commit 9a2607a1277f13fad798808a0282260d893d5b96 Author: ModelHub XC Date: Sun Aug 2 03:53:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ac834f2 --- /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 +LLAMA3-8b-LIMA-Alpaca-style.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-8b-LIMA-Alpaca-style.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA3-8b-LIMA-Alpaca-style.IQ3_M.gguf b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_M.gguf new file mode 100644 index 0000000..80dc0e7 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92cf6122234f3c244915e85b47aef39678a22ff16e62a9f40db5f40c72fbecd +size 3784823360 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.IQ3_S.gguf b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_S.gguf new file mode 100644 index 0000000..6f150aa --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152837b452924ace3e65afb7f333f5fdabb0c9b2efa44d1e0e4961416b28bda2 +size 3682325056 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.IQ3_XS.gguf b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_XS.gguf new file mode 100644 index 0000000..bceaaba --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa9a8f603ed1dff3e5ccc75e8f909f1efae70365387421d61a95ecc3148e27e +size 3518747200 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.IQ4_XS.gguf b/LLAMA3-8b-LIMA-Alpaca-style.IQ4_XS.gguf new file mode 100644 index 0000000..0fde3f5 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d722131af56c759f8506ee3830b110b5f840b229a2a02825ad8c215cd5a7ec1 +size 4484362816 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q2_K.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q2_K.gguf new file mode 100644 index 0000000..ba1ec1c --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274a4c319ab42cf5c74ccb4ae1f590f69eeae4c474d2264d53174de33d9d7f7d +size 3179131456 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_L.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_L.gguf new file mode 100644 index 0000000..81bf343 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec15454054a4878712f60aea7d64fbc0d7f7e4b739bede799bdcd441dd3df6dc +size 4321956416 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_M.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_M.gguf new file mode 100644 index 0000000..bd419b7 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965e94fc96ccae1aabfe9ea85bbd6732eba3f9555df8cd8afc38876dbfac81d4 +size 4018917952 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_S.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_S.gguf new file mode 100644 index 0000000..6a6e5a2 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db7959f0a7555e6af806f7b5b8c58409e615b0d193b807a72bfe2ea4653f231 +size 3664499264 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_M.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_M.gguf new file mode 100644 index 0000000..3a6f050 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efe3ebc6534bed97886248dff57c488f5bd8d05715d581eae847f59faebffa36 +size 4920734272 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_S.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_S.gguf new file mode 100644 index 0000000..9eaa46c --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:845ea504fa2f9caa878c657c435451c16012fc3ec81deb798c89ea0dc3f2024f +size 4692668992 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_M.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_M.gguf new file mode 100644 index 0000000..cc9ce12 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db19b40ddd96746db3810647863f1780e3e02395e772e4cd82fe81bb5869149f +size 5732987456 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_S.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_S.gguf new file mode 100644 index 0000000..a285052 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c345c054c18c0b9cfa597d06995bd1465dd5c48993801dcd797f514c893be9f +size 5599294016 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q6_K.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q6_K.gguf new file mode 100644 index 0000000..49b7d21 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e267a059abc76d853893ea65f4b08f0eab7ab096e2033847d3f8a566f8846661 +size 6596006464 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.Q8_0.gguf b/LLAMA3-8b-LIMA-Alpaca-style.Q8_0.gguf new file mode 100644 index 0000000..612b65c --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef968fe458bafeab38f404e404f513df3ae6e73007575b8e8921a87acfd38d0 +size 8540770880 diff --git a/LLAMA3-8b-LIMA-Alpaca-style.f16.gguf b/LLAMA3-8b-LIMA-Alpaca-style.f16.gguf new file mode 100644 index 0000000..09c6159 --- /dev/null +++ b/LLAMA3-8b-LIMA-Alpaca-style.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:621255703780b798e8376cb644043ce5ea9c409633ad45e9704c233a0446ffea +size 16068891200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..41ab88c --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Essacheez/LLAMA3-8b-LIMA-Alpaca-style +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Essacheez/LLAMA3-8b-LIMA-Alpaca-style + + +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/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-8b-LIMA-Alpaca-style-GGUF/resolve/main/LLAMA3-8b-LIMA-Alpaca-style.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. + +