commit 587785a11a005e016598182573581a3429286a9a Author: ModelHub XC Date: Sun May 10 06:15:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/UNDIAL-WMDP-llama3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1d77a48 --- /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 +UNDIAL-WMDP-llama3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +UNDIAL-WMDP-llama3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff12414 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: OPTML-Group/UNDIAL-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/UNDIAL-WMDP-llama3-8b-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#UNDIAL-WMDP-llama3-8b-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/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/UNDIAL-WMDP-llama3-8b-GGUF/resolve/main/UNDIAL-WMDP-llama3-8b.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/UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf b/UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..ea53608 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2023071bec9494ca6fdccc68f147e04c25cf20ef166337a68706b6a611eaa2c +size 4484368960 diff --git a/UNDIAL-WMDP-llama3-8b.Q2_K.gguf b/UNDIAL-WMDP-llama3-8b.Q2_K.gguf new file mode 100644 index 0000000..02a62e3 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d185c5d44992a50bb487a926f1fc81db4c14409d31e5efd52dbed09d593475d9 +size 3179136768 diff --git a/UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf b/UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..921b482 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4737151e8f35289cdd96a7423c406132b2f1effaea33089705c05e455d60f1 +size 4321962144 diff --git a/UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf b/UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..1517af6 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c8b82dc62ec2ae7504ebcc70677a3341c508df3e85c8372caaaef4db261ea0 +size 4018923680 diff --git a/UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf b/UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..d5c3e83 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4bb7af825dc4450673844e397c1d2db67f56558ba421623e1af2dc464ccc7d +size 3664504992 diff --git a/UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf b/UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..6a78435 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490c1a06572a21a0ef4cebb6b6b4ebd17abe0cdb96ea1de00f133c8986c942ec +size 4920740544 diff --git a/UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf b/UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..f8300cb --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134d2796539e32a9c6e1d41f9bed94a9fdbcd0e5e3caab39c041c1bd024c4e9b +size 4692675264 diff --git a/UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf b/UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..c2dfdb5 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c28f3e62e84b759a4b34c09de6e2afef260c2df0aef1b5c5f33dec171f01d9 +size 5732994240 diff --git a/UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf b/UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..7cf08b3 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671f7dc8b4e80abf129745a6e4deeed88a517ef5ded158ce2ad8db3d4680da58 +size 5599300800 diff --git a/UNDIAL-WMDP-llama3-8b.Q6_K.gguf b/UNDIAL-WMDP-llama3-8b.Q6_K.gguf new file mode 100644 index 0000000..1ad1390 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a267205894d443ecc6c9cce113933ac4c841813b50d8d777a083a257b7ff6a +size 6596013792 diff --git a/UNDIAL-WMDP-llama3-8b.Q8_0.gguf b/UNDIAL-WMDP-llama3-8b.Q8_0.gguf new file mode 100644 index 0000000..5490a93 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab59de894f5f3458b02093ab858d6f67545fded4cf451ea917ace1ebe3979e5 +size 8540780192 diff --git a/UNDIAL-WMDP-llama3-8b.f16.gguf b/UNDIAL-WMDP-llama3-8b.f16.gguf new file mode 100644 index 0000000..0db53a2 --- /dev/null +++ b/UNDIAL-WMDP-llama3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4526b5cee9a0003e4b28f81f6274b95ead33de0333fd81f7f25327c43adaf91 +size 16068908192