commit 15658e01bca71231f4720b2625d778ef9246d7c3 Author: ModelHub XC Date: Sun Aug 2 17:29:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-it-prometheus-ko-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4433d02 --- /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 +llama3-8b-it-prometheus-ko.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-it-prometheus-ko.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c498e2 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: nayohan/llama3-8b-it-prometheus-ko +datasets: +- nayohan/feedback-collection-ko +- nayohan/feedback-collection-ko-chat +language: +- en +- ko +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- ko +- eval +- llm-eval +--- +## About + + + + + + +static quants of https://huggingface.co/nayohan/llama3-8b-it-prometheus-ko + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-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/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-it-prometheus-ko-GGUF/resolve/main/llama3-8b-it-prometheus-ko.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. + + diff --git a/llama3-8b-it-prometheus-ko.IQ4_XS.gguf b/llama3-8b-it-prometheus-ko.IQ4_XS.gguf new file mode 100644 index 0000000..9934973 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e459b489664b349356668fb6ea12b7ba11bb13aff8c727410ed9540fb6538f81 +size 4484364192 diff --git a/llama3-8b-it-prometheus-ko.Q2_K.gguf b/llama3-8b-it-prometheus-ko.Q2_K.gguf new file mode 100644 index 0000000..55c70b1 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4518a30cb4804c14e188b754d4bb4f2b72aa212edc5f1925c0ae8d4ac4fe365 +size 3179132832 diff --git a/llama3-8b-it-prometheus-ko.Q3_K_L.gguf b/llama3-8b-it-prometheus-ko.Q3_K_L.gguf new file mode 100644 index 0000000..a14bc7d --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db8de816a7d73a3c82b6ce1889b73c9e932f53c4dce91d5c0a7e507f020c3aa +size 4321957792 diff --git a/llama3-8b-it-prometheus-ko.Q3_K_M.gguf b/llama3-8b-it-prometheus-ko.Q3_K_M.gguf new file mode 100644 index 0000000..8b05453 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e4561acd0173129da9d7dc3342373c8ec28244add4fd2a438bafbc3abb9c4d +size 4018919328 diff --git a/llama3-8b-it-prometheus-ko.Q3_K_S.gguf b/llama3-8b-it-prometheus-ko.Q3_K_S.gguf new file mode 100644 index 0000000..2a86186 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c72107c2e705d0a71fca35bade2fa2a0254cde080696d5abdacd1efdb94aec4 +size 3664500640 diff --git a/llama3-8b-it-prometheus-ko.Q4_K_M.gguf b/llama3-8b-it-prometheus-ko.Q4_K_M.gguf new file mode 100644 index 0000000..45d4981 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f884690c38681f52dc8427415e091c22a420b4161212aa948813f513c0dda436 +size 4920735648 diff --git a/llama3-8b-it-prometheus-ko.Q4_K_S.gguf b/llama3-8b-it-prometheus-ko.Q4_K_S.gguf new file mode 100644 index 0000000..815f63b --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2773eaaba39cd535f9be5e19e7adf62ce4e0b665c44e5b985e4faae732ef4aba +size 4692670368 diff --git a/llama3-8b-it-prometheus-ko.Q5_K_M.gguf b/llama3-8b-it-prometheus-ko.Q5_K_M.gguf new file mode 100644 index 0000000..bfc241e --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1857bcf5b6bc54fd9a74d54c1f2b2383cdba17e4faf596cbb7a4a2a3a0304b8 +size 5732988832 diff --git a/llama3-8b-it-prometheus-ko.Q5_K_S.gguf b/llama3-8b-it-prometheus-ko.Q5_K_S.gguf new file mode 100644 index 0000000..c30d863 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54dc5d667acbb04ebd44d960662f7d78634f22889285515e31760ce2f554bc6 +size 5599295392 diff --git a/llama3-8b-it-prometheus-ko.Q6_K.gguf b/llama3-8b-it-prometheus-ko.Q6_K.gguf new file mode 100644 index 0000000..0141887 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fe545a2e41908fd3fa457690267c5713a8d08a0cb7fcb2c73bc7a1ca8cdb23 +size 6596007840 diff --git a/llama3-8b-it-prometheus-ko.Q8_0.gguf b/llama3-8b-it-prometheus-ko.Q8_0.gguf new file mode 100644 index 0000000..9697199 --- /dev/null +++ b/llama3-8b-it-prometheus-ko.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7593505314f982d0269df314d2cf2a0326acaeb0329ef60b6a8954efe5c2b97 +size 8540772256 diff --git a/llama3-8b-it-prometheus-ko.f16.gguf b/llama3-8b-it-prometheus-ko.f16.gguf new file mode 100644 index 0000000..8de1f5c --- /dev/null +++ b/llama3-8b-it-prometheus-ko.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766cb9f769f6cfeda307609787361687ce684d9789348ec86fe2480922e477e7 +size 16068892576