commit 6f7ffeb945d04c912034992bce77b104594727f8 Author: ModelHub XC Date: Mon Apr 20 15:41:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/docsgpt-7b-mistral-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b2c9a96 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +docsgpt-7b-mistral.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.f16.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +docsgpt-7b-mistral.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1a7d32 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Arc53/docsgpt-7b-mistral +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- rag +- closed-qa +- context +- mistral +--- +## About + + + + + + +static quants of https://huggingface.co/Arc53/docsgpt-7b-mistral + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/docsgpt-7b-mistral-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/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/docsgpt-7b-mistral-GGUF/resolve/main/docsgpt-7b-mistral.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/docsgpt-7b-mistral.IQ4_XS.gguf b/docsgpt-7b-mistral.IQ4_XS.gguf new file mode 100644 index 0000000..18a0170 --- /dev/null +++ b/docsgpt-7b-mistral.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49377ad78d1542816fd61563bf5561e823c8da1fba774a278cadeaf4726cffc1 +size 3944389696 diff --git a/docsgpt-7b-mistral.Q2_K.gguf b/docsgpt-7b-mistral.Q2_K.gguf new file mode 100644 index 0000000..402c37d --- /dev/null +++ b/docsgpt-7b-mistral.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5c37088a011c0c14eddbbf164402b20f6e54dcbdfd016e34ab7e27605cf52e +size 2719243328 diff --git a/docsgpt-7b-mistral.Q3_K_L.gguf b/docsgpt-7b-mistral.Q3_K_L.gguf new file mode 100644 index 0000000..64b6054 --- /dev/null +++ b/docsgpt-7b-mistral.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a64f9bfa6c27becfe77d4e86e1709728a2a931c4294fe8c6eaace1b342f526 +size 3822025792 diff --git a/docsgpt-7b-mistral.Q3_K_M.gguf b/docsgpt-7b-mistral.Q3_K_M.gguf new file mode 100644 index 0000000..9a3395b --- /dev/null +++ b/docsgpt-7b-mistral.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09271f8e30a65dce20365a0ac9e94ee7ad81fc20fcf50e5edb343c8054cdd081 +size 3518987328 diff --git a/docsgpt-7b-mistral.Q3_K_S.gguf b/docsgpt-7b-mistral.Q3_K_S.gguf new file mode 100644 index 0000000..ddb36a0 --- /dev/null +++ b/docsgpt-7b-mistral.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6186bb738d2562301111ad9ca07cc48bdfe43fbf3f74bc8791c4ff3c57b2a52a +size 3164568640 diff --git a/docsgpt-7b-mistral.Q4_0_4_4.gguf b/docsgpt-7b-mistral.Q4_0_4_4.gguf new file mode 100644 index 0000000..2aed137 --- /dev/null +++ b/docsgpt-7b-mistral.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a999ae44e21f983e123243d746593914918a9e3e5fb0f3346263a279d93e7321 +size 4108917824 diff --git a/docsgpt-7b-mistral.Q4_K_M.gguf b/docsgpt-7b-mistral.Q4_K_M.gguf new file mode 100644 index 0000000..7fdde4f --- /dev/null +++ b/docsgpt-7b-mistral.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9962464a3b32705af25e253810b45335203425d94840df267ffd2941a6edd7ac +size 4368440384 diff --git a/docsgpt-7b-mistral.Q4_K_S.gguf b/docsgpt-7b-mistral.Q4_K_S.gguf new file mode 100644 index 0000000..6e2af96 --- /dev/null +++ b/docsgpt-7b-mistral.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb0ac70bc28bff14dc0366d9f74fda8acf82e2111fdaa16ff24340a60933b07 +size 4140375104 diff --git a/docsgpt-7b-mistral.Q5_K_M.gguf b/docsgpt-7b-mistral.Q5_K_M.gguf new file mode 100644 index 0000000..1e07464 --- /dev/null +++ b/docsgpt-7b-mistral.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b690df8a5b813994ca745f898a1f71feadb0cb96ac4e958518e0492c5b8281 +size 5131410496 diff --git a/docsgpt-7b-mistral.Q5_K_S.gguf b/docsgpt-7b-mistral.Q5_K_S.gguf new file mode 100644 index 0000000..7effd4b --- /dev/null +++ b/docsgpt-7b-mistral.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043848c203b549e79b45145379b87fd94be6d0ed4475caf3dbf8a70bcd612dee +size 4997717056 diff --git a/docsgpt-7b-mistral.Q6_K.gguf b/docsgpt-7b-mistral.Q6_K.gguf new file mode 100644 index 0000000..e18e205 --- /dev/null +++ b/docsgpt-7b-mistral.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe0afdd44d8707f6448c5b8a3359d74304aee500d38209dfe51c4d57b9c0a1d +size 5942066240 diff --git a/docsgpt-7b-mistral.Q8_0.gguf b/docsgpt-7b-mistral.Q8_0.gguf new file mode 100644 index 0000000..02f18a5 --- /dev/null +++ b/docsgpt-7b-mistral.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0586b09c43034559a5d1ee3fbd550f9591db42ed72dfc7dbc64038c57a989617 +size 7695858752 diff --git a/docsgpt-7b-mistral.f16.gguf b/docsgpt-7b-mistral.f16.gguf new file mode 100644 index 0000000..9ef59b1 --- /dev/null +++ b/docsgpt-7b-mistral.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73517e2229469b3e4ae8e2dc4260c1575e287e3753708ef4eea9c8e9dbbbb092 +size 14484732992