commit a819836fe32179bb32bc19a4d7e415517533220f Author: ModelHub XC Date: Sun May 31 09:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8084f0d --- /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 +ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-RMU-WMDP-llama3-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.IQ4_XS.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..76d9465 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d798807b41f40ad9b73c1cdecd457c8cc36b44f7f25661a4cceb5b8fe1c0eba4 +size 4484363520 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q2_K.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..95a3319 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa3c7014e1b231db26ca214dee12b0da864a88499ec0c1ca8989f083da8bb870 +size 3179132160 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_L.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..2fe7dd1 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0798e707771a3c63d45daa8a671fd0088dc296473231415f231023c2acf336 +size 4321957120 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_M.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..5bc03a0 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bf5b6178bf4083964c68de9967e1aaf649f5297920d4820c2b7de020de556a +size 4018918656 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_S.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..fa37e7d --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3470bcb6f7415d7c1e82c1928fdc9c6f0252df6bfbe7e391bdb37ee752e166 +size 3664499968 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_M.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..1ea062b --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d38621a0f7a5b10ecb684decbb57aadc568276cd0590eafef644593f97c0264e +size 4920734976 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_S.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..9a570c6 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a547d1d9877de57fe86eeb688a0de30d3d814639c689ca81c91fb297286358 +size 4692669696 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_M.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..42cbd0e --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344e4ba7cb46bb1e88f3290a533663a667d5217f6ca1d5af992b54886c040bbb +size 5732988160 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_S.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..45d5084 --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5e96bd7544fcc5ccd5398d18852c14aadc771c200a24b6a81b4f302cf17eee +size 5599294720 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q6_K.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..0b41c5f --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26696e5abf64a99e72c092ea9ef647cea806e4bfe9d1ca2800c9067760724cc8 +size 6596007168 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.Q8_0.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..f54eefb --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b25451d95fd6fd1a915b0bb285973f3f484d4047ce6ad6a03da878bf29a4414 +size 8540771584 diff --git a/ILU-RMU-WMDP-llama3-8b-instruct.f16.gguf b/ILU-RMU-WMDP-llama3-8b-instruct.f16.gguf new file mode 100644 index 0000000..1622a4e --- /dev/null +++ b/ILU-RMU-WMDP-llama3-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1adc1d9f7aa1f82f64ffb28b9d7c1972c44477cd5568bca7011d2c956d997aae +size 16068891904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1bc57aa --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: OPTML-Group/ILU-RMU-WMDP-llama3-8b-instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OPTML-Group/ILU-RMU-WMDP-llama3-8b-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ILU-RMU-WMDP-llama3-8b-instruct-GGUF).*** + +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/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-RMU-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-RMU-WMDP-llama3-8b-instruct.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. + +