commit aca84d552b6daeb9f2aab67cfd2da29f50904533 Author: ModelHub XC Date: Fri Jun 12 02:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2e3c98 --- /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 +RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.f16.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RoLlama3.1-8b-Instruct-2024-10-09.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cfef59f --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09 +datasets: +- OpenLLM-Ro/ro_sft_alpaca +- OpenLLM-Ro/ro_sft_alpaca_gpt4 +- OpenLLM-Ro/ro_sft_dolly +- OpenLLM-Ro/ro_sft_selfinstruct_gpt4 +- OpenLLM-Ro/ro_sft_norobots +- OpenLLM-Ro/ro_sft_orca +- OpenLLM-Ro/ro_sft_camel +- OpenLLM-Ro/ro_sft_oasst +- OpenLLM-Ro/ro_sft_ultrachat +language: +- ro +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2024-10-09 + + +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/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RoLlama3.1-8b-Instruct-2024-10-09-GGUF/resolve/main/RoLlama3.1-8b-Instruct-2024-10-09.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. + + diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.IQ4_XS.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.IQ4_XS.gguf new file mode 100644 index 0000000..93a3302 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4899d557b6e6b4a9cec7b5ea98819abd793ad4730ca8f63ee54cb7c8e9114c2c +size 4484366368 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q2_K.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q2_K.gguf new file mode 100644 index 0000000..8072ca6 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed432fe7a2e322f3c0182426af17bc3e32b3e62472e191c8bb65294f4f3fbd4 +size 3179135008 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_L.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_L.gguf new file mode 100644 index 0000000..8d010b9 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74de02a3f9aad1def5031927b8602b613fd7d54b6f0386a4c5853856ea07c2a2 +size 4321959968 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_M.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_M.gguf new file mode 100644 index 0000000..81f8a88 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c97e9bd4a08a971392d6cf8cdcbcfb3dc880dcd81ea5cd214f7a97ab58fa9a +size 4018921504 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_S.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_S.gguf new file mode 100644 index 0000000..2eff541 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db4df57d5202eb7e516b31b2e707c78c7645e205983a7cde8604df9fc6a5188 +size 3664502816 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_M.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_M.gguf new file mode 100644 index 0000000..42c752e --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10235a3e8b93437667ca97b77ac36b20bc4a4bf33a3902346d8014886435953 +size 4920737824 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_S.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_S.gguf new file mode 100644 index 0000000..80affa4 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e85b814746ea1c37aef23cdf99b83d7cb053ee51976b7af0f534f5edaeec379 +size 4692672544 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_M.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_M.gguf new file mode 100644 index 0000000..77da82d --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4032f99032756f40e182fdf689ca61299ff3d5e4361893ae8b379f13acb0d67 +size 5732991008 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_S.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_S.gguf new file mode 100644 index 0000000..063522d --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:812cf3c1f6a3d7b07b981ee4f876867472f0feaaeea4967e3430d1aa7ccc9126 +size 5599297568 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q6_K.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q6_K.gguf new file mode 100644 index 0000000..d07cb22 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f1bc092c7696a1f6ea6d17164e60f48ad93d59ef199a6d26e6bb076abe44a3 +size 6596010016 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.Q8_0.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.Q8_0.gguf new file mode 100644 index 0000000..f743eed --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4fa5875aa411afba9aaa24801861d2422f78ce75fe28cd942b2ab941ba8b1d +size 8540774432 diff --git a/RoLlama3.1-8b-Instruct-2024-10-09.f16.gguf b/RoLlama3.1-8b-Instruct-2024-10-09.f16.gguf new file mode 100644 index 0000000..e45be37 --- /dev/null +++ b/RoLlama3.1-8b-Instruct-2024-10-09.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e7b503fe65d2bb22756f1414a2f093ab0d91808c6874a8db124576c6f7091c +size 16068894752