commit fa48b9ca3803e97c79d0e3d060fa85634ad739da Author: ModelHub XC Date: Thu May 7 20:58:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-bophades-v3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40349a0 --- /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-v3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-bophades-v3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd6e87c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: nbeerbower/llama-3-bophades-v3-8B +datasets: +- jondurbin/truthy-dpo-v0.1 +- kyujinpy/orca_math_dpo +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/llama-3-bophades-v3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-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-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-bophades-v3-8B-GGUF/resolve/main/llama-3-bophades-v3-8B.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/llama-3-bophades-v3-8B.IQ4_XS.gguf b/llama-3-bophades-v3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..e8b9641 --- /dev/null +++ b/llama-3-bophades-v3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1d131a8d5d3cd703081381e887fa48af55e4f1c1331d4f2c96057c405d77281 +size 4484364064 diff --git a/llama-3-bophades-v3-8B.Q2_K.gguf b/llama-3-bophades-v3-8B.Q2_K.gguf new file mode 100644 index 0000000..fd1489c --- /dev/null +++ b/llama-3-bophades-v3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3763b4d54d98f5261fbeec056e1a6bcddeaa0a5a3a701c034a3c7a55216eb9 +size 3179132704 diff --git a/llama-3-bophades-v3-8B.Q3_K_L.gguf b/llama-3-bophades-v3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..2dbc067 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f8a789ce947054e2dd66e88ad71da8a06cb270980154d93539586221e82f72 +size 4321957664 diff --git a/llama-3-bophades-v3-8B.Q3_K_M.gguf b/llama-3-bophades-v3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..e9e36c0 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223ce790370de71dea3169edcb515f09f8e078ddae77b419ef8224c4f46e1fb5 +size 4018919200 diff --git a/llama-3-bophades-v3-8B.Q3_K_S.gguf b/llama-3-bophades-v3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..1206fcc --- /dev/null +++ b/llama-3-bophades-v3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed9c3dabea3ace7674131df05cf7c8aedc4276f9c857c4a1e01bb147bb02e59 +size 3664500512 diff --git a/llama-3-bophades-v3-8B.Q4_K_M.gguf b/llama-3-bophades-v3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a6dcf22 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f3873eeb78cd68e787f6a83a0a20e4849d59734ce93e29e9e3ed8bd5f2e0d1 +size 4920735520 diff --git a/llama-3-bophades-v3-8B.Q4_K_S.gguf b/llama-3-bophades-v3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..d646b67 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daf0431902f3a8795d538b6468890173dd3157598662a5839aefebea6dc540f +size 4692670240 diff --git a/llama-3-bophades-v3-8B.Q5_K_M.gguf b/llama-3-bophades-v3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..eae6e6d --- /dev/null +++ b/llama-3-bophades-v3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2bb14866afdd4e91f262e3681fc96f56d40ff6e41c950a6aefa351dddd94bf6 +size 5732988704 diff --git a/llama-3-bophades-v3-8B.Q5_K_S.gguf b/llama-3-bophades-v3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..df349ef --- /dev/null +++ b/llama-3-bophades-v3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6732f772366e053fdc24e7c4dbe99fc30dcdcf231dd5829f851db1a65b268774 +size 5599295264 diff --git a/llama-3-bophades-v3-8B.Q6_K.gguf b/llama-3-bophades-v3-8B.Q6_K.gguf new file mode 100644 index 0000000..b6300f1 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3686206306f8b5e064561add3f9ceade8cb0622fd0696d6514ed37cab2ece997 +size 6596007712 diff --git a/llama-3-bophades-v3-8B.Q8_0.gguf b/llama-3-bophades-v3-8B.Q8_0.gguf new file mode 100644 index 0000000..49581d7 --- /dev/null +++ b/llama-3-bophades-v3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cddd097f06c614f6c858820296e4d3e3fab2b5b560eb27a9bca7236dade6529 +size 8540772128 diff --git a/llama-3-bophades-v3-8B.f16.gguf b/llama-3-bophades-v3-8B.f16.gguf new file mode 100644 index 0000000..091e283 --- /dev/null +++ b/llama-3-bophades-v3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c5cc1088582bb921194fb1aba75a048d390044abdb17d0c06fef93d720018a +size 16068892448