commit 0cfbf0d39b3451b7f5dfc2f9a229702a403bff9c Author: ModelHub XC Date: Tue Sep 1 16:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/flammen9X-mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..87354bd --- /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 +flammen9X-mistral-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +flammen9X-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..d375515 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: flammenai/flammen9X-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/flammen9X-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/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/flammen9X-mistral-7B-GGUF/resolve/main/flammen9X-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/flammen9X-mistral-7B.IQ4_XS.gguf b/flammen9X-mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..7e0ad26 --- /dev/null +++ b/flammen9X-mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbfdc93733b38484f7dc7b186d3bc110497560db23fa1fe7b5af1106d28cb06 +size 3944389696 diff --git a/flammen9X-mistral-7B.Q2_K.gguf b/flammen9X-mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..002ee64 --- /dev/null +++ b/flammen9X-mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f09bd032526b5038b6102225b9f95b8768dd65b99556ae05fae2c7730d9c5b +size 2719243328 diff --git a/flammen9X-mistral-7B.Q3_K_L.gguf b/flammen9X-mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..dafab3c --- /dev/null +++ b/flammen9X-mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e4aca5bf91d227bd8b6a0e1105fab929dcdadcb01fcfc49a850de346ebee2d +size 3822025792 diff --git a/flammen9X-mistral-7B.Q3_K_M.gguf b/flammen9X-mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..4811738 --- /dev/null +++ b/flammen9X-mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2983d16e19f9f3c86f252d5ecc943613f7cf9131415210344bbb4b663dd7f3 +size 3518987328 diff --git a/flammen9X-mistral-7B.Q3_K_S.gguf b/flammen9X-mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c6574da --- /dev/null +++ b/flammen9X-mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ed20e450d04bd432bf2c4d636882c631e29df61da3625f5cf6fde5971dea42 +size 3164568640 diff --git a/flammen9X-mistral-7B.Q4_K_M.gguf b/flammen9X-mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..ef77098 --- /dev/null +++ b/flammen9X-mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6951bde807d713f793ccdd61844593499b1558ae28dda52b90fa8f7e97cf2c3c +size 4368440384 diff --git a/flammen9X-mistral-7B.Q4_K_S.gguf b/flammen9X-mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..e253a8d --- /dev/null +++ b/flammen9X-mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2864a4d025c838f06187094aece588c6a2e435e80daee056246083ec5453ba4 +size 4140375104 diff --git a/flammen9X-mistral-7B.Q5_K_M.gguf b/flammen9X-mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..d355c90 --- /dev/null +++ b/flammen9X-mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae859ece270e4b09bba3e7c1133e1dfa3f108721561be2acbdb22d76eb4678ca +size 5131410496 diff --git a/flammen9X-mistral-7B.Q5_K_S.gguf b/flammen9X-mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..9098e92 --- /dev/null +++ b/flammen9X-mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c027317474a0a4c1873af4b6cd7cee31e3a2a85a8edac9870e8fc18bd926e18a +size 4997717056 diff --git a/flammen9X-mistral-7B.Q6_K.gguf b/flammen9X-mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..ea71026 --- /dev/null +++ b/flammen9X-mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96151d65df6eefb2449f045e19d158abf305b53cb7509e3ff4867d768c7e8e75 +size 5942066240 diff --git a/flammen9X-mistral-7B.Q8_0.gguf b/flammen9X-mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..cc6e365 --- /dev/null +++ b/flammen9X-mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f83fc67ed95dbe24c07fdaef4cdd0287a2ffc3c48488098175e5705bfb5c0e7 +size 7695858752 diff --git a/flammen9X-mistral-7B.f16.gguf b/flammen9X-mistral-7B.f16.gguf new file mode 100644 index 0000000..8ff18ed --- /dev/null +++ b/flammen9X-mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec31762d9c625d5ff8c053c5a1e2e49833fdfe68d2a00be56673121e211b2a69 +size 14484732992