commit 28ef884141a2dbefc7f851ab0f3d456d2d44cdce Author: ModelHub XC Date: Mon May 4 08:31:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-11b-pretrained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ede4233 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-3.1-11b-pretrained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-11b-pretrained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-11b-pretrained.IQ3_M.gguf b/Llama-3.1-11b-pretrained.IQ3_M.gguf new file mode 100644 index 0000000..ad1427f --- /dev/null +++ b/Llama-3.1-11b-pretrained.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20a2d22cde405b5b531ca1e8d44d9b44db7cafdb1b623a4ed5db186a455c8e8 +size 5047578720 diff --git a/Llama-3.1-11b-pretrained.IQ3_S.gguf b/Llama-3.1-11b-pretrained.IQ3_S.gguf new file mode 100644 index 0000000..9d17b2a --- /dev/null +++ b/Llama-3.1-11b-pretrained.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25e8d51d0d027009348fbde2bb8db19030d48d36baacb1599e5ce9471a5c5fb +size 4908314720 diff --git a/Llama-3.1-11b-pretrained.IQ3_XS.gguf b/Llama-3.1-11b-pretrained.IQ3_XS.gguf new file mode 100644 index 0000000..6d5235f --- /dev/null +++ b/Llama-3.1-11b-pretrained.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef13672cc0dd9c57d010bcb3c24cb187a04acda1a7c78ceda3dd66a2f2a515ed +size 4676907104 diff --git a/Llama-3.1-11b-pretrained.IQ4_XS.gguf b/Llama-3.1-11b-pretrained.IQ4_XS.gguf new file mode 100644 index 0000000..fe9d3bc --- /dev/null +++ b/Llama-3.1-11b-pretrained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fe20b57803f551f22b17712f255930194947268c3637f57888e9dd709e741a +size 6008770656 diff --git a/Llama-3.1-11b-pretrained.Q2_K.gguf b/Llama-3.1-11b-pretrained.Q2_K.gguf new file mode 100644 index 0000000..6d67f7d --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4b190b39fc3cb49d6413cb424e8290a15101101134a3685131c7c3d7647fb1 +size 4222373984 diff --git a/Llama-3.1-11b-pretrained.Q3_K_L.gguf b/Llama-3.1-11b-pretrained.Q3_K_L.gguf new file mode 100644 index 0000000..a08a62b --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6dc4754c627384eb388650a3d37056ca7cca35b3e1006f88d255a0a5082fdf +size 5807796320 diff --git a/Llama-3.1-11b-pretrained.Q3_K_M.gguf b/Llama-3.1-11b-pretrained.Q3_K_M.gguf new file mode 100644 index 0000000..cc44dab --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ce51d3d9957cc92977bffe3a5d85f77b9edaf4b91e9858d92352868cceda7c +size 5375258720 diff --git a/Llama-3.1-11b-pretrained.Q3_K_S.gguf b/Llama-3.1-11b-pretrained.Q3_K_S.gguf new file mode 100644 index 0000000..f070e52 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419c5c03a7fc647c44b528e0d728dcea4c69ec5767c34990b743dc2a7b09a53c +size 4883247200 diff --git a/Llama-3.1-11b-pretrained.Q4_K_M.gguf b/Llama-3.1-11b-pretrained.Q4_K_M.gguf new file mode 100644 index 0000000..593049c --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2010ddd8c73e26c37fe9ab2f0f1e9553ac81f23a288b6cc6b9251a6672355b +size 6613373024 diff --git a/Llama-3.1-11b-pretrained.Q4_K_S.gguf b/Llama-3.1-11b-pretrained.Q4_K_S.gguf new file mode 100644 index 0000000..9f50f59 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1617bdab6c5bed66b4f013cd99edc4d75fb10a093b68809b5007b315bfb8b32e +size 6295326816 diff --git a/Llama-3.1-11b-pretrained.Q5_K_M.gguf b/Llama-3.1-11b-pretrained.Q5_K_M.gguf new file mode 100644 index 0000000..5be1315 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0da213068106da1e4ee1d24f23c3946c8e7b4c0f8437ee0cbbb939f0813cae +size 7732858976 diff --git a/Llama-3.1-11b-pretrained.Q5_K_S.gguf b/Llama-3.1-11b-pretrained.Q5_K_S.gguf new file mode 100644 index 0000000..d4b2257 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96471417de19a8486b3b7569ab47a3bd621b76f56cfc12d3f6029ab62a2730d4 +size 7549030496 diff --git a/Llama-3.1-11b-pretrained.Q6_K.gguf b/Llama-3.1-11b-pretrained.Q6_K.gguf new file mode 100644 index 0000000..36a2bb1 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a330448626a971b71c4230cb64eea38b1e061a91c9b0bf3c73e44a2a0d63e510 +size 8922312800 diff --git a/Llama-3.1-11b-pretrained.Q8_0.gguf b/Llama-3.1-11b-pretrained.Q8_0.gguf new file mode 100644 index 0000000..1a1b265 --- /dev/null +++ b/Llama-3.1-11b-pretrained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5874aecb30c4f6223f244041784589499b66162a7302fe66c5f54199f4026181 +size 11553763424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..341a24c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: athirdpath/Llama-3.1-11b-pretrained +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/athirdpath/Llama-3.1-11b-pretrained + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-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-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q2_K.gguf) | Q2_K | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.IQ3_XS.gguf) | IQ3_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q3_K_S.gguf) | Q3_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.IQ3_S.gguf) | IQ3_S | 5.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.IQ3_M.gguf) | IQ3_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q3_K_L.gguf) | Q3_K_L | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.IQ4_XS.gguf) | IQ4_XS | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q4_K_S.gguf) | Q4_K_S | 6.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q4_K_M.gguf) | Q4_K_M | 6.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q5_K_S.gguf) | Q5_K_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q5_K_M.gguf) | Q5_K_M | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q6_K.gguf) | Q6_K | 9.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-11b-pretrained-GGUF/resolve/main/Llama-3.1-11b-pretrained.Q8_0.gguf) | Q8_0 | 11.7 | fast, best quality | + +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. + +