commit 37484e6d290db83dad090eee93fc145afe2810d9 Author: ModelHub XC Date: Sun Jun 14 01:15:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/webrl-llama-3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c28e304 --- /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 +webrl-llama-3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +webrl-llama-3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..faad81c --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: zai-org/webrl-llama-3.1-8b +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- webrl +- llama3.1 +- webarena-lite +- llm +- agent +--- +## About + + + + + + +static quants of https://huggingface.co/zai-org/webrl-llama-3.1-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#webrl-llama-3.1-8b-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/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/webrl-llama-3.1-8b-GGUF/resolve/main/webrl-llama-3.1-8b.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/webrl-llama-3.1-8b.IQ4_XS.gguf b/webrl-llama-3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..c011cd7 --- /dev/null +++ b/webrl-llama-3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a523d5afebf03f2910db68ff36e5bc53aedf9ecfc298be5214cc6e07486a444 +size 4484363936 diff --git a/webrl-llama-3.1-8b.Q2_K.gguf b/webrl-llama-3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..d1b8889 --- /dev/null +++ b/webrl-llama-3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40270c83e998046bacb9b4cff3e572e9aaf22623544e95876be42d179c082f48 +size 3179132576 diff --git a/webrl-llama-3.1-8b.Q3_K_L.gguf b/webrl-llama-3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..6dc1e7b --- /dev/null +++ b/webrl-llama-3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7e25e9a75183080de24d627884eeaa0f75561c1a87ea972fa26091e87e69ef +size 4321957536 diff --git a/webrl-llama-3.1-8b.Q3_K_M.gguf b/webrl-llama-3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..aa0cc69 --- /dev/null +++ b/webrl-llama-3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09e3ed63cdc05c90c683815dd287c33c719dddcb80f6123befdd3dfaf0181fd +size 4018919072 diff --git a/webrl-llama-3.1-8b.Q3_K_S.gguf b/webrl-llama-3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..efd32f6 --- /dev/null +++ b/webrl-llama-3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df2c45410e6edefbbe8651e0d8f639175f4e961960c69373b506f3c028e1031a +size 3664500384 diff --git a/webrl-llama-3.1-8b.Q4_K_M.gguf b/webrl-llama-3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..4eeeafb --- /dev/null +++ b/webrl-llama-3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153c4414f1d75661d035142ce064d7881727e5120d4bc96d28a634749f29879e +size 4920735392 diff --git a/webrl-llama-3.1-8b.Q4_K_S.gguf b/webrl-llama-3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..76ef9fd --- /dev/null +++ b/webrl-llama-3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24479dd409b0fdcd604c8eb75e331b2f471e961c5651dd14be803a9d77a996a +size 4692670112 diff --git a/webrl-llama-3.1-8b.Q5_K_M.gguf b/webrl-llama-3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..2ad6548 --- /dev/null +++ b/webrl-llama-3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084a5a7342a44e7288739c6727a848d520aec4e2bacbaf91ddd5e5bee1510680 +size 5732988576 diff --git a/webrl-llama-3.1-8b.Q5_K_S.gguf b/webrl-llama-3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..c168ed0 --- /dev/null +++ b/webrl-llama-3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88da5c1ccec0449226e8226e7508d1144769d9815fff0dd5516a5d7524f02f2 +size 5599295136 diff --git a/webrl-llama-3.1-8b.Q6_K.gguf b/webrl-llama-3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..6252e7c --- /dev/null +++ b/webrl-llama-3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f252c5439995fb7f17b88f3e51cecb7b542c69a9edd60b40e42c940d1071a993 +size 6596007584 diff --git a/webrl-llama-3.1-8b.Q8_0.gguf b/webrl-llama-3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..6bbf072 --- /dev/null +++ b/webrl-llama-3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60ca749fe52d6a231ddd7ad441783f485b13c685bcf8f3da937c6aceb11ea6f +size 8540772000 diff --git a/webrl-llama-3.1-8b.f16.gguf b/webrl-llama-3.1-8b.f16.gguf new file mode 100644 index 0000000..03a04da --- /dev/null +++ b/webrl-llama-3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70203fd8d34c367f37fcb985ea051ebf312fc2cd2ff8be5b02d829b7872ee32f +size 16068892320