commit 6ee639a04091d77259c6e9dca4d43b48b412466e Author: ModelHub XC Date: Tue Aug 4 18:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-bophades-v1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8367c5 --- /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 +llama-3-bophades-v1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9cad516 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: nbeerbower/llama-3-bophades-v1-8B +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/llama-3-bophades-v1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-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-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v1-8B-GGUF/resolve/main/llama-3-bophades-v1-8B.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-3-bophades-v1-8B.IQ4_XS.gguf b/llama-3-bophades-v1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..0f6869a --- /dev/null +++ b/llama-3-bophades-v1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c5d9b7226a7f1aec6620d05e99df6da8579d784bacbd92c170b0995512ed64 +size 4484364896 diff --git a/llama-3-bophades-v1-8B.Q2_K.gguf b/llama-3-bophades-v1-8B.Q2_K.gguf new file mode 100644 index 0000000..e8dba26 --- /dev/null +++ b/llama-3-bophades-v1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca65ceecdd00f5096f98be625378246b1933190b2c063b6f1f762326dd05579d +size 3179133536 diff --git a/llama-3-bophades-v1-8B.Q3_K_L.gguf b/llama-3-bophades-v1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..15fd844 --- /dev/null +++ b/llama-3-bophades-v1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb322f0e6072b1db8553d1a26bddfb92a0d92bed6ab7fd6a9b991a1021367c0 +size 4321958496 diff --git a/llama-3-bophades-v1-8B.Q3_K_M.gguf b/llama-3-bophades-v1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..9a6f65d --- /dev/null +++ b/llama-3-bophades-v1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c115b8a455e5bb0cd86a63406f92bc18d578f73353ca2d08bd832de4b7d16c +size 4018920032 diff --git a/llama-3-bophades-v1-8B.Q3_K_S.gguf b/llama-3-bophades-v1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..95fac2d --- /dev/null +++ b/llama-3-bophades-v1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4057d834ffd3763c934d8b65b0fc6adce9c3282efd3225d602b279b06e31d63f +size 3664501344 diff --git a/llama-3-bophades-v1-8B.Q4_K_M.gguf b/llama-3-bophades-v1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..fcb7c6b --- /dev/null +++ b/llama-3-bophades-v1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec37351fc4df8af6cf5522e1bee1e1ef869505033f04065d6e3a279ab08ec4d +size 4920736352 diff --git a/llama-3-bophades-v1-8B.Q4_K_S.gguf b/llama-3-bophades-v1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..cd8724d --- /dev/null +++ b/llama-3-bophades-v1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b4bf07d3e22928105e240f0c4b5a5c9641a5f725b830b86a8ebd4def59009b +size 4692671072 diff --git a/llama-3-bophades-v1-8B.Q5_K_M.gguf b/llama-3-bophades-v1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..55e5aff --- /dev/null +++ b/llama-3-bophades-v1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6812821a5b0e2c358f569dba6c72142d922c37fd221c6ae5825244578f32198b +size 5732989536 diff --git a/llama-3-bophades-v1-8B.Q5_K_S.gguf b/llama-3-bophades-v1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..3ecd221 --- /dev/null +++ b/llama-3-bophades-v1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b6a7051f08ffd33d1cd1d447fbb3da5beb01a8697c767ec4a01435b473eaad +size 5599296096 diff --git a/llama-3-bophades-v1-8B.Q6_K.gguf b/llama-3-bophades-v1-8B.Q6_K.gguf new file mode 100644 index 0000000..904260d --- /dev/null +++ b/llama-3-bophades-v1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab524f99749ef8b2ab3d850a64df01947ec0bad8f4ab0362b031a613ba006c3 +size 6596008544 diff --git a/llama-3-bophades-v1-8B.Q8_0.gguf b/llama-3-bophades-v1-8B.Q8_0.gguf new file mode 100644 index 0000000..93827da --- /dev/null +++ b/llama-3-bophades-v1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb227af27738810e004ae19227b30f9af007082cc11e74b14200ae82da87dff +size 8540772960 diff --git a/llama-3-bophades-v1-8B.f16.gguf b/llama-3-bophades-v1-8B.f16.gguf new file mode 100644 index 0000000..a2a60ee --- /dev/null +++ b/llama-3-bophades-v1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44e52d6e87d17b66ed3e14a014962c77abfb11f2676982c7582f29c628ae182 +size 16068893280