commit fa5925f7992176e6c4e8b37fc92ab2cb236796bf Author: ModelHub XC Date: Fri Jul 17 21:54:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-1M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bf419d --- /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-1M.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-1M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-1M.IQ4_XS.gguf b/Qwen2.5-7B-Instruct-1M.IQ4_XS.gguf new file mode 100644 index 0000000..cf0f530 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbabde6e75714b96f566085e9cba06e604a89a64975d08075f42f6d59fc707c +size 4250299168 diff --git a/Qwen2.5-7B-Instruct-1M.Q2_K.gguf b/Qwen2.5-7B-Instruct-1M.Q2_K.gguf new file mode 100644 index 0000000..1903898 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f18f415d096dea93a4b086a648d24f6c5160b1cd580fb064abd19f2a5da6a6 +size 3015940896 diff --git a/Qwen2.5-7B-Instruct-1M.Q3_K_L.gguf b/Qwen2.5-7B-Instruct-1M.Q3_K_L.gguf new file mode 100644 index 0000000..2e1074c --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40aa082f77ffb7de62fcb4f25950df63e4496cd1f19623866a6de6f6ec86d031 +size 4088460064 diff --git a/Qwen2.5-7B-Instruct-1M.Q3_K_M.gguf b/Qwen2.5-7B-Instruct-1M.Q3_K_M.gguf new file mode 100644 index 0000000..74b8de7 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80dad9dac47ccfcccfd618540574ead5b7426b109f59b87d9a2f8fdb76d53bb4 +size 3808391968 diff --git a/Qwen2.5-7B-Instruct-1M.Q3_K_S.gguf b/Qwen2.5-7B-Instruct-1M.Q3_K_S.gguf new file mode 100644 index 0000000..4302c3b --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abeb5ecfa440f9ae4929d8eb9564f54c8c82cf93ed45b1ee5879414d4298fc8b +size 3492369184 diff --git a/Qwen2.5-7B-Instruct-1M.Q4_K_M.gguf b/Qwen2.5-7B-Instruct-1M.Q4_K_M.gguf new file mode 100644 index 0000000..286b031 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f6e8615e15a157ec03037bafc75997541dc1e7541453c1e4a592c7324954f6 +size 4683074336 diff --git a/Qwen2.5-7B-Instruct-1M.Q4_K_S.gguf b/Qwen2.5-7B-Instruct-1M.Q4_K_S.gguf new file mode 100644 index 0000000..0b5b2f6 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c36c825d63bddac3295db109901604c0d1123d841de4f801a862a77529d2c689 +size 4457769760 diff --git a/Qwen2.5-7B-Instruct-1M.Q5_K_M.gguf b/Qwen2.5-7B-Instruct-1M.Q5_K_M.gguf new file mode 100644 index 0000000..c01a84b --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9bd6796e605406f88edd5276023f06ab64e3aa1ccdd24550ad603a6a893d25a +size 5444832032 diff --git a/Qwen2.5-7B-Instruct-1M.Q5_K_S.gguf b/Qwen2.5-7B-Instruct-1M.Q5_K_S.gguf new file mode 100644 index 0000000..254a987 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c105ed8dcc7cee2bf9bbb39fc220e462f4b8e6ce67e358ecc429278c3359df8 +size 5315177248 diff --git a/Qwen2.5-7B-Instruct-1M.Q6_K.gguf b/Qwen2.5-7B-Instruct-1M.Q6_K.gguf new file mode 100644 index 0000000..5a45962 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f62cf1ff7161887b2aadc3f13eb36bad3f62b8cb62ae9e37ddde4972560da8 +size 6254199584 diff --git a/Qwen2.5-7B-Instruct-1M.Q8_0.gguf b/Qwen2.5-7B-Instruct-1M.Q8_0.gguf new file mode 100644 index 0000000..5d6618b --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd9c22d8ef1ba8f89c88299f706d404728187dc6802cdd917738e555e2d6eef +size 8098525984 diff --git a/Qwen2.5-7B-Instruct-1M.f16.gguf b/Qwen2.5-7B-Instruct-1M.f16.gguf new file mode 100644 index 0000000..f9e4ad9 --- /dev/null +++ b/Qwen2.5-7B-Instruct-1M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4056e6551491883fb33febb0a62a6a35ae73e89de1effb704b2d9b0612d361e +size 15237853984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f72ac30 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Qwen/Qwen2.5-7B-Instruct-1M +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M/blob/main/LICENSE +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-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/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-1M.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-1M-GGUF/resolve/main/Qwen2.5-7B-Instruct-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. + +