commit 620f9ba8232a71e6146fa18692cf332afd97b7b9 Author: ModelHub XC Date: Thu Jun 18 09:10:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-instruct-diverce-v2.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3e7393d --- /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-instruct-diverce-v2.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-instruct-diverce-v2.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e81c93d --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: sel303/llama3-instruct-diverce-v2.0 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/sel303/llama3-instruct-diverce-v2.0 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-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/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-instruct-diverce-v2.0-GGUF/resolve/main/llama3-instruct-diverce-v2.0.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/llama3-instruct-diverce-v2.0.IQ4_XS.gguf b/llama3-instruct-diverce-v2.0.IQ4_XS.gguf new file mode 100644 index 0000000..229f7c1 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ccd4313bdc589e9fdeb822b1dc519f3fa767cecf4eab1c6da8d396ecca52d7b +size 4484363328 diff --git a/llama3-instruct-diverce-v2.0.Q2_K.gguf b/llama3-instruct-diverce-v2.0.Q2_K.gguf new file mode 100644 index 0000000..fb82d62 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a93eab650a3b2e8b74a02ebce20d8201e6d52a9d3291ce66a7ee00cfb70fa3 +size 3179131968 diff --git a/llama3-instruct-diverce-v2.0.Q3_K_L.gguf b/llama3-instruct-diverce-v2.0.Q3_K_L.gguf new file mode 100644 index 0000000..98914fe --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c2e8090c967f4dcce0d3bea8e1bfcb971bd7a7ff99d17ea2f01a49e7cb416b +size 4321956928 diff --git a/llama3-instruct-diverce-v2.0.Q3_K_M.gguf b/llama3-instruct-diverce-v2.0.Q3_K_M.gguf new file mode 100644 index 0000000..c2520f9 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a936632aa1192126b6ffdd925395b67c0b9ab533c21e2cf7d7f279dc68797cb7 +size 4018918464 diff --git a/llama3-instruct-diverce-v2.0.Q3_K_S.gguf b/llama3-instruct-diverce-v2.0.Q3_K_S.gguf new file mode 100644 index 0000000..f2ce567 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e26031cf1126c1d761b05a2ff46928488a3277a1651e674cb4e97a75236a109 +size 3664499776 diff --git a/llama3-instruct-diverce-v2.0.Q4_K_M.gguf b/llama3-instruct-diverce-v2.0.Q4_K_M.gguf new file mode 100644 index 0000000..a6c5086 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da71c0b87a84132a91b4508773bc70bfa2a15eeefd7c44d1a564d60a4c89bcf +size 4920734784 diff --git a/llama3-instruct-diverce-v2.0.Q4_K_S.gguf b/llama3-instruct-diverce-v2.0.Q4_K_S.gguf new file mode 100644 index 0000000..e65f20f --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afb32e5f063df2546263c7c73708104b3675e08c55e97742a343ee450307d749 +size 4692669504 diff --git a/llama3-instruct-diverce-v2.0.Q5_K_M.gguf b/llama3-instruct-diverce-v2.0.Q5_K_M.gguf new file mode 100644 index 0000000..b2d0a31 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3613f2e95d0ce45083bd2b20b03d02ce921adb96a79e107cbb0ae760e2a77d5c +size 5732987968 diff --git a/llama3-instruct-diverce-v2.0.Q5_K_S.gguf b/llama3-instruct-diverce-v2.0.Q5_K_S.gguf new file mode 100644 index 0000000..905a681 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ea3858ca820d8d7eec0763113d8aef1cf298e8bb4843e57617d16cea002535 +size 5599294528 diff --git a/llama3-instruct-diverce-v2.0.Q6_K.gguf b/llama3-instruct-diverce-v2.0.Q6_K.gguf new file mode 100644 index 0000000..620a76a --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d75c349253ddbbaa044460b1d15e10559b84fe2b18277e0326ab7c15b9223b6 +size 6596006976 diff --git a/llama3-instruct-diverce-v2.0.Q8_0.gguf b/llama3-instruct-diverce-v2.0.Q8_0.gguf new file mode 100644 index 0000000..c461381 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371f2a1f312bef2a5b3001189cc34fd34405097988f973764c661ead3e3b1555 +size 8540771392 diff --git a/llama3-instruct-diverce-v2.0.f16.gguf b/llama3-instruct-diverce-v2.0.f16.gguf new file mode 100644 index 0000000..9bf4b19 --- /dev/null +++ b/llama3-instruct-diverce-v2.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6794fd34a4108f2b0663f81ff08e654ab7c9960b6f7467f9fc1f7e119414b728 +size 16068891712