commit 1f86ed31e9936f9bc938dc640416e34b7698966b Author: ModelHub XC Date: Tue Jul 21 09:37:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea97c85 --- /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 +Qwen2.5-7B-Instruct-Fusion.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-Fusion.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-Fusion.IQ4_XS.gguf b/Qwen2.5-7B-Instruct-Fusion.IQ4_XS.gguf new file mode 100644 index 0000000..89b05f4 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c034de398c949f82174a4b69172e57661c8646841ec9b1113b37a19607b7900 +size 4250299680 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q2_K.gguf b/Qwen2.5-7B-Instruct-Fusion.Q2_K.gguf new file mode 100644 index 0000000..d5949cd --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147fe3c9140c0039b0eb985037cfb9eecade0953c277d3768525d56e009f4e44 +size 3015941408 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q3_K_L.gguf b/Qwen2.5-7B-Instruct-Fusion.Q3_K_L.gguf new file mode 100644 index 0000000..99ec859 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e5ead976c213f4327afde78a6ac6901275d9db3b6dc8658dda24573afaaff0 +size 4088460576 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q3_K_M.gguf b/Qwen2.5-7B-Instruct-Fusion.Q3_K_M.gguf new file mode 100644 index 0000000..daf5905 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28141ee7f0cda2c409568962968b078a55a19c7422a278a8430cad181b163c67 +size 3808392480 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q3_K_S.gguf b/Qwen2.5-7B-Instruct-Fusion.Q3_K_S.gguf new file mode 100644 index 0000000..1aeeee1 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c2f4368c3c728780931292b1396a6c589b4285df096c6439720d6bfd9a287c +size 3492369696 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q4_K_M.gguf b/Qwen2.5-7B-Instruct-Fusion.Q4_K_M.gguf new file mode 100644 index 0000000..0ee03f3 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181ea6a8fb14dc70ea1df3dc318d90bdbce536951992f723959cf3789a8d8958 +size 4683074848 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q4_K_S.gguf b/Qwen2.5-7B-Instruct-Fusion.Q4_K_S.gguf new file mode 100644 index 0000000..831b0ae --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75842062d0a367a1b5b46eb528859a1e48f52ac0233743d74efbf3c4330e795f +size 4457770272 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q5_K_M.gguf b/Qwen2.5-7B-Instruct-Fusion.Q5_K_M.gguf new file mode 100644 index 0000000..368b287 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3a048e4008871145bae08eee6f46936d8aeb7fb493183a97d462d2cc7b185d0 +size 5444832544 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q5_K_S.gguf b/Qwen2.5-7B-Instruct-Fusion.Q5_K_S.gguf new file mode 100644 index 0000000..9e029a8 --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6833d20972dfc0fb9b0e9b95c6089d3a56e46e0972cee58e678243f5eb4496bc +size 5315177760 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q6_K.gguf b/Qwen2.5-7B-Instruct-Fusion.Q6_K.gguf new file mode 100644 index 0000000..37f3f0a --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5671faa9607649147bbd97a3339caf0d45733bca971d4147f795a5fd08932309 +size 6254200096 diff --git a/Qwen2.5-7B-Instruct-Fusion.Q8_0.gguf b/Qwen2.5-7B-Instruct-Fusion.Q8_0.gguf new file mode 100644 index 0000000..2a0ce6c --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072ed3e080102a2a54c22f03d14d39892106797a6ba9ee89309cbfd8162eb5ca +size 8098526496 diff --git a/Qwen2.5-7B-Instruct-Fusion.f16.gguf b/Qwen2.5-7B-Instruct-Fusion.f16.gguf new file mode 100644 index 0000000..6448e4c --- /dev/null +++ b/Qwen2.5-7B-Instruct-Fusion.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b91c8423ddf03ecd0e8fa44f7d44cdf140108b42af86d6cd676809111cc2496 +size 15237854496 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d398afd --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Qwen2.5-7B-Instruct-Fusion +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Qwen2.5-7B-Instruct-Fusion + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-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/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-Fusion-GGUF/resolve/main/Qwen2.5-7B-Instruct-Fusion.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. + +