commit ef544f67517ec17b8cb8200d4e6705427fbbce72 Author: ModelHub XC Date: Thu Jul 16 15:03:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MindChat-Qwen2-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce8b5c9 --- /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 +MindChat-Qwen2-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MindChat-Qwen2-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MindChat-Qwen2-4B.IQ4_XS.gguf b/MindChat-Qwen2-4B.IQ4_XS.gguf new file mode 100644 index 0000000..49b9fd5 --- /dev/null +++ b/MindChat-Qwen2-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93aaa52a2585394dc91e5efbad3130f5d0a54d6b1367e5190fe60ee8641acb7a +size 2232632032 diff --git a/MindChat-Qwen2-4B.Q2_K.gguf b/MindChat-Qwen2-4B.Q2_K.gguf new file mode 100644 index 0000000..6ef4c56 --- /dev/null +++ b/MindChat-Qwen2-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a92cc21d66a70b2001203d7f4995286a6c2ec839caca98774563e84bcc6d6d5 +size 1620633312 diff --git a/MindChat-Qwen2-4B.Q3_K_L.gguf b/MindChat-Qwen2-4B.Q3_K_L.gguf new file mode 100644 index 0000000..c3679bf --- /dev/null +++ b/MindChat-Qwen2-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fed331af54b5828314848a375251d593adce41e4b68acbf9ec990a2b39167bd +size 2174799072 diff --git a/MindChat-Qwen2-4B.Q3_K_M.gguf b/MindChat-Qwen2-4B.Q3_K_M.gguf new file mode 100644 index 0000000..9f945a5 --- /dev/null +++ b/MindChat-Qwen2-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf0e2b2cb414f99743c1221ab499ecfc8a2526c5551a0adbef43d8748e9ff91 +size 2026851552 diff --git a/MindChat-Qwen2-4B.Q3_K_S.gguf b/MindChat-Qwen2-4B.Q3_K_S.gguf new file mode 100644 index 0000000..bf5ae58 --- /dev/null +++ b/MindChat-Qwen2-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65119b072df6ce5a3f41e5c939b3472e14d71f16a3bb0ef9dced4867bc0b51f8 +size 1857154272 diff --git a/MindChat-Qwen2-4B.Q4_K_M.gguf b/MindChat-Qwen2-4B.Q4_K_M.gguf new file mode 100644 index 0000000..e74e3ee --- /dev/null +++ b/MindChat-Qwen2-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee6ee9cdbe90aa7c1e1c4ff5bfb55d49a80751e0c49a3570242302d166a89c1 +size 2455116512 diff --git a/MindChat-Qwen2-4B.Q4_K_S.gguf b/MindChat-Qwen2-4B.Q4_K_S.gguf new file mode 100644 index 0000000..04e75c1 --- /dev/null +++ b/MindChat-Qwen2-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba93cad885bd002328b34f9c819afb41a31f00430e181c9a2f46e5a627ec29af +size 2344422112 diff --git a/MindChat-Qwen2-4B.Q5_K_M.gguf b/MindChat-Qwen2-4B.Q5_K_M.gguf new file mode 100644 index 0000000..036ef8b --- /dev/null +++ b/MindChat-Qwen2-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f30a86ccc9c4870bf555ade434c708cb024a8d1d2dff91330943a1b156c1ae +size 2839608032 diff --git a/MindChat-Qwen2-4B.Q5_K_S.gguf b/MindChat-Qwen2-4B.Q5_K_S.gguf new file mode 100644 index 0000000..35aae81 --- /dev/null +++ b/MindChat-Qwen2-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1e0e04ea001a32cfdbe9cb7c63adf111c95a45ac977035bb3226b7fc538267 +size 2775198432 diff --git a/MindChat-Qwen2-4B.Q6_K.gguf b/MindChat-Qwen2-4B.Q6_K.gguf new file mode 100644 index 0000000..a585a7d --- /dev/null +++ b/MindChat-Qwen2-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80014acd74f1118d32b192d976df15dfc60cf879de84aa446d00fc03ebae5702 +size 3248130272 diff --git a/MindChat-Qwen2-4B.Q8_0.gguf b/MindChat-Qwen2-4B.Q8_0.gguf new file mode 100644 index 0000000..07c4b07 --- /dev/null +++ b/MindChat-Qwen2-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c56dfd23bc0cfa3a4b90e298d2a9279a788f2046438478ae7d52778014399f +size 4204735712 diff --git a/MindChat-Qwen2-4B.f16.gguf b/MindChat-Qwen2-4B.f16.gguf new file mode 100644 index 0000000..f8840c5 --- /dev/null +++ b/MindChat-Qwen2-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35b63f0e5b1a25f3320d518492f780cf072b30fccb120b2c1a702e5de375f076 +size 7907724512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a07ce1 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: X-D-Lab/MindChat-Qwen2-4B +language: +- zh +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/X-D-Lab/MindChat-Qwen2-4B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MindChat-Qwen2-4B-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/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MindChat-Qwen2-4B-GGUF/resolve/main/MindChat-Qwen2-4B.f16.gguf) | f16 | 8.0 | 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. + +