eb4264bd749945620262bf +size 3164568608 diff --git a/flammen12-mistral-7B.Q4_K_M.gguf b/flammen12-mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..1ca72a2 --- /dev/null +++ b/flammen12-mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a682e87ab048795ec1c8effb6654cbe26b5bf08bcd73f8cd67cef48a4aa6062 +size 4368440352 diff --git a/flammen12-mistral-7B.Q4_K_S.gguf b/flammen12-mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..cf905c9 --- /dev/null +++ b/flammen12-mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1346fc35fed4119b33c6ddaaa778b14acdbacba01cbf79f48f24c1c9b1dcfb6 +size 4140375072 diff --git a/flammen12-mistral-7B.Q5_K_M.gguf b/flammen12-mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..9837e59 --- /dev/null +++ b/flammen12-mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694756766451554c42fcc653ae5d2cb3eedcc2933fc0f0dbc8d5511a947d06f4 +size 5131410464 diff --git a/flammen12-mistral-7B.Q5_K_S.gguf b/flammen12-mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..640158e --- /dev/null +++ b/flammen12-mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdefed8fe5e1d2354e534ce8215bcadec6924ef7d73df87b58fa0a719d04785 +size 4997717024 diff --git a/flammen12-mistral-7B.Q6_K.gguf b/flammen12-mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..627a650 --- /dev/null +++ b/flammen12-mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36fe00d3585c16fd54ff93323602da6105e7458dbc5612303a7965cd49938651 +size 5942066208 diff --git a/flammen12-mistral-7B.Q8_0.gguf b/flammen12-mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..d4bde5a --- /dev/null +++ b/flammen12-mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2816d84e8610203def526c942513907fd5fa162c22dcba178edbffb0b1f981 +size 7695858720 diff --git a/flammen12-mistral-7B.f16.gguf b/flammen12-mistral-7B.f16.gguf new file mode 100644 index 0000000..1666bba --- /dev/null +++ b/flammen12-mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0720e91aadf0097e2bb157837292066b39e57c44fcf6782f9152719e778d550f +size 14484732960