commit 98529ec72ea1b9f747bc165076361177f43df0a5 Author: ModelHub XC Date: Sun Jun 14 09:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/flammen21X-mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9555a71 --- /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 +flammen21X-mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen21X-mistral-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..04bc42c --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: flammenai/flammen21X-mistral-7B +datasets: +- ResplendentAI/NSFW_RP_Format_NoQuote +- flammenai/Prude-Phi3-DPO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- nsfw +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/flammenai/flammen21X-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/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/flammen21X-mistral-7B-GGUF/resolve/main/flammen21X-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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/flammen21X-mistral-7B.IQ4_XS.gguf b/flammen21X-mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..284eff4 --- /dev/null +++ b/flammen21X-mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78a3df4a8df396aa373cd2f7455cf05a91b01294308b5285806dbcefb60a555 +size 3944389952 diff --git a/flammen21X-mistral-7B.Q2_K.gguf b/flammen21X-mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..184d4b0 --- /dev/null +++ b/flammen21X-mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1812fdf5c4d249d63e87ff100125bc034d6008a331655998569ba7ca23e2ebd2 +size 2719243584 diff --git a/flammen21X-mistral-7B.Q3_K_L.gguf b/flammen21X-mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..53249cb --- /dev/null +++ b/flammen21X-mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604c9383e961556ec4f4196840f387996552d2d4fd93b8a3aee5c17184718fe7 +size 3822026048 diff --git a/flammen21X-mistral-7B.Q3_K_M.gguf b/flammen21X-mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..3ad61c7 --- /dev/null +++ b/flammen21X-mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2820c261eb9a117134769cb921be3df60358307ca686c3cff30e6e127ebd6d2 +size 3518987584 diff --git a/flammen21X-mistral-7B.Q3_K_S.gguf b/flammen21X-mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..cc367c0 --- /dev/null +++ b/flammen21X-mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6edfebb7d3e776f0ff45defa1cbf6fbb44982ec800943e280056ff3f4b5228 +size 3164568896 diff --git a/flammen21X-mistral-7B.Q4_K_M.gguf b/flammen21X-mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..a76ae87 --- /dev/null +++ b/flammen21X-mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af60a2a4ec898bcf391909177d8cd712385207aed42f6f29b5069cb1acd44533 +size 4368440640 diff --git a/flammen21X-mistral-7B.Q4_K_S.gguf b/flammen21X-mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..d6f8928 --- /dev/null +++ b/flammen21X-mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a870d35320960ace524e0ada848278ccdd542eebd0ce96e803bf70954ff367 +size 4140375360 diff --git a/flammen21X-mistral-7B.Q5_K_M.gguf b/flammen21X-mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..92e590e --- /dev/null +++ b/flammen21X-mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0400ed1dab3b9e861231f2b72a7aada0360950506418f13ef2fbdf304a88e3f8 +size 5131410752 diff --git a/flammen21X-mistral-7B.Q5_K_S.gguf b/flammen21X-mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..a7e3b9e --- /dev/null +++ b/flammen21X-mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08010c16b50c820a035845c5b16ea865827c42a55b97d124fcbe8938b0176daf +size 4997717312 diff --git a/flammen21X-mistral-7B.Q6_K.gguf b/flammen21X-mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..8993b01 --- /dev/null +++ b/flammen21X-mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806ef72dd7f6adffd6063c25664badee7a3f8d34ece5380b9a1357821be6c190 +size 5942066496 diff --git a/flammen21X-mistral-7B.Q8_0.gguf b/flammen21X-mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..1e2b9e9 --- /dev/null +++ b/flammen21X-mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d26d202100ff0a67b8684df8115186f09cb2ac9b0d55f3b8a8d537be3853a0 +size 7695859008 diff --git a/flammen21X-mistral-7B.f16.gguf b/flammen21X-mistral-7B.f16.gguf new file mode 100644 index 0000000..729fa0a --- /dev/null +++ b/flammen21X-mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f45883802602524f0b46b19fe0785f9c2e84e8b9784e8f632fad74b66beacd84 +size 14484733248