commit 4ee80e29183307f7993493ecce5f4210efee3db8 Author: ModelHub XC Date: Tue Jun 2 17:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..df10621 --- /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 +HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumorReject-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..ad2f9af --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf974c58f62f6634d81c1f6fd763b1b04e6d58a13f26c7fbe17261ce2d5c2c4b +size 3944389856 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q2_K.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..9c9510d --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499c541567458d1576d2664970dbf9761ea585f04c5a954aac4a207c299c7f6d +size 2719243488 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..a769cd8 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475d4f9dc1c392dc0818acdaadf03fbcf71b55ddcc453c4ed6bbff5ed233ba94 +size 3822025952 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..e6b5a22 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec5da42d971fe8f06a7a02f3c7e1fc88e98d77d0d51848154e8667c92a29452 +size 3518987488 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..4357bc1 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733668f8e06ffb62f99cb161dd82d4b00c171d9eba23de4eb03e33249bf7c88e +size 3164568800 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..3b5371f --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab513d738d1bb41b83e26bc7c8ee4b22c4608d40e76103ee93906438654b615 +size 4368440544 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..922e359 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda8dc292f98b982a951a39fe2f8701902d0d55c7ac5dea2e7332b7009692a98 +size 4140375264 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..6540cac --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a928575a2ec37ddac051235f34a1452a7d6374f74ea1e1c86a493aa198d7bdd6 +size 5131410656 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..daa7632 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003c1246c248182a9ea875b02eb67e4bde7bf11c1731770141d4ac2d7ac25cf5 +size 4997717216 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q6_K.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..9f26c34 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9bf0bfb5e92446942375584f9a07fb094d2960cc9a1bc42bc12047fe111f36 +size 5942066400 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.Q8_0.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..4229abc --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0916155a12b30693d31ca19722b84e5f5e723cc788009cd48f6fe22626a4d0dd +size 7695858912 diff --git a/HumorReject-Mistral-7B-Instruct-v0.1.f16.gguf b/HumorReject-Mistral-7B-Instruct-v0.1.f16.gguf new file mode 100644 index 0000000..77a16e2 --- /dev/null +++ b/HumorReject-Mistral-7B-Instruct-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f7909e309dde08bc8d70ed227658f4ddcfaaf838e93413d9dfd86ccad497f8 +size 14484733152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3febc90 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: hui98/HumorReject-Mistral-7B-Instruct-v0.1 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/hui98/HumorReject-Mistral-7B-Instruct-v0.1 + + +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/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HumorReject-Mistral-7B-Instruct-v0.1-GGUF/resolve/main/HumorReject-Mistral-7B-Instruct-v0.1.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. + +