commit 558b175461a0d6f9623b49a995620d5c2063e735 Author: ModelHub XC Date: Wed May 6 15:10:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Xwin-LM-7B-V0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..944d1ee --- /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 +Xwin-LM-7B-V0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Xwin-LM-7B-V0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3da92c3 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Xwin-LM/Xwin-LM-7B-V0.1 +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-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/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Xwin-LM-7B-V0.1-GGUF/resolve/main/Xwin-LM-7B-V0.1.f16.gguf) | f16 | 13.6 | 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/Xwin-LM-7B-V0.1.IQ4_XS.gguf b/Xwin-LM-7B-V0.1.IQ4_XS.gguf new file mode 100644 index 0000000..6eb4636 --- /dev/null +++ b/Xwin-LM-7B-V0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10e37650250fbbadb24d8e8faa8159fe7a759296f5cc1044165287410eb75a6 +size 3647517248 diff --git a/Xwin-LM-7B-V0.1.Q2_K.gguf b/Xwin-LM-7B-V0.1.Q2_K.gguf new file mode 100644 index 0000000..9f0ca45 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653380ce3a7f400f8cd813bf82ccdcc9a44cae4533945def5736cfba9bedfeb6 +size 2532864576 diff --git a/Xwin-LM-7B-V0.1.Q3_K_L.gguf b/Xwin-LM-7B-V0.1.Q3_K_L.gguf new file mode 100644 index 0000000..5c08fbd --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7037c93d07d8a83ee95c433132249f1bc83ad8b59f851fb3f518bf257b32a829 +size 3597111872 diff --git a/Xwin-LM-7B-V0.1.Q3_K_M.gguf b/Xwin-LM-7B-V0.1.Q3_K_M.gguf new file mode 100644 index 0000000..7723864 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26815c2d8321f90b62905dfaa3ff419c30c513acae26fac4c5070a4de45f4613 +size 3298005568 diff --git a/Xwin-LM-7B-V0.1.Q3_K_S.gguf b/Xwin-LM-7B-V0.1.Q3_K_S.gguf new file mode 100644 index 0000000..4aea886 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab64193c2e56f572fb20083cae8a7cf761479550d415e7ead1ec041a65c9f973 +size 2948305472 diff --git a/Xwin-LM-7B-V0.1.Q4_K_M.gguf b/Xwin-LM-7B-V0.1.Q4_K_M.gguf new file mode 100644 index 0000000..164a35f --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce793c38074bb8fc7fcb8ad835fa2fe836b5a55ed1ac35460e9394665e43ad61 +size 4081005120 diff --git a/Xwin-LM-7B-V0.1.Q4_K_S.gguf b/Xwin-LM-7B-V0.1.Q4_K_S.gguf new file mode 100644 index 0000000..d7667c2 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5280b842a4e0c95cb5294678129ee9bd74eae9e450bd1ff1e71faf9945dacd2b +size 3856740928 diff --git a/Xwin-LM-7B-V0.1.Q5_K_M.gguf b/Xwin-LM-7B-V0.1.Q5_K_M.gguf new file mode 100644 index 0000000..5abae50 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8535ddc76f03d8fec0eae6a12f7757b78ae2e1b4cdd87b00e64d971f1de62ed5 +size 4783157824 diff --git a/Xwin-LM-7B-V0.1.Q5_K_S.gguf b/Xwin-LM-7B-V0.1.Q5_K_S.gguf new file mode 100644 index 0000000..bd50bbb --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a5e3f3cdae1d65c6c9fbf32b7914424e5f0dd1fb0174d3b0c23f4f83991040 +size 4651692608 diff --git a/Xwin-LM-7B-V0.1.Q6_K.gguf b/Xwin-LM-7B-V0.1.Q6_K.gguf new file mode 100644 index 0000000..00fe005 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372914ea902bc309236c4dddbdcae997043b449b1cf00d13d3eb2218e1dac95e +size 5529195072 diff --git a/Xwin-LM-7B-V0.1.Q8_0.gguf b/Xwin-LM-7B-V0.1.Q8_0.gguf new file mode 100644 index 0000000..38ff077 --- /dev/null +++ b/Xwin-LM-7B-V0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1defc74cb0822adb518f9826cc88037dbe13a9033e9882bee8d5968f78267b9c +size 7161090624 diff --git a/Xwin-LM-7B-V0.1.f16.gguf b/Xwin-LM-7B-V0.1.f16.gguf new file mode 100644 index 0000000..df260ed --- /dev/null +++ b/Xwin-LM-7B-V0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421f1aa98bb17a592ceeb8ed4c8dcc95b20d9542a1af3f58f61b38013715420a +size 13478105664