commit f8ca397bd8e4c728be6627690a97a661bdbfcedd Author: ModelHub XC Date: Tue Jun 2 06:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b6df72 --- /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 +Mistral-7B-v0.3-Middo-Wizard.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-v0.3-Middo-Wizard.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-v0.3-Middo-Wizard.IQ4_XS.gguf b/Mistral-7B-v0.3-Middo-Wizard.IQ4_XS.gguf new file mode 100644 index 0000000..855928d --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc53a5571b03dd22e85d0e93a888b943d4a6e4d3ee88c042dee51ca4dffea3a +size 3948664288 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q2_K.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q2_K.gguf new file mode 100644 index 0000000..3c376a1 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323c002d679d5b426a097c59090047532e577bb3582d1fee9cbfd48bf67e8a65 +size 2722878944 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q3_K_L.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_L.gguf new file mode 100644 index 0000000..ad89468 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182b3bba9a404d9a699e33e81f9de9c382110e43072f98051c0e553e7ac8d3f4 +size 3825980896 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q3_K_M.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_M.gguf new file mode 100644 index 0000000..fa5380e --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaeeb4e5c9eaaa56fe03c92e9f41d863a36c4764333520b5547d94eb6e89b2a7 +size 3522942432 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q3_K_S.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_S.gguf new file mode 100644 index 0000000..9d795fc --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c31223383e4b726d3b34c2e6a4c83a369b12f3ea8873d3a3a25ef19a1a2e7c7 +size 3168523744 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q4_K_M.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q4_K_M.gguf new file mode 100644 index 0000000..16afb38 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d07aab521c7fd7fe378b08521823a0e273b217fd7af87dcaedfba5467ee208 +size 4372813280 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q4_K_S.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q4_K_S.gguf new file mode 100644 index 0000000..c256299 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2c2e07c5c0e99211e793fbdc748b316ba099dab8ab560e0a1f3b23bca69c24 +size 4144748000 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q5_K_M.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q5_K_M.gguf new file mode 100644 index 0000000..fd9e829 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a3b94473d4f28d690e4bdd27cb03b106a488a3f83e88b0854b777d34161f2f +size 5136176608 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q5_K_S.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q5_K_S.gguf new file mode 100644 index 0000000..1cd8e17 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc15662c90b160b87f9a3c24683eab73245265ca227ebe8e1a714afc1fa88be +size 5002483168 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q6_K.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q6_K.gguf new file mode 100644 index 0000000..34e301a --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172775be9c115798fdf67734aae880777b31f699cb72669e17826855f3744123 +size 5947250144 diff --git a/Mistral-7B-v0.3-Middo-Wizard.Q8_0.gguf b/Mistral-7B-v0.3-Middo-Wizard.Q8_0.gguf new file mode 100644 index 0000000..27f1358 --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10277c12aab9556ec832535d1d60f222104bbf878ab9fa93ecca74c438211a1d +size 7702566368 diff --git a/Mistral-7B-v0.3-Middo-Wizard.f16.gguf b/Mistral-7B-v0.3-Middo-Wizard.f16.gguf new file mode 100644 index 0000000..58d4b4c --- /dev/null +++ b/Mistral-7B-v0.3-Middo-Wizard.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a41044eb48d114f8fa5efb0ae9dd7cd3d80ea6038487f9b20ef27cd5b597821 +size 14497338848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4721620 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Word2Li/Mistral-7B-v0.3-Middo-Wizard +datasets: +- Word2Li/MiddOptimized +language: en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Word2Li/Mistral-7B-v0.3-Middo-Wizard + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-v0.3-Middo-Wizard-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-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-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-v0.3-Middo-Wizard-GGUF/resolve/main/Mistral-7B-v0.3-Middo-Wizard.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. + +