commit bbfe6739795d9146d14811cadd89a616f9879d47 Author: ModelHub XC Date: Sun Aug 2 11:31:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Nerdy-RP-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e12e95b --- /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 +Llama-3-Nerdy-RP-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Nerdy-RP-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Nerdy-RP-8B.IQ3_M.gguf b/Llama-3-Nerdy-RP-8B.IQ3_M.gguf new file mode 100644 index 0000000..842c101 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ade208fed549975553e7ca0f95709ecf63affb8a08c007c8cc80c69e55d270e +size 3784823072 diff --git a/Llama-3-Nerdy-RP-8B.IQ3_S.gguf b/Llama-3-Nerdy-RP-8B.IQ3_S.gguf new file mode 100644 index 0000000..5db56e5 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef6c54f7f45436c921ca3b0d5aa1e023e31c396a04e327b12c3dcad1a9840b0 +size 3682324768 diff --git a/Llama-3-Nerdy-RP-8B.IQ3_XS.gguf b/Llama-3-Nerdy-RP-8B.IQ3_XS.gguf new file mode 100644 index 0000000..246a05b --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78412d9569bf06e5f5248df1194c830b4aff86fdff3b6a00037712143951deee +size 3518746912 diff --git a/Llama-3-Nerdy-RP-8B.IQ4_XS.gguf b/Llama-3-Nerdy-RP-8B.IQ4_XS.gguf new file mode 100644 index 0000000..b27215e --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157d9b66c914513915516d1c0a9e29abc0aa1559163aa70afadb4b5e50523750 +size 4484362528 diff --git a/Llama-3-Nerdy-RP-8B.Q2_K.gguf b/Llama-3-Nerdy-RP-8B.Q2_K.gguf new file mode 100644 index 0000000..4b3be20 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd5f68d87591ece4a9037e052bf5d21f47b4f633f57f72347f7b5818b54f19d +size 3179131168 diff --git a/Llama-3-Nerdy-RP-8B.Q3_K_L.gguf b/Llama-3-Nerdy-RP-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0a9523c --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee7808751088c12a2cfbaafb7a261ad67338fa5811c3025ee7668c4521e24cd +size 4321956128 diff --git a/Llama-3-Nerdy-RP-8B.Q3_K_M.gguf b/Llama-3-Nerdy-RP-8B.Q3_K_M.gguf new file mode 100644 index 0000000..aed9ef4 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdcce0767d025c66ea274fcce22ff528f2731a04c9c9836c4e00c6a83ce4415 +size 4018917664 diff --git a/Llama-3-Nerdy-RP-8B.Q3_K_S.gguf b/Llama-3-Nerdy-RP-8B.Q3_K_S.gguf new file mode 100644 index 0000000..cdc3cfd --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b8ce9f77e78de39b5e8f4561a48fb5f70d7979d2115687613be58ed36106b3 +size 3664498976 diff --git a/Llama-3-Nerdy-RP-8B.Q4_K_M.gguf b/Llama-3-Nerdy-RP-8B.Q4_K_M.gguf new file mode 100644 index 0000000..49bf0e2 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e851d79e9963892893880c4261884ea4bb49e63adce088532aa6b5577a8f1f93 +size 4920733984 diff --git a/Llama-3-Nerdy-RP-8B.Q4_K_S.gguf b/Llama-3-Nerdy-RP-8B.Q4_K_S.gguf new file mode 100644 index 0000000..94bd2b2 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da754f4526bcf960a666b6a39d5eb29403e72bd5a7792efcd00bfc801d96f1c +size 4692668704 diff --git a/Llama-3-Nerdy-RP-8B.Q5_K_M.gguf b/Llama-3-Nerdy-RP-8B.Q5_K_M.gguf new file mode 100644 index 0000000..bf14fd4 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96acc358b056b2a285d119dafcb100730ac01a76c64eec35727d3e7ef03bc2b3 +size 5732987168 diff --git a/Llama-3-Nerdy-RP-8B.Q5_K_S.gguf b/Llama-3-Nerdy-RP-8B.Q5_K_S.gguf new file mode 100644 index 0000000..4a9ec61 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55febcc74a4ce06c3722fe353e01b7050ce2b87d078f5b010ee866778e13251f +size 5599293728 diff --git a/Llama-3-Nerdy-RP-8B.Q6_K.gguf b/Llama-3-Nerdy-RP-8B.Q6_K.gguf new file mode 100644 index 0000000..c518c4b --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b53f1b1b2ff724707a2893d2c0762deb0c8047183da90b332128a410684b3e +size 6596006176 diff --git a/Llama-3-Nerdy-RP-8B.Q8_0.gguf b/Llama-3-Nerdy-RP-8B.Q8_0.gguf new file mode 100644 index 0000000..7643d0e --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02bc400b7eb5cf1a0939852c69ba0591a5279245381f05b6a809487120c826c +size 8540770592 diff --git a/Llama-3-Nerdy-RP-8B.f16.gguf b/Llama-3-Nerdy-RP-8B.f16.gguf new file mode 100644 index 0000000..63f8639 --- /dev/null +++ b/Llama-3-Nerdy-RP-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ecd4895816c27b06cd73653fc7c7714c65c951711330d6989ddc7422ea7b364 +size 16068890912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5063d27 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: Azazelle/Llama-3-Nerdy-RP-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Azazelle/Llama-3-Nerdy-RP-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-i1-GGUF +## 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/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Nerdy-RP-8B-GGUF/resolve/main/Llama-3-Nerdy-RP-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. + +