commit 97d4fae42dc062f9e640ba41cbc803d45c5baaac Author: ModelHub XC Date: Mon Sep 28 09:51:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/flammen14-mistral-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..adc5618 --- /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 +flammen14-mistral-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-mistral-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +flammen14-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..bd51471 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: flammenai/flammen14-mistral-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/flammenai/flammen14-mistral-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#flammen14-mistral-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/flammen14-mistral-7B-i1-GGUF +## 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/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-mistral-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/flammen14-mistral-7B-GGUF/resolve/main/flammen14-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/flammen14-mistral-7B.IQ4_XS.gguf b/flammen14-mistral-7B.IQ4_XS.gguf new file mode 100644 index 0000000..b28a857 --- /dev/null +++ b/flammen14-mistral-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3673a336a9a265d21c9f2d720e2cb5e469716d980d85b3fe835628fcc5241a69 +size 3944389664 diff --git a/flammen14-mistral-7B.Q2_K.gguf b/flammen14-mistral-7B.Q2_K.gguf new file mode 100644 index 0000000..8fa1037 --- /dev/null +++ b/flammen14-mistral-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b37e3871fe67e140e92cabf62f3b52053d01e157cbffe881483736644a7fdd69 +size 2719243296 diff --git a/flammen14-mistral-7B.Q3_K_L.gguf b/flammen14-mistral-7B.Q3_K_L.gguf new file mode 100644 index 0000000..4b541e4 --- /dev/null +++ b/flammen14-mistral-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1e69578d76045fa1f6b8e96cb30ac5e85774118225e3ccc3c528fd7009495a +size 3822025760 diff --git a/flammen14-mistral-7B.Q3_K_M.gguf b/flammen14-mistral-7B.Q3_K_M.gguf new file mode 100644 index 0000000..8ec5be8 --- /dev/null +++ b/flammen14-mistral-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da70170c0b4a1ea2e36feb7082b50f85b086c375e7118dc5b19180d03ddb164 +size 3518987296 diff --git a/flammen14-mistral-7B.Q3_K_S.gguf b/flammen14-mistral-7B.Q3_K_S.gguf new file mode 100644 index 0000000..767bf4a --- /dev/null +++ b/flammen14-mistral-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f298498f866cda2219b9a6e376319fec61a6efde85ebe8e6d503b05459ddea +size 3164568608 diff --git a/flammen14-mistral-7B.Q4_K_M.gguf b/flammen14-mistral-7B.Q4_K_M.gguf new file mode 100644 index 0000000..6010f58 --- /dev/null +++ b/flammen14-mistral-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a460a4ade2ec0cd3052402bcbad17718d0f58cb0f60416899dfe969efffdea +size 4368440352 diff --git a/flammen14-mistral-7B.Q4_K_S.gguf b/flammen14-mistral-7B.Q4_K_S.gguf new file mode 100644 index 0000000..34de788 --- /dev/null +++ b/flammen14-mistral-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35575d2a4de7da619f3045dcca8da203320c7d12bc9a552c2de5b0d4e138547 +size 4140375072 diff --git a/flammen14-mistral-7B.Q5_K_M.gguf b/flammen14-mistral-7B.Q5_K_M.gguf new file mode 100644 index 0000000..c693491 --- /dev/null +++ b/flammen14-mistral-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c19dd93d4a13772d2374cb69c48ac9396534af5d86dff1177f226df45270405 +size 5131410464 diff --git a/flammen14-mistral-7B.Q5_K_S.gguf b/flammen14-mistral-7B.Q5_K_S.gguf new file mode 100644 index 0000000..3637597 --- /dev/null +++ b/flammen14-mistral-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a65df0750b614ebe06f8f151960178fb9c1dbe2d263b90a3865003fb0a0ebf1 +size 4997717024 diff --git a/flammen14-mistral-7B.Q6_K.gguf b/flammen14-mistral-7B.Q6_K.gguf new file mode 100644 index 0000000..60cbab2 --- /dev/null +++ b/flammen14-mistral-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc287a1cedb3c84d08be9ab6415c17f0465c475fccec4a4bae6fce4593327dc5 +size 5942066208 diff --git a/flammen14-mistral-7B.Q8_0.gguf b/flammen14-mistral-7B.Q8_0.gguf new file mode 100644 index 0000000..9e0e9b1 --- /dev/null +++ b/flammen14-mistral-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f4e135862b9547d45746f13c9e722c14061cfc16c61e14df229329691e31f93 +size 7695858720 diff --git a/flammen14-mistral-7B.f16.gguf b/flammen14-mistral-7B.f16.gguf new file mode 100644 index 0000000..9a6f64c --- /dev/null +++ b/flammen14-mistral-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221236a8f0641ca022c416c5a4c088ec815b8148b7e1d3081b29df7eb8eca1c0 +size 14484732960