commit 4827fafbad1749eb745bf8d797a2718b68b5ad3a Author: ModelHub XC Date: Tue Jun 2 05:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ebea4f4 --- /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 +Llama3.1-8B-Middo-Alpaca.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Middo-Alpaca.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Middo-Alpaca.IQ4_XS.gguf b/Llama3.1-8B-Middo-Alpaca.IQ4_XS.gguf new file mode 100644 index 0000000..cefdc0a --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c2de7f0b17f67458198dfe6b70dba01b05ac2e415794f689f2e8e64fb88534 +size 4484364448 diff --git a/Llama3.1-8B-Middo-Alpaca.Q2_K.gguf b/Llama3.1-8B-Middo-Alpaca.Q2_K.gguf new file mode 100644 index 0000000..34714eb --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6688c04cba241f3047737bce674df222b734dfe68abe65b165be723f7185a34 +size 3179133088 diff --git a/Llama3.1-8B-Middo-Alpaca.Q3_K_L.gguf b/Llama3.1-8B-Middo-Alpaca.Q3_K_L.gguf new file mode 100644 index 0000000..005c742 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f125a0465effc1627b285bccdac1b07792384027d6657e5b9d5206ef9e032d8 +size 4321958048 diff --git a/Llama3.1-8B-Middo-Alpaca.Q3_K_M.gguf b/Llama3.1-8B-Middo-Alpaca.Q3_K_M.gguf new file mode 100644 index 0000000..55bb1d1 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bec355c2780b941e2976eb0d37dbdfddaa45da6d2f9e7f5e52070cc3b9ba9ad +size 4018919584 diff --git a/Llama3.1-8B-Middo-Alpaca.Q3_K_S.gguf b/Llama3.1-8B-Middo-Alpaca.Q3_K_S.gguf new file mode 100644 index 0000000..7da1918 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc966046358d2812e698c5d91501392cfe38b2498d82f394dcb5a6133e616876 +size 3664500896 diff --git a/Llama3.1-8B-Middo-Alpaca.Q4_K_M.gguf b/Llama3.1-8B-Middo-Alpaca.Q4_K_M.gguf new file mode 100644 index 0000000..4ff58d4 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7a07da1349c41c60a9e6f3426b0e47e3f7e73d63d5fe68bf2951c9e8a0d859 +size 4920735904 diff --git a/Llama3.1-8B-Middo-Alpaca.Q4_K_S.gguf b/Llama3.1-8B-Middo-Alpaca.Q4_K_S.gguf new file mode 100644 index 0000000..80ded0e --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a069e169aea3df673ccc905ebb0e8dc0a8ec9e3249f778c839cb826bda05cf2d +size 4692670624 diff --git a/Llama3.1-8B-Middo-Alpaca.Q5_K_M.gguf b/Llama3.1-8B-Middo-Alpaca.Q5_K_M.gguf new file mode 100644 index 0000000..639c3b4 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713715fd89c2c7f34352e313634e782a970488bf7e82c75c3392861680a26bf9 +size 5732989088 diff --git a/Llama3.1-8B-Middo-Alpaca.Q5_K_S.gguf b/Llama3.1-8B-Middo-Alpaca.Q5_K_S.gguf new file mode 100644 index 0000000..8338f57 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d70f302854f25fc55cc3d066b93f2ff5b2fac97895ea8a1489e7c186210b280 +size 5599295648 diff --git a/Llama3.1-8B-Middo-Alpaca.Q6_K.gguf b/Llama3.1-8B-Middo-Alpaca.Q6_K.gguf new file mode 100644 index 0000000..05fc038 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d74c7b193b8e70cd6db2b03e274ce42702e6934fea95d129da3c9024b4ff67 +size 6596008096 diff --git a/Llama3.1-8B-Middo-Alpaca.Q8_0.gguf b/Llama3.1-8B-Middo-Alpaca.Q8_0.gguf new file mode 100644 index 0000000..7f31020 --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e24f775d6e0e82d015919bafc764d5207d1478efbe0ef324c118986b8216210 +size 8540772512 diff --git a/Llama3.1-8B-Middo-Alpaca.f16.gguf b/Llama3.1-8B-Middo-Alpaca.f16.gguf new file mode 100644 index 0000000..c233fad --- /dev/null +++ b/Llama3.1-8B-Middo-Alpaca.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6003d0d446c6a0b06e83c09763f8b251035da3d6454bd62a8441c3ac00d9dcbe +size 16068892832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7fb34e --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Word2Li/Llama3.1-8B-Middo-Alpaca +datasets: +- Word2Li/MiddOptimized +language: en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Word2Li/Llama3.1-8B-Middo-Alpaca + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-Middo-Alpaca-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-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/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Middo-Alpaca-GGUF/resolve/main/Llama3.1-8B-Middo-Alpaca.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. + +