commit a085f1a6664090beaf8971ec1ee4d736268022ac Author: ModelHub XC Date: Mon Apr 13 19:18:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Artificium-llama3.1-8B-001-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e47196d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Artificium-llama3.1-8B-001.f16.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Artificium-llama3.1-8B-001.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Artificium-llama3.1-8B-001.IQ3_M.gguf b/Artificium-llama3.1-8B-001.IQ3_M.gguf new file mode 100644 index 0000000..5062059 --- /dev/null +++ b/Artificium-llama3.1-8B-001.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdf90e402d3d3f192f8c12e4b214840ac2266233a849bc6310379bec7269cd9 +size 3784828320 diff --git a/Artificium-llama3.1-8B-001.IQ3_S.gguf b/Artificium-llama3.1-8B-001.IQ3_S.gguf new file mode 100644 index 0000000..5472449 --- /dev/null +++ b/Artificium-llama3.1-8B-001.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea42b8d2b1ab7b77afafa15ed95b0b2e708d6d21adf6fbdc23f7002b2a9c8e1 +size 3682330016 diff --git a/Artificium-llama3.1-8B-001.IQ3_XS.gguf b/Artificium-llama3.1-8B-001.IQ3_XS.gguf new file mode 100644 index 0000000..c597f79 --- /dev/null +++ b/Artificium-llama3.1-8B-001.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62362eb181986d5255917d8ba547042c5b72fc13d021d7782322480b47bc9bf2 +size 3518752160 diff --git a/Artificium-llama3.1-8B-001.IQ4_XS.gguf b/Artificium-llama3.1-8B-001.IQ4_XS.gguf new file mode 100644 index 0000000..accfeb5 --- /dev/null +++ b/Artificium-llama3.1-8B-001.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e39dfa5c7e8ade33a543c5ffd2588be54c4b22cbf072bc6599419c27d7ff4c4 +size 4484367776 diff --git a/Artificium-llama3.1-8B-001.Q2_K.gguf b/Artificium-llama3.1-8B-001.Q2_K.gguf new file mode 100644 index 0000000..11f76a7 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772088507d99d41ac4b2e8724cf6581ee59d3be40d802c947e92180b1d5f4121 +size 3179136416 diff --git a/Artificium-llama3.1-8B-001.Q3_K_L.gguf b/Artificium-llama3.1-8B-001.Q3_K_L.gguf new file mode 100644 index 0000000..d290db6 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fde9ea405b0ca8d86c91191eedaa26c18cf351d7980658a9449c4ba301fffa1 +size 4321961376 diff --git a/Artificium-llama3.1-8B-001.Q3_K_M.gguf b/Artificium-llama3.1-8B-001.Q3_K_M.gguf new file mode 100644 index 0000000..64ed2ae --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7e8219dced31cea91dd57891e1ba374e6b8263c31019e013a8e93d4f2761bb +size 4018922912 diff --git a/Artificium-llama3.1-8B-001.Q3_K_S.gguf b/Artificium-llama3.1-8B-001.Q3_K_S.gguf new file mode 100644 index 0000000..fba4f3b --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e999d6d1d794f0936e997e0f21039ef2b1bc36d8c6ad46f8eb263355fe1966 +size 3664504224 diff --git a/Artificium-llama3.1-8B-001.Q4_K_M.gguf b/Artificium-llama3.1-8B-001.Q4_K_M.gguf new file mode 100644 index 0000000..621576d --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8488214fe43b21f68b8616cee77c4ad95c8ee4e709544e425c0a7ec7394cd2 +size 4920739232 diff --git a/Artificium-llama3.1-8B-001.Q4_K_S.gguf b/Artificium-llama3.1-8B-001.Q4_K_S.gguf new file mode 100644 index 0000000..3814e90 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0124668b1601ed4f687124b54dcdb65d882229d4b758d9c05d06a9f0404cf775 +size 4692673952 diff --git a/Artificium-llama3.1-8B-001.Q5_K_M.gguf b/Artificium-llama3.1-8B-001.Q5_K_M.gguf new file mode 100644 index 0000000..41ade41 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca4a5250e6661a393dabe88ec0843f8913bebf95fc47d99cfedda15d8086a92f +size 5732992416 diff --git a/Artificium-llama3.1-8B-001.Q5_K_S.gguf b/Artificium-llama3.1-8B-001.Q5_K_S.gguf new file mode 100644 index 0000000..02c0ee3 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:455e54574313ca092a8378d913855e666ba4b6dce66d8fc111f6e1e656877a6e +size 5599298976 diff --git a/Artificium-llama3.1-8B-001.Q6_K.gguf b/Artificium-llama3.1-8B-001.Q6_K.gguf new file mode 100644 index 0000000..8b6c7c9 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c084ccc7b334092d3e9d56b53fa3b94cba3f4ebe1600283a746b730064eeb8e +size 6596011424 diff --git a/Artificium-llama3.1-8B-001.Q8_0.gguf b/Artificium-llama3.1-8B-001.Q8_0.gguf new file mode 100644 index 0000000..f519469 --- /dev/null +++ b/Artificium-llama3.1-8B-001.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53164d45c4b67b697e2eb6dd5411ae4e1ce4687507bd554fcd37797c41bef35 +size 8540775840 diff --git a/Artificium-llama3.1-8B-001.f16.gguf b/Artificium-llama3.1-8B-001.f16.gguf new file mode 100644 index 0000000..bf96aec --- /dev/null +++ b/Artificium-llama3.1-8B-001.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478e6b29304cf05c00bbb0718bb2d56b1b130a1d4ea8ab756dd4d78171790f8b +size 16068896160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1fe8153 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: AGI-0/smartllama3.1-8B-001 +language: +- en +library_name: transformers +license: unknown +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AGI-0/smartllama3.1-8B-001 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-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/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Artificium-llama3.1-8B-001-GGUF/resolve/main/Artificium-llama3.1-8B-001.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. + +