commit 3d53b80d06dbdab934329c2ad00760d022d69e3b Author: ModelHub XC Date: Wed Aug 26 16:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..708ae17 --- /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-NPO-WMDP-llama3-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ILU-NPO-WMDP-llama3-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.IQ4_XS.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..5226310 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa2c0efad231b2e2c7ec024ad8dc2c16816e11ee41b4166e27b87ebdb77f0d4 +size 4484363424 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q2_K.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..60efc09 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c672eeb5c390dafb1cd64f0ffdb92a725e7d339e0f581933c90197c17927fb69 +size 3179132064 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_L.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..7e020fb --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89afc65a10c5e955475163e2d28b9716f05ba99e57c337acde61b283ae171b0b +size 4321957024 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_M.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b07473d --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cc32dbf9ff27adb0836e3482aa1dd4827b69bc5937d9ecc08265a129c69c4f +size 4018918560 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_S.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..97d3e17 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0d35274a2d17c7c6daa98d068068d952cd9c0a1721260881accbcc8b12c314 +size 3664499872 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_M.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5da58be --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c056963781e75e213dcc6fc0af36a1fef36cd884b844968517551e3db8e5033 +size 4920734880 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_S.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e96fefc --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15b765150d0f7c84edf025b0f0fbc1a85ebbcc641c2d53b47b8fd3bf833f235 +size 4692669600 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_M.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..644d3b8 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fece5db839e9f71e5b47852ce6aeff739b7ecddf1a585f2d6214407102f88f1 +size 5732988064 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_S.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..6acddd2 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5152acd3be5cb21f43be96faafe43216ba9cb6a49d43d7ae2a540312a5550d8b +size 5599294624 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q6_K.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..bebc0c1 --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19da6677670a1c9d48fcff3814ea644f9d818727eae9bae4909df01416fa73cc +size 6596007072 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.Q8_0.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..452b7fa --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c667426f28d2fb983d7390d85f2a869c6ccc5764cdc75e9b1fda0439024d46b0 +size 8540771488 diff --git a/ILU-NPO-WMDP-llama3-8b-instruct.f16.gguf b/ILU-NPO-WMDP-llama3-8b-instruct.f16.gguf new file mode 100644 index 0000000..97fbcac --- /dev/null +++ b/ILU-NPO-WMDP-llama3-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:496568cdcf73cfd465a7e8798721db4527fb1548775429dbb6ff4023284eed16 +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..edc558d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: OPTML-Group/NPO-ILU-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/NPO-ILU-WMDP-llama3-8b-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ILU-NPO-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-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-WMDP-llama3-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ILU-NPO-WMDP-llama3-8b-instruct-GGUF/resolve/main/ILU-NPO-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. + +