commit 3644f3c55eb048626ca5fb4092f1d1b2aa113774 Author: ModelHub XC Date: Wed Jul 22 04:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-UtK-7B-128K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3850ba3 --- /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 +Qwen2-UtK-7B-128K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-UtK-7B-128K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-UtK-7B-128K.IQ4_XS.gguf b/Qwen2-UtK-7B-128K.IQ4_XS.gguf new file mode 100644 index 0000000..095e243 --- /dev/null +++ b/Qwen2-UtK-7B-128K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effed58f957dec54a0760857e569ec55c824b86b280f8ab79b7cb203883ec17a +size 4250296608 diff --git a/Qwen2-UtK-7B-128K.Q2_K.gguf b/Qwen2-UtK-7B-128K.Q2_K.gguf new file mode 100644 index 0000000..73f6d76 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97778ffee4ffa5125f127c95f53bea444f6c8187adb7ce4c86bfda72c5c02532 +size 3015938336 diff --git a/Qwen2-UtK-7B-128K.Q3_K_L.gguf b/Qwen2-UtK-7B-128K.Q3_K_L.gguf new file mode 100644 index 0000000..a741d01 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f036ef288070b32069b2f74fbf986d874eed32d0faa0f70211e35b27ae4b3dd +size 4088457504 diff --git a/Qwen2-UtK-7B-128K.Q3_K_M.gguf b/Qwen2-UtK-7B-128K.Q3_K_M.gguf new file mode 100644 index 0000000..aa6b674 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dbcbb942bbd4d822c04729688ecaad21e666cf45cc1aaee8ba700ac301f965 +size 3808389408 diff --git a/Qwen2-UtK-7B-128K.Q3_K_S.gguf b/Qwen2-UtK-7B-128K.Q3_K_S.gguf new file mode 100644 index 0000000..6e86142 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfae9da56acff7ab5da55c3d1d06b3059a675bff12d17199c1b309347f1f4a15 +size 3492366624 diff --git a/Qwen2-UtK-7B-128K.Q4_K_M.gguf b/Qwen2-UtK-7B-128K.Q4_K_M.gguf new file mode 100644 index 0000000..b85fe2b --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7ee507140409911bafe33a7badc90e167a70ede8726bab599717a2d8ef0da6c +size 4683071776 diff --git a/Qwen2-UtK-7B-128K.Q4_K_S.gguf b/Qwen2-UtK-7B-128K.Q4_K_S.gguf new file mode 100644 index 0000000..64250f3 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0f62f275b7cd11013c94e16b352d213a35866107a1056c108b2a4a2939da74 +size 4457767200 diff --git a/Qwen2-UtK-7B-128K.Q5_K_M.gguf b/Qwen2-UtK-7B-128K.Q5_K_M.gguf new file mode 100644 index 0000000..204c0cf --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2058105f7fecc5ee7e7aeba3eec184decc94dc79e00fd859398d9c62db7ec7a0 +size 5444829472 diff --git a/Qwen2-UtK-7B-128K.Q5_K_S.gguf b/Qwen2-UtK-7B-128K.Q5_K_S.gguf new file mode 100644 index 0000000..dcb5861 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb444c30aea6b21acf60e3f79a6485e07fb457bbaea79c51a4c7f85d62c99be +size 5315174688 diff --git a/Qwen2-UtK-7B-128K.Q6_K.gguf b/Qwen2-UtK-7B-128K.Q6_K.gguf new file mode 100644 index 0000000..5677da5 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6819e5f459c3a233d9836bad1209b9851d4079ff62f170459aee7e930cac41 +size 6254197024 diff --git a/Qwen2-UtK-7B-128K.Q8_0.gguf b/Qwen2-UtK-7B-128K.Q8_0.gguf new file mode 100644 index 0000000..6f7e4c4 --- /dev/null +++ b/Qwen2-UtK-7B-128K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9865777a893f897c7a71b4041be67844ec4cdcf2993c5567dc4b6e2445d06370 +size 8098523424 diff --git a/Qwen2-UtK-7B-128K.f16.gguf b/Qwen2-UtK-7B-128K.f16.gguf new file mode 100644 index 0000000..ef58aca --- /dev/null +++ b/Qwen2-UtK-7B-128K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a8ea495dd491a4bb686c113aeae5aa435e2ef321a92bdaef30c460511d8885 +size 15237851424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79d298d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: rgtjf/Qwen2-UtK-7B-128K +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- base +- 128k +--- +## About + + + + + + +static quants of https://huggingface.co/rgtjf/Qwen2-UtK-7B-128K + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2-UtK-7B-128K-GGUF).*** + +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/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-UtK-7B-128K-GGUF/resolve/main/Qwen2-UtK-7B-128K.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. + +