commit 740ccf512cbd0d79074e6e4e75f471dd73e96c15 Author: ModelHub XC Date: Sun Apr 26 22:30:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Orca-2-13b-SFT-v6-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c7d1ac --- /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 +Orca-2-13b-SFT-v6.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Orca-2-13b-SFT-v6.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Orca-2-13b-SFT-v6.IQ4_XS.gguf b/Orca-2-13b-SFT-v6.IQ4_XS.gguf new file mode 100644 index 0000000..d2cd010 --- /dev/null +++ b/Orca-2-13b-SFT-v6.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f9b05e24d71d5e74f4f7e1c965ddfcf475ddbd2565eb4a6d9dad74029737e7 +size 7019541760 diff --git a/Orca-2-13b-SFT-v6.Q2_K.gguf b/Orca-2-13b-SFT-v6.Q2_K.gguf new file mode 100644 index 0000000..d3d5248 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ca50308850d89098a30461f3a0c62d916f3a88113edf0ecb24b685fb0b2bf0 +size 4854290656 diff --git a/Orca-2-13b-SFT-v6.Q3_K_L.gguf b/Orca-2-13b-SFT-v6.Q3_K_L.gguf new file mode 100644 index 0000000..b1f9c1c --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6a3d20b1ea9e707990822d98a187e6b062e1a0ab57fa6447c716e78805cce3 +size 6929581824 diff --git a/Orca-2-13b-SFT-v6.Q3_K_M.gguf b/Orca-2-13b-SFT-v6.Q3_K_M.gguf new file mode 100644 index 0000000..1dec676 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2be23196da952cbe5ae9e8ae0052a337f311f2ea3c3751e8bbafff57f01a4d4 +size 6337791744 diff --git a/Orca-2-13b-SFT-v6.Q3_K_S.gguf b/Orca-2-13b-SFT-v6.Q3_K_S.gguf new file mode 100644 index 0000000..b208276 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f025a845fd2f1df817bc0c35f4017bf36ead0db125c0593d71379b7f833fd0b +size 5659002624 diff --git a/Orca-2-13b-SFT-v6.Q4_0_4_4.gguf b/Orca-2-13b-SFT-v6.Q4_0_4_4.gguf new file mode 100644 index 0000000..dbf1204 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa35f1efedf3fa8d7e840c50316e9fa74f6c0043cdf34a42d0579b63aebcf7ca +size 7365859040 diff --git a/Orca-2-13b-SFT-v6.Q4_K_M.gguf b/Orca-2-13b-SFT-v6.Q4_K_M.gguf new file mode 100644 index 0000000..a9d82e6 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8305f598d42fd47805d6ff91a3ebbd2c49698016f4029427f5f5901d51638d +size 7865980640 diff --git a/Orca-2-13b-SFT-v6.Q4_K_S.gguf b/Orca-2-13b-SFT-v6.Q4_K_S.gguf new file mode 100644 index 0000000..e54e3bc --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b192fd0f75aaaa7d3700ccefae7094d9fa0c428983d5e6c30a1b61c9a6c7a56 +size 7423203040 diff --git a/Orca-2-13b-SFT-v6.Q5_K_M.gguf b/Orca-2-13b-SFT-v6.Q5_K_M.gguf new file mode 100644 index 0000000..62c8fc5 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:730a37dc20c749f3d0c7f9d394799d6122188afdfcac253ad95805ce0c3fae05 +size 9229950560 diff --git a/Orca-2-13b-SFT-v6.Q5_K_S.gguf b/Orca-2-13b-SFT-v6.Q5_K_S.gguf new file mode 100644 index 0000000..e773da5 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65496eb52aa4bf56ba1b0f77626cc4de3cf6435d42d523f4ee37745a7b174ae6 +size 8972312160 diff --git a/Orca-2-13b-SFT-v6.Q6_K.gguf b/Orca-2-13b-SFT-v6.Q6_K.gguf new file mode 100644 index 0000000..8092eed --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7acf0f69b893bc7bd1ded18e8b8998155866a3eee25e43edade5bf85f96ca7 +size 10679168608 diff --git a/Orca-2-13b-SFT-v6.Q8_0.gguf b/Orca-2-13b-SFT-v6.Q8_0.gguf new file mode 100644 index 0000000..d239c91 --- /dev/null +++ b/Orca-2-13b-SFT-v6.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97cd5627892837e2acde85985601184632cbab8040f6e1eb771007cc83ef4a4a +size 13831355232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb8b375 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Locutusque/Orca-2-13b-SFT-v6 +datasets: +- HuggingFaceH4/no_robots +- mlabonne/guanaco-llama2-1k +- OpenAssistant/oasst_top1_2023-08-25 +- totally-not-an-llm/EverythingLM-data-V3 +- LDJnr/Pure-Dove +- LDJnr/Capybara +- LDJnr/LessWrong-Amplify-Instruct +- LDJnr/Verified-Camel +language: +- en +- fr +- es +- hi +- zh +- code +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Locutusque/Orca-2-13b-SFT-v6 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-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/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q2_K.gguf) | Q2_K | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q3_K_S.gguf) | Q3_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q3_K_L.gguf) | Q3_K_L | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.IQ4_XS.gguf) | IQ4_XS | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q4_0_4_4.gguf) | Q4_0_4_4 | 7.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q5_K_S.gguf) | Q5_K_S | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q5_K_M.gguf) | Q5_K_M | 9.3 | | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q6_K.gguf) | Q6_K | 10.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Orca-2-13b-SFT-v6-GGUF/resolve/main/Orca-2-13b-SFT-v6.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality | + +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. + +