commit cc1b439e27ffb7cbe816998a4966a8063d4a5451 Author: ModelHub XC Date: Mon Jun 15 09:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hercules-5.0-Qwen2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..32488ce --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Hercules-5.0-Qwen2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-5.0-Qwen2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hercules-5.0-Qwen2-7B.IQ3_M.gguf b/Hercules-5.0-Qwen2-7B.IQ3_M.gguf new file mode 100644 index 0000000..1f9b5cb --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2444f796c2ff1c215b8cb4e0f8bebf126e8b8d9596cd208d99a99a488246f12e +size 3574009824 diff --git a/Hercules-5.0-Qwen2-7B.IQ3_S.gguf b/Hercules-5.0-Qwen2-7B.IQ3_S.gguf new file mode 100644 index 0000000..4670f07 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc00362cd55cb6089f6bd31450efdb8b4d445031bed983a01dea5cd233e09632 +size 3499190240 diff --git a/Hercules-5.0-Qwen2-7B.IQ3_XS.gguf b/Hercules-5.0-Qwen2-7B.IQ3_XS.gguf new file mode 100644 index 0000000..44e2c1a --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d848d66f7867d38624bad580c3a68e675129b28250d8c64465825ae567d70476 +size 3346253792 diff --git a/Hercules-5.0-Qwen2-7B.IQ4_XS.gguf b/Hercules-5.0-Qwen2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..c860b77 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972b17b2185b8d5598e66f05707407d9497f5d20cce6a5da598feb391622fa0d +size 4250296288 diff --git a/Hercules-5.0-Qwen2-7B.Q2_K.gguf b/Hercules-5.0-Qwen2-7B.Q2_K.gguf new file mode 100644 index 0000000..9e2efca --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426ea40fe729dff016d9701df2d0c21106af8035c7df506b6068c1e74a8fce30 +size 3015938016 diff --git a/Hercules-5.0-Qwen2-7B.Q3_K_L.gguf b/Hercules-5.0-Qwen2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..9bfb5a6 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c10812feb7787e226d44550ad7a18322b75e0fb83e0549c7307a5cb499bc45 +size 4088457184 diff --git a/Hercules-5.0-Qwen2-7B.Q3_K_M.gguf b/Hercules-5.0-Qwen2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..e39f420 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c099b17d0937c21b15911c43bc68e0b610d3f5cb4fa2e24a150154953837a53 +size 3808389088 diff --git a/Hercules-5.0-Qwen2-7B.Q3_K_S.gguf b/Hercules-5.0-Qwen2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c0c26c7 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f77168b0ddb70d75714681f07226361ba7dd05f39276788fc7df474c17d7a7a +size 3492366304 diff --git a/Hercules-5.0-Qwen2-7B.Q4_K_M.gguf b/Hercules-5.0-Qwen2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..6287319 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da7b09329e1f07a9e90f3ec41504b87ee24b30ab8cc56eb9b55827acec33ed0 +size 4683071456 diff --git a/Hercules-5.0-Qwen2-7B.Q4_K_S.gguf b/Hercules-5.0-Qwen2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..c8f4a71 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4318d965ccda4e8a0e9c605bc043973958c7610812746dd319ae3e8c516f44ce +size 4457766880 diff --git a/Hercules-5.0-Qwen2-7B.Q5_K_M.gguf b/Hercules-5.0-Qwen2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..7287cb8 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1917a6e85b064e9ec7dd88d7a6c34d08e4bb75804f083f6c05413d7fefec7544 +size 5444829152 diff --git a/Hercules-5.0-Qwen2-7B.Q5_K_S.gguf b/Hercules-5.0-Qwen2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..49e06bf --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc0ab7f9b7cc4551d155e126e15f15950272e16d70774368c00f06fe628dfd2 +size 5315174368 diff --git a/Hercules-5.0-Qwen2-7B.Q6_K.gguf b/Hercules-5.0-Qwen2-7B.Q6_K.gguf new file mode 100644 index 0000000..824e7b6 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9200c278402afe336ce15d469ee2534bbef02c01a4e79198097d37d59da90081 +size 6254196704 diff --git a/Hercules-5.0-Qwen2-7B.Q8_0.gguf b/Hercules-5.0-Qwen2-7B.Q8_0.gguf new file mode 100644 index 0000000..ece5658 --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ef5e056eaeafdbdc67a94016a60d0cff030dea51f41639844ec44da07578f0 +size 8098523104 diff --git a/Hercules-5.0-Qwen2-7B.f16.gguf b/Hercules-5.0-Qwen2-7B.f16.gguf new file mode 100644 index 0000000..2cbce7c --- /dev/null +++ b/Hercules-5.0-Qwen2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2374909def3cb1ab28083bfcf06dedc12329c53f8b87a02ef6c495f465007f7b +size 15237851104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d899da --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Locutusque/Hercules-5.0-Qwen2-7B +datasets: +- Locutusque/hercules-v5.0 +language: +- en +library_name: transformers +license: apache-2.0 +no_imatrix: nan +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Locutusque/Hercules-5.0-Qwen2-7B + + +## 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/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-5.0-Qwen2-7B-GGUF/resolve/main/Hercules-5.0-Qwen2-7B.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. + +