commit 955559270f1b12b0eb972a25c066384d42eadb20 Author: ModelHub XC Date: Mon May 25 09:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/alpaca-8b-reproduced-llama-3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..38ffa1a --- /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 +alpaca-8b-reproduced-llama-3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.f16.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +alpaca-8b-reproduced-llama-3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f33cd3b --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: PKU-Alignment/alpaca-8b-reproduced-llama-3 +datasets: +- tatsu-lab/alpaca +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- instruction-following +- instruction-fine-tuning +- supervised-fine-tuning +- ift +- sft +- deepspeed +- beaver +- llama +- alpaca +--- +## About + + + + + + +static quants of https://huggingface.co/PKU-Alignment/alpaca-8b-reproduced-llama-3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#alpaca-8b-reproduced-llama-3-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/alpaca-8b-reproduced-llama-3-GGUF/resolve/main/alpaca-8b-reproduced-llama-3.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. + + diff --git a/alpaca-8b-reproduced-llama-3.IQ4_XS.gguf b/alpaca-8b-reproduced-llama-3.IQ4_XS.gguf new file mode 100644 index 0000000..a8e55aa --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b56c5ab9a2f6b2cbc833e015bb8e9904a8f98a987690e6d131fd5f826e95a70 +size 4484374464 diff --git a/alpaca-8b-reproduced-llama-3.Q2_K.gguf b/alpaca-8b-reproduced-llama-3.Q2_K.gguf new file mode 100644 index 0000000..2370df2 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d4ea3ebc7e96df22b3b9cb148a47b491172dc0aefbd6480a13fcbe89b138d6 +size 3179141440 diff --git a/alpaca-8b-reproduced-llama-3.Q3_K_L.gguf b/alpaca-8b-reproduced-llama-3.Q3_K_L.gguf new file mode 100644 index 0000000..8b741a0 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494c0023f8493741c309ca16aa06a375737f28524995bb249ce49c5f2ce18ba2 +size 4321967232 diff --git a/alpaca-8b-reproduced-llama-3.Q3_K_M.gguf b/alpaca-8b-reproduced-llama-3.Q3_K_M.gguf new file mode 100644 index 0000000..eb3a19a --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ce28a4ecfce209c489d633ee07d96d7cc49e0076b8b68686df257ebcbcae6a +size 4018928768 diff --git a/alpaca-8b-reproduced-llama-3.Q3_K_S.gguf b/alpaca-8b-reproduced-llama-3.Q3_K_S.gguf new file mode 100644 index 0000000..e53566b --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab818e79a197453f676a69a0451527dbee909f4aa2dcc36a33e1a72a8af2d714 +size 3664510080 diff --git a/alpaca-8b-reproduced-llama-3.Q4_K_M.gguf b/alpaca-8b-reproduced-llama-3.Q4_K_M.gguf new file mode 100644 index 0000000..e8024e0 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a76d7ae59acf67b36275270c6794b2e8f0f1d038ffe9533790b008c35dce20 +size 4920746176 diff --git a/alpaca-8b-reproduced-llama-3.Q4_K_S.gguf b/alpaca-8b-reproduced-llama-3.Q4_K_S.gguf new file mode 100644 index 0000000..0dda2a4 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:994a97247f0e8e844e253ef12add78910c267265c1ec9ee29e0b5aaa349bdd96 +size 4692680896 diff --git a/alpaca-8b-reproduced-llama-3.Q5_K_M.gguf b/alpaca-8b-reproduced-llama-3.Q5_K_M.gguf new file mode 100644 index 0000000..829e216 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de15e9c8f0f0cd79ee1f14bf0c1a0c5e4404d15c89c7f3e7d663f79e15229760 +size 5733000384 diff --git a/alpaca-8b-reproduced-llama-3.Q5_K_S.gguf b/alpaca-8b-reproduced-llama-3.Q5_K_S.gguf new file mode 100644 index 0000000..2445cf5 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c69bcb259cb4b2158b9f45fc98a4508272abb84dec18cdee49b99e9c997a1c99 +size 5599306944 diff --git a/alpaca-8b-reproduced-llama-3.Q6_K.gguf b/alpaca-8b-reproduced-llama-3.Q6_K.gguf new file mode 100644 index 0000000..ddca562 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f606915fe06ca02d1382ccf92e3560281cd5bfb5f3ecd449ecf6abb23f5fbe97 +size 6596020480 diff --git a/alpaca-8b-reproduced-llama-3.Q8_0.gguf b/alpaca-8b-reproduced-llama-3.Q8_0.gguf new file mode 100644 index 0000000..0842e6e --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ead873502116241055b85e310c507ce42c7f119f2feffc6415cde6fe61da68d +size 8540788864 diff --git a/alpaca-8b-reproduced-llama-3.f16.gguf b/alpaca-8b-reproduced-llama-3.f16.gguf new file mode 100644 index 0000000..a84e6c8 --- /dev/null +++ b/alpaca-8b-reproduced-llama-3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bfad8d573513d682e310524a2ca115a91a00af132a20c80ca198eb449a33aa +size 16068924544