commit 091e423c4b2cbc7d305041d233640e5144cb204f Author: ModelHub XC Date: Sat May 9 11:54:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-diverce-v4.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9d5956 --- /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 +llama3-diverce-v4.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-diverce-v4.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1547f9c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: sel303/llama3-diverce-v4.5 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sel303/llama3-diverce-v4.5 + + +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-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-diverce-v4.5-GGUF/resolve/main/llama3-diverce-v4.5.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/llama3-diverce-v4.5.IQ4_XS.gguf b/llama3-diverce-v4.5.IQ4_XS.gguf new file mode 100644 index 0000000..00fd618 --- /dev/null +++ b/llama3-diverce-v4.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10bd0d461641d01b72e9e7787e47c03cf3e7a8685803689c2656084ad9b9f976 +size 4484363328 diff --git a/llama3-diverce-v4.5.Q2_K.gguf b/llama3-diverce-v4.5.Q2_K.gguf new file mode 100644 index 0000000..ee1e155 --- /dev/null +++ b/llama3-diverce-v4.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c186859d467212ba8abd3607d3ad383745d4ca18d0691f7935e156ef3f32c8f0 +size 3179131968 diff --git a/llama3-diverce-v4.5.Q3_K_L.gguf b/llama3-diverce-v4.5.Q3_K_L.gguf new file mode 100644 index 0000000..e185e7b --- /dev/null +++ b/llama3-diverce-v4.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760edc2291b79401b02749b0834469a57cdce54355af2dad12c206238d67a501 +size 4321956928 diff --git a/llama3-diverce-v4.5.Q3_K_M.gguf b/llama3-diverce-v4.5.Q3_K_M.gguf new file mode 100644 index 0000000..551e596 --- /dev/null +++ b/llama3-diverce-v4.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30909a00224f13ddbd4c817f721408269b9fe0567eb5bafa012c97d9a2c82b76 +size 4018918464 diff --git a/llama3-diverce-v4.5.Q3_K_S.gguf b/llama3-diverce-v4.5.Q3_K_S.gguf new file mode 100644 index 0000000..f49f7ec --- /dev/null +++ b/llama3-diverce-v4.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c164f2107c49f171578b497ad079b7114af92f103067f6b6e95d730562610ae4 +size 3664499776 diff --git a/llama3-diverce-v4.5.Q4_K_M.gguf b/llama3-diverce-v4.5.Q4_K_M.gguf new file mode 100644 index 0000000..7a0fb1c --- /dev/null +++ b/llama3-diverce-v4.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df44e86c482be796eebd826f2becd8a8cceded1f5f973247339446513f2c5bf3 +size 4920734784 diff --git a/llama3-diverce-v4.5.Q4_K_S.gguf b/llama3-diverce-v4.5.Q4_K_S.gguf new file mode 100644 index 0000000..7d4de26 --- /dev/null +++ b/llama3-diverce-v4.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c55de891645b8393fb8932843c9b68ec6d57760c6701732549fc0e91565e316 +size 4692669504 diff --git a/llama3-diverce-v4.5.Q5_K_M.gguf b/llama3-diverce-v4.5.Q5_K_M.gguf new file mode 100644 index 0000000..0eecdc8 --- /dev/null +++ b/llama3-diverce-v4.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9fb8785c8c2a590901fb3c49ce1032cb52f91968e18fcbca78f2da9d18a5aa +size 5732987968 diff --git a/llama3-diverce-v4.5.Q5_K_S.gguf b/llama3-diverce-v4.5.Q5_K_S.gguf new file mode 100644 index 0000000..79598b8 --- /dev/null +++ b/llama3-diverce-v4.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2fbc1d3382da3a3e8615e6b069c37e64e179f15d2b900168359984d2d4430db +size 5599294528 diff --git a/llama3-diverce-v4.5.Q6_K.gguf b/llama3-diverce-v4.5.Q6_K.gguf new file mode 100644 index 0000000..f11311d --- /dev/null +++ b/llama3-diverce-v4.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf025e5c896c131c1778aca2d7b3651ea3aa0e35f2ea76ba0ef33e73792fbe7 +size 6596006976 diff --git a/llama3-diverce-v4.5.Q8_0.gguf b/llama3-diverce-v4.5.Q8_0.gguf new file mode 100644 index 0000000..ba6cb6b --- /dev/null +++ b/llama3-diverce-v4.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc61d94c5b217f5a8202f742695ed1bac727dd5349b98c3a9046a919edfd0d4f +size 8540771392 diff --git a/llama3-diverce-v4.5.f16.gguf b/llama3-diverce-v4.5.f16.gguf new file mode 100644 index 0000000..6380ab9 --- /dev/null +++ b/llama3-diverce-v4.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d789f88fce35dd73ac81db71e484bd78ffd4efef069917bc2bf9a1a7835f6a6 +size 16068891712