commit 4e0348c4c2f00e2a77907c15b20859d4a3b0968e Author: ModelHub XC Date: Fri May 8 09:56:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b10dbf2 --- /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 +Qwen-7B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7B-Chat.IQ4_XS.gguf b/Qwen-7B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..fb9087c --- /dev/null +++ b/Qwen-7B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:590993fd0ded80f231b1ea9137667d4d4727503684afa3be927922d9d4c83c5b +size 4318258656 diff --git a/Qwen-7B-Chat.Q2_K.gguf b/Qwen-7B-Chat.Q2_K.gguf new file mode 100644 index 0000000..f10fd63 --- /dev/null +++ b/Qwen-7B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7e9e76bcf35080a2454dcb1980f551b6549630cc2071e77c358eb74cee1911 +size 3049293280 diff --git a/Qwen-7B-Chat.Q3_K_L.gguf b/Qwen-7B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..b28776c --- /dev/null +++ b/Qwen-7B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed329a1819ff1045af19d3f36ba2dad11047e898f67d0e3d8d2ec49f6ef88b5 +size 4293457376 diff --git a/Qwen-7B-Chat.Q3_K_M.gguf b/Qwen-7B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..aed089c --- /dev/null +++ b/Qwen-7B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b66a04213ef2fe9e8ef8d0d4585375e1cd228a073b974c9ca23c76d7f160f8d +size 4057265632 diff --git a/Qwen-7B-Chat.Q3_K_S.gguf b/Qwen-7B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..7bd0f59 --- /dev/null +++ b/Qwen-7B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80806e7ce9d9a57d0cfd06be430666da64e031bb9eefd939297e33567dae710 +size 3569153504 diff --git a/Qwen-7B-Chat.Q4_K_M.gguf b/Qwen-7B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..0a0d867 --- /dev/null +++ b/Qwen-7B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc841aa7b33e3bb010bc39c1dad1eb01bc6f2328e5a11c0b28dabf3d049021ea +size 4899218912 diff --git a/Qwen-7B-Chat.Q4_K_S.gguf b/Qwen-7B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..f90fad1 --- /dev/null +++ b/Qwen-7B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3024cbcb258c16188aa937fcdd8aa00efcea65afa165590be6024b72f1bc5dbb +size 4534445536 diff --git a/Qwen-7B-Chat.Q5_K_M.gguf b/Qwen-7B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..1496031 --- /dev/null +++ b/Qwen-7B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46b78654d0e76aea35110054970b8b2f632650e7a2ab043e1dc63935044a350 +size 5708916192 diff --git a/Qwen-7B-Chat.Q5_K_S.gguf b/Qwen-7B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..6ba3825 --- /dev/null +++ b/Qwen-7B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731cfd130579cbb29be6741964b11ea597d74a1b4ff792769d96fe5e933abb2c +size 5399193056 diff --git a/Qwen-7B-Chat.Q6_K.gguf b/Qwen-7B-Chat.Q6_K.gguf new file mode 100644 index 0000000..3f7396b --- /dev/null +++ b/Qwen-7B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c446a4f4d3bd803ed8907a64f68a5943b6728e9c3fc01faf6ecacc4398ae1014 +size 6341940704 diff --git a/Qwen-7B-Chat.Q8_0.gguf b/Qwen-7B-Chat.Q8_0.gguf new file mode 100644 index 0000000..2a8137d --- /dev/null +++ b/Qwen-7B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a1c4ffa4bcf2499d77a102785d79403d4fa8aa8bc299766f8e82b99b4a2263 +size 8211789280 diff --git a/Qwen-7B-Chat.f16.gguf b/Qwen-7B-Chat.f16.gguf new file mode 100644 index 0000000..ad1335f --- /dev/null +++ b/Qwen-7B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f45c9bb46de96b4ccd25f1e6dcd6aa6ac2adfb214ae495fe36445cfaaf86e9 +size 15449912800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..35e3cf3 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Qwen/Qwen-7B-Chat +language: +- zh +- en +library_name: transformers +license: other +license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT +license_name: tongyi-qianwen-license-agreement +quantized_by: mradermacher +tags: +- qwen +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen-7B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-7B-Chat-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/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-GGUF/resolve/main/Qwen-7B-Chat.f16.gguf) | f16 | 15.5 | 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. + +