commit 0e0260a94d24838280165c510b3343a53432703e Author: ModelHub XC Date: Sat Sep 26 05:11:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3_8B_norobots-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5477591 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama3_8B_norobots.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3_8B_norobots.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..27ca7c1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: monsterapi/llama3_8B_norobots +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + +static quants of https://huggingface.co/monsterapi/llama3_8B_norobots + + +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/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3_8B_norobots-GGUF/resolve/main/llama3_8B_norobots.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/llama3_8B_norobots.IQ3_M.gguf b/llama3_8B_norobots.IQ3_M.gguf new file mode 100644 index 0000000..26b6b05 --- /dev/null +++ b/llama3_8B_norobots.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f7d74052a5dee9376751fcaba631d0483d84f10726b4919e0924deb8085594 +size 3785335648 diff --git a/llama3_8B_norobots.IQ3_S.gguf b/llama3_8B_norobots.IQ3_S.gguf new file mode 100644 index 0000000..f9e0373 --- /dev/null +++ b/llama3_8B_norobots.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a73fd4b086ea1dd1d4bb9800317a966843a14d106a5dda948022211d1760d4 +size 3682837344 diff --git a/llama3_8B_norobots.IQ3_XS.gguf b/llama3_8B_norobots.IQ3_XS.gguf new file mode 100644 index 0000000..1ee3d71 --- /dev/null +++ b/llama3_8B_norobots.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bcaadb21c804822b835ed767afb2fdfa698fb7396ce23a6a322298fe4a5e28 +size 3519259488 diff --git a/llama3_8B_norobots.IQ4_XS.gguf b/llama3_8B_norobots.IQ4_XS.gguf new file mode 100644 index 0000000..a611963 --- /dev/null +++ b/llama3_8B_norobots.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6de5d0cd6e382cc006a5f216a90108c0826359c900bc362f3b98f5f9c49411 +size 4484875104 diff --git a/llama3_8B_norobots.Q2_K.gguf b/llama3_8B_norobots.Q2_K.gguf new file mode 100644 index 0000000..746df3b --- /dev/null +++ b/llama3_8B_norobots.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6cbc78800fe723b352b587c9abaca7aaf7998f5a1f067407dd764b29e467cce +size 3179643744 diff --git a/llama3_8B_norobots.Q3_K_L.gguf b/llama3_8B_norobots.Q3_K_L.gguf new file mode 100644 index 0000000..c9ba032 --- /dev/null +++ b/llama3_8B_norobots.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e931cb2695d9359a0f6ee386252b211bef20845e5fb0971d91cd84b4a0acd163 +size 4322468704 diff --git a/llama3_8B_norobots.Q3_K_M.gguf b/llama3_8B_norobots.Q3_K_M.gguf new file mode 100644 index 0000000..6d38886 --- /dev/null +++ b/llama3_8B_norobots.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2ea8b4696ada07144e5a7bed4cd69913f798aa3753cfc04be7871e442b928e +size 4019430240 diff --git a/llama3_8B_norobots.Q3_K_S.gguf b/llama3_8B_norobots.Q3_K_S.gguf new file mode 100644 index 0000000..8e68d86 --- /dev/null +++ b/llama3_8B_norobots.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd45d7714b67d863003b7fa3c4fc79067193033cf109429484e19adc6a1d34e9 +size 3665011552 diff --git a/llama3_8B_norobots.Q4_K_M.gguf b/llama3_8B_norobots.Q4_K_M.gguf new file mode 100644 index 0000000..a2254fa --- /dev/null +++ b/llama3_8B_norobots.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad36c16fb94c0aa8c9265180fc7a86518d2f1b18f7a70b381cf4664df302b2b6 +size 4921246560 diff --git a/llama3_8B_norobots.Q4_K_S.gguf b/llama3_8B_norobots.Q4_K_S.gguf new file mode 100644 index 0000000..bbb357b --- /dev/null +++ b/llama3_8B_norobots.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:852fddd7e850e3277898057f61ac9526e0c714795ea290edf83f27985260313c +size 4693181280 diff --git a/llama3_8B_norobots.Q5_K_M.gguf b/llama3_8B_norobots.Q5_K_M.gguf new file mode 100644 index 0000000..b204c46 --- /dev/null +++ b/llama3_8B_norobots.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9c3176a2b794ec359553ff5440d130af3a7bdfc4b0de0cb0ae18ddb68f6455 +size 5733499744 diff --git a/llama3_8B_norobots.Q5_K_S.gguf b/llama3_8B_norobots.Q5_K_S.gguf new file mode 100644 index 0000000..750bfb5 --- /dev/null +++ b/llama3_8B_norobots.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:650d0a791b310d6a95834ec66e4cad29157f2eaea7c98dead08e180910a20aa7 +size 5599806304 diff --git a/llama3_8B_norobots.Q6_K.gguf b/llama3_8B_norobots.Q6_K.gguf new file mode 100644 index 0000000..732145d --- /dev/null +++ b/llama3_8B_norobots.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed9d9c830e6cd61d1531803f5433e737c3e7521e7952af718b47579b28440ec +size 6596518752 diff --git a/llama3_8B_norobots.Q8_0.gguf b/llama3_8B_norobots.Q8_0.gguf new file mode 100644 index 0000000..9ced7a1 --- /dev/null +++ b/llama3_8B_norobots.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155506d9620254edddd3028da8c06deae577b8d5e6c12d5e992d9730c76d1775 +size 8541283168 diff --git a/llama3_8B_norobots.f16.gguf b/llama3_8B_norobots.f16.gguf new file mode 100644 index 0000000..7ba5ac6 --- /dev/null +++ b/llama3_8B_norobots.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4dd531e796e23dd9e52e69a13f6ec8d3451f5b445da41e7870c690aa8b49b5c +size 16069403488