commit f1f2a2fb1f6b3b849dc322b5522e1b947c5e5faa Author: ModelHub XC Date: Tue Oct 6 10:53:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..80ff9f4 --- /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-slerp-dolphin-sauce-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-slerp-dolphin-sauce-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b97d5a8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: nbeerbower/llama-3-slerp-dolphin-sauce-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-slerp-dolphin-sauce-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-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-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-slerp-dolphin-sauce-8B-GGUF/resolve/main/llama-3-slerp-dolphin-sauce-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-slerp-dolphin-sauce-8B.IQ4_XS.gguf b/llama-3-slerp-dolphin-sauce-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c3ef39c --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b28c893afc6b0fd5156730ae6879735d11163c7d6ba3dcdca64d085b44c8506 +size 4484363808 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q2_K.gguf b/llama-3-slerp-dolphin-sauce-8B.Q2_K.gguf new file mode 100644 index 0000000..78be8b0 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92108a3e2113966ab155aba4013166d9fe53cfcd462feb7179bf393bf01768a2 +size 3179132448 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q3_K_L.gguf b/llama-3-slerp-dolphin-sauce-8B.Q3_K_L.gguf new file mode 100644 index 0000000..b302f7b --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a458535799f2a22b2bb793f2b2f59d1c24fbb180a23432640f2b597d036ed18 +size 4321957408 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q3_K_M.gguf b/llama-3-slerp-dolphin-sauce-8B.Q3_K_M.gguf new file mode 100644 index 0000000..50a4677 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb406d73c88d20eccb7fe916208148cdee9cbaea69cfa003b71311425a213d96 +size 4018918944 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q3_K_S.gguf b/llama-3-slerp-dolphin-sauce-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9612e2f --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee51bf8ef3ae72a33b9708f3d3f2e2f9164836b5d197feb0559cf4c94fce0ae +size 3664500256 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q4_K_M.gguf b/llama-3-slerp-dolphin-sauce-8B.Q4_K_M.gguf new file mode 100644 index 0000000..f1a5307 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d12a9c95007ff9921b4bc6b71f544c98acc23f443a93f496d4ec5292422baf +size 4920735264 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q4_K_S.gguf b/llama-3-slerp-dolphin-sauce-8B.Q4_K_S.gguf new file mode 100644 index 0000000..0af6ea1 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4825446e1aaa8574f62d8cc2edf8186cec95b46590c942c1f7e098d75018526c +size 4692669984 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q5_K_M.gguf b/llama-3-slerp-dolphin-sauce-8B.Q5_K_M.gguf new file mode 100644 index 0000000..b49fce9 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f04b62fd33cc5ff1f961637c12a314a741082ea12f7fca5932df3dc9586846e +size 5732988448 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q5_K_S.gguf b/llama-3-slerp-dolphin-sauce-8B.Q5_K_S.gguf new file mode 100644 index 0000000..c5033eb --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd78cf600f9fa7cc91069f77214653683463a3ac0004793f26ba52f9f03b013d +size 5599295008 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q6_K.gguf b/llama-3-slerp-dolphin-sauce-8B.Q6_K.gguf new file mode 100644 index 0000000..cad30a3 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd7793a56eaf3258c1414831f59b8644a662454fb8e12bd20c56525ac09a7d41 +size 6596007456 diff --git a/llama-3-slerp-dolphin-sauce-8B.Q8_0.gguf b/llama-3-slerp-dolphin-sauce-8B.Q8_0.gguf new file mode 100644 index 0000000..b4c3ee5 --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee4428aaff3bff265514bd0cb6bf86d54394135013ee222b0862cd4350141474 +size 8540771872 diff --git a/llama-3-slerp-dolphin-sauce-8B.f16.gguf b/llama-3-slerp-dolphin-sauce-8B.f16.gguf new file mode 100644 index 0000000..74d26ab --- /dev/null +++ b/llama-3-slerp-dolphin-sauce-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8bc1e914dfde5841382462a7ad0345c08ff538ac1459f19b65675a2765ab21 +size 16068892192