commit ce0522b7a3adeecd72748b1c7fb7eb54fbda6154 Author: ModelHub XC Date: Sun May 24 19:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Impish_QWEN_7B-1M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27349ba --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Impish_QWEN_7B-1M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.f16.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Impish_QWEN_7B-1M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Impish_QWEN_7B-1M.IQ4_XS.gguf b/Impish_QWEN_7B-1M.IQ4_XS.gguf new file mode 100644 index 0000000..9904c4c --- /dev/null +++ b/Impish_QWEN_7B-1M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ae583c099347f25d4e220976d23197d192fb81272792ad67781b7407cfcd9e +size 4250296928 diff --git a/Impish_QWEN_7B-1M.Q2_K.gguf b/Impish_QWEN_7B-1M.Q2_K.gguf new file mode 100644 index 0000000..5e6b83c --- /dev/null +++ b/Impish_QWEN_7B-1M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb9acb11d392ac1dd0009094bf960d0c9c6bd1e3391590423650c2938195197 +size 3015938656 diff --git a/Impish_QWEN_7B-1M.Q3_K_L.gguf b/Impish_QWEN_7B-1M.Q3_K_L.gguf new file mode 100644 index 0000000..d5e462b --- /dev/null +++ b/Impish_QWEN_7B-1M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1a76030657f42bfaaeb8bbf61273f0fee6f084fcf40e3a581dd8b7a4e88a20 +size 4088457824 diff --git a/Impish_QWEN_7B-1M.Q3_K_M.gguf b/Impish_QWEN_7B-1M.Q3_K_M.gguf new file mode 100644 index 0000000..1d84bd3 --- /dev/null +++ b/Impish_QWEN_7B-1M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166b51caadc715acae88bdeade6e653a50bbf8cdc3d3ed04c56e4d66a9fc26b0 +size 3808389728 diff --git a/Impish_QWEN_7B-1M.Q3_K_S.gguf b/Impish_QWEN_7B-1M.Q3_K_S.gguf new file mode 100644 index 0000000..d0a661c --- /dev/null +++ b/Impish_QWEN_7B-1M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7fc872a9376474e2fcda78465461b77a9a9b48c91a0dc66e11643f8bb42f6a8 +size 3492366944 diff --git a/Impish_QWEN_7B-1M.Q4_K_M.gguf b/Impish_QWEN_7B-1M.Q4_K_M.gguf new file mode 100644 index 0000000..53b775b --- /dev/null +++ b/Impish_QWEN_7B-1M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcfb119829aae279e5cde0f8f608b11fdab96055f5d2b1be70bd2177f67f911 +size 4683072096 diff --git a/Impish_QWEN_7B-1M.Q4_K_S.gguf b/Impish_QWEN_7B-1M.Q4_K_S.gguf new file mode 100644 index 0000000..30ccd08 --- /dev/null +++ b/Impish_QWEN_7B-1M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c9562aab5de88e42fdd273577da92c245ed7df7d9cd357cfadc5aafec6d10a +size 4457767520 diff --git a/Impish_QWEN_7B-1M.Q5_K_M.gguf b/Impish_QWEN_7B-1M.Q5_K_M.gguf new file mode 100644 index 0000000..625d246 --- /dev/null +++ b/Impish_QWEN_7B-1M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16cda76af378fde9c19d1ff6a98df09536760bef01de6f06f22cea69a6f82802 +size 5444829792 diff --git a/Impish_QWEN_7B-1M.Q5_K_S.gguf b/Impish_QWEN_7B-1M.Q5_K_S.gguf new file mode 100644 index 0000000..e5c206a --- /dev/null +++ b/Impish_QWEN_7B-1M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e981ab4227cb449908aacb8f13b57544ba099f3fe57a3e0798fb17c64e9a79e +size 5315175008 diff --git a/Impish_QWEN_7B-1M.Q6_K.gguf b/Impish_QWEN_7B-1M.Q6_K.gguf new file mode 100644 index 0000000..8efb42e --- /dev/null +++ b/Impish_QWEN_7B-1M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf7c62cc38256ec45ca39c9a7494e4996b506a21710da86647745aee56179c6 +size 6254197344 diff --git a/Impish_QWEN_7B-1M.Q8_0.gguf b/Impish_QWEN_7B-1M.Q8_0.gguf new file mode 100644 index 0000000..59adf27 --- /dev/null +++ b/Impish_QWEN_7B-1M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ec50854255133c6421a8875ea4cd4f70af29df1a9ca52bef2f4c06e6ac5fcc +size 8098523744 diff --git a/Impish_QWEN_7B-1M.f16.gguf b/Impish_QWEN_7B-1M.f16.gguf new file mode 100644 index 0000000..ec4c51e --- /dev/null +++ b/Impish_QWEN_7B-1M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aba5dfeb4140ea551e53f003d1e3e8b492d6c801e9050e368b6ce8c0df05e7d +size 15237851744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..39ae1fa --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: SicariusSicariiStuff/Impish_QWEN_7B-1M +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_7B-1M + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-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/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Impish_QWEN_7B-1M-GGUF/resolve/main/Impish_QWEN_7B-1M.f16.gguf) | f16 | 15.3 | 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. + +