commit b27a9c571e025e51175b2820e1af0a1b39619af8 Author: ModelHub XC Date: Wed Sep 23 23:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA-O1-Supervised-1129-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6043ac2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +LLaMA-O1-Supervised-1129.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-O1-Supervised-1129.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-O1-Supervised-1129.IQ4_XS.gguf b/LLaMA-O1-Supervised-1129.IQ4_XS.gguf new file mode 100644 index 0000000..5665423 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e5c87cb0e9d94f7d78df4227c65a217be55d402e8b965569ceb7c0c0c1d052 +size 4484719936 diff --git a/LLaMA-O1-Supervised-1129.Q2_K.gguf b/LLaMA-O1-Supervised-1129.Q2_K.gguf new file mode 100644 index 0000000..bb5724c --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66667505cdae4aecdd478530ebc0e13ea9dd6d39f5b0602b71feed39af27f964 +size 3179435328 diff --git a/LLaMA-O1-Supervised-1129.Q3_K_L.gguf b/LLaMA-O1-Supervised-1129.Q3_K_L.gguf new file mode 100644 index 0000000..4f2dd39 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b399195b149bc46ee57a915b113e91457dc29ca773367a8a7f2c1835d863cab +size 4322286912 diff --git a/LLaMA-O1-Supervised-1129.Q3_K_M.gguf b/LLaMA-O1-Supervised-1129.Q3_K_M.gguf new file mode 100644 index 0000000..866963f --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d27a2651b2bcd291b1da4a39f439a6ccbda804f48ea1c5c5073aaa049fa0392 +size 4019248448 diff --git a/LLaMA-O1-Supervised-1129.Q3_K_S.gguf b/LLaMA-O1-Supervised-1129.Q3_K_S.gguf new file mode 100644 index 0000000..fa391e9 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7183d7cacc6a724d8342299a73645c10822b160dee22d1d53727366e23f3539 +size 3664829760 diff --git a/LLaMA-O1-Supervised-1129.Q4_0_4_4.gguf b/LLaMA-O1-Supervised-1129.Q4_0_4_4.gguf new file mode 100644 index 0000000..7b8697e --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd4cb699e49dddf6ad2e9b7967377793271eba8983919e9e3c7c7799da78f97 +size 4661577024 diff --git a/LLaMA-O1-Supervised-1129.Q4_K_M.gguf b/LLaMA-O1-Supervised-1129.Q4_K_M.gguf new file mode 100644 index 0000000..a5e739d --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a889062f90baf2fd8baae0dff0a1c7dfe7ec1080592d7eaee4e46e1d0ca77b0f +size 4921099584 diff --git a/LLaMA-O1-Supervised-1129.Q4_K_S.gguf b/LLaMA-O1-Supervised-1129.Q4_K_S.gguf new file mode 100644 index 0000000..34a8bd3 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae3dded6535ab9ae5708b2f1992cebf13467c83d7110b3417a818b71b42d443 +size 4693034304 diff --git a/LLaMA-O1-Supervised-1129.Q5_K_M.gguf b/LLaMA-O1-Supervised-1129.Q5_K_M.gguf new file mode 100644 index 0000000..0855a5b --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142bb9528cdb305d55e5331d350eff6a322d888957aa9d64615b7646f85df0ce +size 5733385536 diff --git a/LLaMA-O1-Supervised-1129.Q5_K_S.gguf b/LLaMA-O1-Supervised-1129.Q5_K_S.gguf new file mode 100644 index 0000000..1c4fb7f --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423c5e14a1cd957d68bd038ade07bcb62115462d92ad339dbd720b94ba5d8437 +size 5599692096 diff --git a/LLaMA-O1-Supervised-1129.Q6_K.gguf b/LLaMA-O1-Supervised-1129.Q6_K.gguf new file mode 100644 index 0000000..49e1c50 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6315ad2001e9b1b0f611bfc2e9ce5ffa76473f06eb3d95ab30a21ebbfb664d +size 6596439360 diff --git a/LLaMA-O1-Supervised-1129.Q8_0.gguf b/LLaMA-O1-Supervised-1129.Q8_0.gguf new file mode 100644 index 0000000..a53b311 --- /dev/null +++ b/LLaMA-O1-Supervised-1129.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71fee3c71728bee908730544278bfcd22663a34ce0056735c35d4de0484bfc2 +size 8541330752 diff --git a/LLaMA-O1-Supervised-1129.f16.gguf b/LLaMA-O1-Supervised-1129.f16.gguf new file mode 100644 index 0000000..adcf03f --- /dev/null +++ b/LLaMA-O1-Supervised-1129.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50bbbf1f4c5a4828a57c5c2090c00a496a1448579097afe8141e3f5cf2f8d90c +size 16069942592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c58cfc2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: SimpleBerry/LLaMA-O1-Supervised-1129 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/SimpleBerry/LLaMA-O1-Supervised-1129 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-O1-Supervised-1129-GGUF/resolve/main/LLaMA-O1-Supervised-1129.f16.gguf) | f16 | 16.2 | 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. + +