commit 10e5bec4274b80ff5e636fc90d2cbda4d2864299 Author: ModelHub XC Date: Thu Jun 18 05:20:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8a6f92f --- /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-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-instruct-ortho-v3.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..198b061 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3 +language: +- en +library_name: transformers +license: wtfpl +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-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-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.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-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-instruct-ortho-v3-GGUF/resolve/main/llama-3.1-8b-instruct-ortho-v3.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-v3.IQ4_XS.gguf b/llama-3.1-8b-instruct-ortho-v3.IQ4_XS.gguf new file mode 100644 index 0000000..c3bc8d0 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b592b4a69657473b1ce0de1a6da9f406936e56c9d8834f8d727b927bba0f8b +size 4484363584 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q2_K.gguf b/llama-3.1-8b-instruct-ortho-v3.Q2_K.gguf new file mode 100644 index 0000000..83450e6 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0053ef1523927edf0fa90aa95214b95f51a07ec5fef4a69dd35b799c31bfcc24 +size 3179132224 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q3_K_L.gguf b/llama-3.1-8b-instruct-ortho-v3.Q3_K_L.gguf new file mode 100644 index 0000000..cb3351f --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9543fa0d7b8b128d0111f5eaf18d3c32a9c09dd1d008a87873ac58fb4beb0a4a +size 4321957184 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q3_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.Q3_K_M.gguf new file mode 100644 index 0000000..700ca32 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1f04b8ab0941fec0739768a7b0152b3b68071e2a6179ecce614a1867e02dec +size 4018918720 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q3_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.Q3_K_S.gguf new file mode 100644 index 0000000..01dad1d --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd48948b742f82ce0a716f5baddc610e881c4a68bc7cb831f276425713d83174 +size 3664500032 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q4_0_4_4.gguf b/llama-3.1-8b-instruct-ortho-v3.Q4_0_4_4.gguf new file mode 100644 index 0000000..96a4421 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b7e718f5fa94bde471e45b37bec72baeff1088fb1527016d3a5d74669048ba +size 4661212480 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q4_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.Q4_K_M.gguf new file mode 100644 index 0000000..8612382 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1dd638ed80019f5cd61240d1f06fd1333413f61427bef4d288c5b8cd9d8cea +size 4920735040 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q4_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.Q4_K_S.gguf new file mode 100644 index 0000000..5555634 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965d7f102aa2ce02260a0c961b0c21d81565995158bcba43c4df6f65b76d64bc +size 4692669760 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q5_K_M.gguf b/llama-3.1-8b-instruct-ortho-v3.Q5_K_M.gguf new file mode 100644 index 0000000..3c1627c --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:076b3992ac0bbd0ef7b0e7d48e70db1ebf44bb174f95de594895dd851f9d5c21 +size 5732988224 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q5_K_S.gguf b/llama-3.1-8b-instruct-ortho-v3.Q5_K_S.gguf new file mode 100644 index 0000000..7e0453a --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbdb555831cd705bd8545ba27ea3708177808b980f3c7d1625606058a9a0e6a9 +size 5599294784 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q6_K.gguf b/llama-3.1-8b-instruct-ortho-v3.Q6_K.gguf new file mode 100644 index 0000000..4469f20 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7fa90f0e2f65635654ce365f74fd6ddf9928e326d6c08d53426749758aec42 +size 6596007232 diff --git a/llama-3.1-8b-instruct-ortho-v3.Q8_0.gguf b/llama-3.1-8b-instruct-ortho-v3.Q8_0.gguf new file mode 100644 index 0000000..acff994 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b77dce658d84a1e754a35fc8955d8f60be16c2ce3621d1968497994f9d930e9 +size 8540771648 diff --git a/llama-3.1-8b-instruct-ortho-v3.f16.gguf b/llama-3.1-8b-instruct-ortho-v3.f16.gguf new file mode 100644 index 0000000..c92e2c3 --- /dev/null +++ b/llama-3.1-8b-instruct-ortho-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:360a64250c6bbba3ad1e534cad3c5bb5a5ce13a43b43fa0c5d23da633ea45409 +size 16068891968