commit 883d3baaf05de2adb1bd45a5d0e5557501154c5d Author: ModelHub XC Date: Wed Oct 14 07:24:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..affb0ed --- /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 +Mistral-7B-Instruct-v0.2-expanded.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.2-expanded.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.2-expanded.IQ4_XS.gguf b/Mistral-7B-Instruct-v0.2-expanded.IQ4_XS.gguf new file mode 100644 index 0000000..e9f6a88 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b23a109b72cfa2f725f5400eadcf97d1d0c02adb4de86b7a78fd35006f015d +size 4886015264 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q2_K.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q2_K.gguf new file mode 100644 index 0000000..669972b --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c6470fae8db2e41d0ca7fac91018efea8ccc292beb6c0b7b3cf3b649ee7874 +size 3361238304 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q3_K_L.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_L.gguf new file mode 100644 index 0000000..766ce90 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d55162bb8ad4e4a485a257b144d29eda4c01dd551d50f8aabd9d11d2492987c +size 4736388384 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q3_K_M.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_M.gguf new file mode 100644 index 0000000..6b4bbb8 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f5a2530f10bb7e32a6323eb5acc3f1ab0d7165810d70bf7cde448fd866eb53 +size 4353658144 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q3_K_S.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_S.gguf new file mode 100644 index 0000000..2f1a314 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b91ad0b3b7c1df1cd75af92891fd158960e3d897baa45c048792d7772ebf40f +size 3914566944 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q4_0_4_4.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q4_0_4_4.gguf new file mode 100644 index 0000000..b5b318d --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdc8db019b3905ef5f4515fe29b3c57da295ab17d266741b0e4477e0748df9b +size 5090651424 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q4_K_M.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q4_K_M.gguf new file mode 100644 index 0000000..9656141 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a93af42fb2602d34c22205eb224f50cc1c7df893a48b820dfe13112862f0ed6 +size 5415054624 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q4_K_S.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q4_K_S.gguf new file mode 100644 index 0000000..fd75bcc --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f153dd7d03013582604ff42d0cc5b17d8c6fae7ca9b17768115218a9b8fe41 +size 5129448736 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q5_K_M.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q5_K_M.gguf new file mode 100644 index 0000000..c710ad7 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc076845b7a7d94dd0e1a8e8eb4ec31e053e12b7d99c72c7c8970e9f7906a8d +size 6364671264 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q5_K_S.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q5_K_S.gguf new file mode 100644 index 0000000..977c131 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfe0ac5f741c1e0b266eb8180e1ab169905bd54513f660d6bbd5e5b21f23c38 +size 6197554464 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q6_K.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q6_K.gguf new file mode 100644 index 0000000..d0f1c1d --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731d288097514d8d0ca0abe3da3613401365a48f699218ddf66959309fe9073f +size 7373638944 diff --git a/Mistral-7B-Instruct-v0.2-expanded.Q8_0.gguf b/Mistral-7B-Instruct-v0.2-expanded.Q8_0.gguf new file mode 100644 index 0000000..35f41cd --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada0d2a786f27ccc1fbb4d040189252b9c8b13de8de7d61ed08e7aaac393c5b2 +size 9550007584 diff --git a/Mistral-7B-Instruct-v0.2-expanded.f16.gguf b/Mistral-7B-Instruct-v0.2-expanded.f16.gguf new file mode 100644 index 0000000..5d2a43a --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-expanded.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f9724e5ba8d2cfa940cb32b77a1c4dff317d8f7756bedb39324a6892e0df23 +size 17974660384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1c548a --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: arcee-ai/Mistral-7B-Instruct-v0.2-expanded +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- block expansion +- progressive mistral +- arcee cpt +--- +## About + + + + + + +static quants of https://huggingface.co/arcee-ai/Mistral-7B-Instruct-v0.2-expanded + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-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/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.IQ4_XS.gguf) | IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q5_K_S.gguf) | Q5_K_S | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q5_K_M.gguf) | Q5_K_M | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q6_K.gguf) | Q6_K | 7.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.Q8_0.gguf) | Q8_0 | 9.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Instruct-v0.2-expanded-GGUF/resolve/main/Mistral-7B-Instruct-v0.2-expanded.f16.gguf) | f16 | 18.1 | 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. + +