commit a162b6280050a5a4fb5a80b8d020a4d53719a727 Author: ModelHub XC Date: Thu May 14 11:01:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hercules-3-10B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..19a08cd --- /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 +Hercules-3-10B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3-10B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hercules-3-10B.IQ4_XS.gguf b/Hercules-3-10B.IQ4_XS.gguf new file mode 100644 index 0000000..ee24615 --- /dev/null +++ b/Hercules-3-10B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a600aad930ba4b2820bd0fef0f0887ae7e45aecd896f5f44e241c52ccbc666e +size 5652183072 diff --git a/Hercules-3-10B.Q2_K.gguf b/Hercules-3-10B.Q2_K.gguf new file mode 100644 index 0000000..82c38e1 --- /dev/null +++ b/Hercules-3-10B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e21345f92ea6ca64b82b9beca5703e7e8f5a63efb943441def8f3b704c319d +size 3924047904 diff --git a/Hercules-3-10B.Q3_K_L.gguf b/Hercules-3-10B.Q3_K_L.gguf new file mode 100644 index 0000000..71569ae --- /dev/null +++ b/Hercules-3-10B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01bac39b5ec74699cd7ff81d7443f2d6475684dc65d5061a11a1788581932e8 +size 5450807328 diff --git a/Hercules-3-10B.Q3_K_M.gguf b/Hercules-3-10B.Q3_K_M.gguf new file mode 100644 index 0000000..be43785 --- /dev/null +++ b/Hercules-3-10B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54091d5b8e843f61bfc172d789254803d37d33b03b3233713de8d526c97a8fab +size 5052479520 diff --git a/Hercules-3-10B.Q3_K_S.gguf b/Hercules-3-10B.Q3_K_S.gguf new file mode 100644 index 0000000..e9c6677 --- /dev/null +++ b/Hercules-3-10B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6281b5a0c887cac849101c95c3fd755fa80bb983af0709c8bcfcae8670a7db48 +size 4591138848 diff --git a/Hercules-3-10B.Q4_K_M.gguf b/Hercules-3-10B.Q4_K_M.gguf new file mode 100644 index 0000000..75a0e22 --- /dev/null +++ b/Hercules-3-10B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956ebb30715eee1fcd6f13e9ae16ea343e298752588557fbdfc6e5757e75dacf +size 6287521824 diff --git a/Hercules-3-10B.Q4_K_S.gguf b/Hercules-3-10B.Q4_K_S.gguf new file mode 100644 index 0000000..868c092 --- /dev/null +++ b/Hercules-3-10B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5460f64bd48cbf14a440dd57838d7159961235212c2f791f4725af738d8818ca +size 5952157728 diff --git a/Hercules-3-10B.Q5_K_M.gguf b/Hercules-3-10B.Q5_K_M.gguf new file mode 100644 index 0000000..ef1fb12 --- /dev/null +++ b/Hercules-3-10B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84cf7164433cbb8507a2c836886ff5c5de6a832e996aab2b491624f720675d02 +size 7340554272 diff --git a/Hercules-3-10B.Q5_K_S.gguf b/Hercules-3-10B.Q5_K_S.gguf new file mode 100644 index 0000000..c845067 --- /dev/null +++ b/Hercules-3-10B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2149481b6c60e3588aa7fadb9fa5bb17f78e510cdb4e0dc8861e2034ea4d5c92 +size 7144192032 diff --git a/Hercules-3-10B.Q6_K.gguf b/Hercules-3-10B.Q6_K.gguf new file mode 100644 index 0000000..259d3f5 --- /dev/null +++ b/Hercules-3-10B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2477ceac02c065f66cf72b185758333d68f3f12eb88a54d3f97b57bdcde0d74 +size 8459401248 diff --git a/Hercules-3-10B.Q8_0.gguf b/Hercules-3-10B.Q8_0.gguf new file mode 100644 index 0000000..aa02b6b --- /dev/null +++ b/Hercules-3-10B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c788165498b877f51bbe9a337922b45ca7ac1841991a11441243c0888fa87c6c +size 10955241504 diff --git a/Hercules-3-10B.f16.gguf b/Hercules-3-10B.f16.gguf new file mode 100644 index 0000000..9ddfa95 --- /dev/null +++ b/Hercules-3-10B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd6a50b40a53d367d40b63194e5c7db899922d579797b12454997487a9138cd +size 20616558624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..64810dd --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: odyssey-labs/Hercules-3-10B +language: +- en +- fr +- pt +- es +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- deployment +- aws-sagemaker +- azure-ml +- google-cloud +- falcon +- NLP +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/odyssey-labs/Hercules-3-10B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hercules-3-10B-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/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q2_K.gguf) | Q2_K | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q3_K_S.gguf) | Q3_K_S | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q3_K_L.gguf) | Q3_K_L | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.IQ4_XS.gguf) | IQ4_XS | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q4_K_S.gguf) | Q4_K_S | 6.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q4_K_M.gguf) | Q4_K_M | 6.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q5_K_S.gguf) | Q5_K_S | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q5_K_M.gguf) | Q5_K_M | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q6_K.gguf) | Q6_K | 8.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.Q8_0.gguf) | Q8_0 | 11.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-3-10B-GGUF/resolve/main/Hercules-3-10B.f16.gguf) | f16 | 20.7 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +