commit d4357b7a61e3c8cd1193763f6f13f8173d60f6c2 Author: ModelHub XC Date: Sun Sep 6 21:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ba1cda --- /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 +Qwen2-7B-Instruct-it-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-it-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-Instruct-it-v1.1.IQ4_XS.gguf b/Qwen2-7B-Instruct-it-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..439bf2a --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef1d2e3fd0f9fc6be7a92e62f36497bd613afeb24718a52f38810d40632fd73 +size 4250297088 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q2_K.gguf b/Qwen2-7B-Instruct-it-v1.1.Q2_K.gguf new file mode 100644 index 0000000..f46afd5 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cbb9150bfd3f35e3424e20c7f42f2450e3f92c5bf6b8cb524de32d21342a8e +size 3015938816 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q3_K_L.gguf b/Qwen2-7B-Instruct-it-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..8a68ac8 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c31fe7c49b61d8a0400198bb3b2a257237dd54a8e45d77f595c5ea3cb481c8 +size 4088457984 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q3_K_M.gguf b/Qwen2-7B-Instruct-it-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..2e49aaf --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7954cb30221cc3a736bf8fedc0e29c5d6e38d21053f4e64c0710aa6ff393cc4d +size 3808389888 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q3_K_S.gguf b/Qwen2-7B-Instruct-it-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..8d39c96 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408efc5075755606d9f46cf48dee500aedfc79787cc1dd260cb3bf9b63896de7 +size 3492367104 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q4_K_M.gguf b/Qwen2-7B-Instruct-it-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..a079710 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86809323222eb06237846ebdf960d540bc3c54e8fe2acd6f4df67548c568882 +size 4683072256 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q4_K_S.gguf b/Qwen2-7B-Instruct-it-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..80142c4 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7692ae27bfcd9736b31b0bf894ed749d0a75a304cae2ef94f40b8bbfc56324b2 +size 4457767680 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q5_K_M.gguf b/Qwen2-7B-Instruct-it-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..00f605e --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85831a44b25eb6f36774af860f4cce71cedf9700f67ead16456aeccbae81991 +size 5444829952 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q5_K_S.gguf b/Qwen2-7B-Instruct-it-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..8d01d24 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986f48ee65cfe14b47e7641db0e50176f90b6df0276001fb575617dbbaf246ad +size 5315175168 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q6_K.gguf b/Qwen2-7B-Instruct-it-v1.1.Q6_K.gguf new file mode 100644 index 0000000..1640dba --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f343792057c3bb1ef8ba6efafd1c1cab0f976255932a47ad8f0c2263aa43a2d0 +size 6254197504 diff --git a/Qwen2-7B-Instruct-it-v1.1.Q8_0.gguf b/Qwen2-7B-Instruct-it-v1.1.Q8_0.gguf new file mode 100644 index 0000000..4a63e56 --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8264fda0ccb7535dc47094757ab55a20960a8d6c4322dc1ba750db2b2ab2203 +size 8098523904 diff --git a/Qwen2-7B-Instruct-it-v1.1.f16.gguf b/Qwen2-7B-Instruct-it-v1.1.f16.gguf new file mode 100644 index 0000000..fd298fd --- /dev/null +++ b/Qwen2-7B-Instruct-it-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e7cec7b4f89bdfe272bc38fa09c67a56cd94e99002b9d0a3c4f4b88de4101d +size 15237851904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7e831a9 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: homeb82784/Qwen2-7B-Instruct-it-v1.1 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- krx +--- +## About + + + + + + +static quants of https://huggingface.co/homeb82784/Qwen2-7B-Instruct-it-v1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2-7B-Instruct-it-v1.1-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/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-Instruct-it-v1.1-GGUF/resolve/main/Qwen2-7B-Instruct-it-v1.1.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. + +