commit 674ecef3d890e5972198306157b313e5e091d093 Author: ModelHub XC Date: Wed Aug 5 12:31:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..70071ea --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.1-8b-instruct-ortho-v5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a141ef5 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v5 +language: +- en +library_name: transformers +license: wtfpl +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-instruct-ortho-v5-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-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-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v5-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v5.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-3.1-8b-instruct-ortho-v5.IQ4_XS.gguf b/llama-3.1-8b-instruct-ortho-v5.IQ4_XS.gguf new file mode 100644 index 0000000..843e048 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb688e76b9b5782c43deaa29ff7e80625f39c464b916fddc798bbe661a49c064 +size 4484363584 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q2_K.gguf b/llama-3.1-8b-instruct-ortho-v5.Q2_K.gguf new file mode 100644 index 0000000..46c802b --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22538ed8735f194c4e8a38f515164a62e74f2727dc7fbee827cf785c0575d47 +size 3179132224 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q3_K_L.gguf b/llama-3.1-8b-instruct-ortho-v5.Q3_K_L.gguf new file mode 100644 index 0000000..788e4cd --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6699e64368cf98a0475905bbe73be44a915d3b0e228b63980b88f238c1ac8c25 +size 4321957184 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q3_K_M.gguf b/llama-3.1-8b-instruct-ortho-v5.Q3_K_M.gguf new file mode 100644 index 0000000..562429f --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2795a7e7a160cdc220033b8031e8937314b058b3e93b82583693292374dffc +size 4018918720 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q3_K_S.gguf b/llama-3.1-8b-instruct-ortho-v5.Q3_K_S.gguf new file mode 100644 index 0000000..a5873a3 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73cbdb2589647650b70bfc8baf0769c308f004e82d99ae04c0f59f3d072a339 +size 3664500032 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q4_0_4_4.gguf b/llama-3.1-8b-instruct-ortho-v5.Q4_0_4_4.gguf new file mode 100644 index 0000000..6341351 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca790b4920d685e488e39ee7c97938867e231eed56819d35e9a931533e3839a +size 4661212480 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q4_K_M.gguf b/llama-3.1-8b-instruct-ortho-v5.Q4_K_M.gguf new file mode 100644 index 0000000..e1ef61d --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecdbe631f6b7a70319d90494a2d2f75e6ea033960176613d3003b4a3eaad0e3 +size 4920735040 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q4_K_S.gguf b/llama-3.1-8b-instruct-ortho-v5.Q4_K_S.gguf new file mode 100644 index 0000000..ef81269 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841fe428a46d21a3ccf871f55c17a5b8ac5307bf877ace690b97486bd9f87f0d +size 4692669760 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q5_K_M.gguf b/llama-3.1-8b-instruct-ortho-v5.Q5_K_M.gguf new file mode 100644 index 0000000..7729cfc --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675de3083e6930c92cd67f86722e0cbb478cf3ac4edf34697ac7934057340bdf +size 5732988224 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q5_K_S.gguf b/llama-3.1-8b-instruct-ortho-v5.Q5_K_S.gguf new file mode 100644 index 0000000..d51a4ea --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e659e6aa39287a17ae36dbaed2422440f8e2cca3be10a12a4409e08b0cd7e0e +size 5599294784 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q6_K.gguf b/llama-3.1-8b-instruct-ortho-v5.Q6_K.gguf new file mode 100644 index 0000000..5902eaa --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18dca525b363ed00f812c63cf9a9af3f5b67fbc1c911de4b9a1e41c2a3275ca +size 6596007232 diff --git a/llama-3.1-8b-instruct-ortho-v5.Q8_0.gguf b/llama-3.1-8b-instruct-ortho-v5.Q8_0.gguf new file mode 100644 index 0000000..81cc904 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ab21aa51be8df0fe1a25a9de8bd16d0a714fbb4a7f93d4a85c0c06750c4f66 +size 8540771648 diff --git a/llama-3.1-8b-instruct-ortho-v5.f16.gguf b/llama-3.1-8b-instruct-ortho-v5.f16.gguf new file mode 100644 index 0000000..5f72115 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb3909800cbc30000785158cc06d518e24b9a6282349fcd766548be00cedeef +size 16068891968