commit 473c14df8b3957908a5209c7b001e40eac01ee86 Author: ModelHub XC Date: Tue Apr 21 17:55:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b695317 --- /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-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-4B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-4B.IQ4_XS.gguf b/Mistral-4B.IQ4_XS.gguf new file mode 100644 index 0000000..4ce7fdb --- /dev/null +++ b/Mistral-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195521d13ed1d6cb358bfb09f02b5bc967c2427117e68c3a45e478a02d1d252f +size 2061139552 diff --git a/Mistral-4B.Q2_K.gguf b/Mistral-4B.Q2_K.gguf new file mode 100644 index 0000000..687a688 --- /dev/null +++ b/Mistral-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88cc276688b1f53762e0227199ca763eb5853399b8263ad19870bba3413cd85 +size 1435254368 diff --git a/Mistral-4B.Q3_K_L.gguf b/Mistral-4B.Q3_K_L.gguf new file mode 100644 index 0000000..2eae509 --- /dev/null +++ b/Mistral-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d701921cbbd3e061e113772f73aed53f5ccdf1a1d71626fd51437f96ade56f2f +size 1993301600 diff --git a/Mistral-4B.Q3_K_M.gguf b/Mistral-4B.Q3_K_M.gguf new file mode 100644 index 0000000..dca1b8a --- /dev/null +++ b/Mistral-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e85161c04514fd4dfd78742ec98b8707b57301f25c5153c3b0b7b33f236194 +size 1842306656 diff --git a/Mistral-4B.Q3_K_S.gguf b/Mistral-4B.Q3_K_S.gguf new file mode 100644 index 0000000..7db1b03 --- /dev/null +++ b/Mistral-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341442a5671b161c77e8f81fcebc50b64a2a26ea51052ec06747d5252ae60f44 +size 1664573024 diff --git a/Mistral-4B.Q4_0_4_4.gguf b/Mistral-4B.Q4_0_4_4.gguf new file mode 100644 index 0000000..0595cd1 --- /dev/null +++ b/Mistral-4B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbdc4fca7c5644ca26f579af07759c28eaca0e5a18634b01865264604754fc86 +size 2145451616 diff --git a/Mistral-4B.Q4_K_M.gguf b/Mistral-4B.Q4_K_M.gguf new file mode 100644 index 0000000..6b6a725 --- /dev/null +++ b/Mistral-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5568fdee32853dfcc668ceee92bf68fc76bb26c643f8b4ccd12c06f797e24898 +size 2275212896 diff --git a/Mistral-4B.Q4_K_S.gguf b/Mistral-4B.Q4_K_S.gguf new file mode 100644 index 0000000..82c7c85 --- /dev/null +++ b/Mistral-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f2df391ea643c6050ba477e73247fc5fb05a1024d668a43f0c112dfbe37161 +size 2162228832 diff --git a/Mistral-4B.Q5_K_M.gguf b/Mistral-4B.Q5_K_M.gguf new file mode 100644 index 0000000..de05307 --- /dev/null +++ b/Mistral-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7d33e2bc757c00c8ffb6f077e34aeccda4c6f01e4b36565995dfe6e5979135 +size 2664889952 diff --git a/Mistral-4B.Q5_K_S.gguf b/Mistral-4B.Q5_K_S.gguf new file mode 100644 index 0000000..4463f41 --- /dev/null +++ b/Mistral-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af056f41012bed2d208ffce27c7f6e26ccb567705f3ed77b6b365111ea8c3a2e +size 2598043232 diff --git a/Mistral-4B.Q6_K.gguf b/Mistral-4B.Q6_K.gguf new file mode 100644 index 0000000..3af33d3 --- /dev/null +++ b/Mistral-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab32c545080a2ef0b28d67826cc41906419079063b98f48fe232d4c3c2f98044 +size 3078921824 diff --git a/Mistral-4B.Q8_0.gguf b/Mistral-4B.Q8_0.gguf new file mode 100644 index 0000000..9654a66 --- /dev/null +++ b/Mistral-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47c696fed58821b51ffd1f5c7deef534118d5ea4ea5cb1726a77878f30a860e +size 3987562080 diff --git a/Mistral-4B.f16.gguf b/Mistral-4B.f16.gguf new file mode 100644 index 0000000..2c4afa6 --- /dev/null +++ b/Mistral-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3eafa3a0deb12366a1ad332710721a99b3fda7935fc6a009329010e7f6236b +size 7504879200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a906d19 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: fhai50032/Mistral-4B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- mistral +- fhai50032/RolePlayLake-7B +- fhai50032/RolePlayLake-7B +- fhai50032/RolePlayLake-7B +- fhai50032/RolePlayLake-7B +- fhai50032/RolePlayLake-7B +- fhai50032/RolePlayLake-7B +--- +## About + + + + + + +static quants of https://huggingface.co/fhai50032/Mistral-4B + + +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/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q3_K_M.gguf) | Q3_K_M | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.Q8_0.gguf) | Q8_0 | 4.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-4B-GGUF/resolve/main/Mistral-4B.f16.gguf) | f16 | 7.6 | 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. + +