commit 3661e0268e6bcf33fc7661344ba5f12148509022 Author: ModelHub XC Date: Tue Sep 8 23:53:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..843f055 --- /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 +CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.f16.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-SAP-RAP-Code.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.IQ4_XS.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.IQ4_XS.gguf new file mode 100644 index 0000000..6597f75 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22d6b90177df72f2edf40854a895b4fa7a4bebc21c9ccdf439ece0215b83842 +size 3647607328 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q2_K.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q2_K.gguf new file mode 100644 index 0000000..cd0e789 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee0dec2053ecb55b797d3ae2dc61b61cacd452f86b10176b817b0585f3b78ff +size 2532941344 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_L.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_L.gguf new file mode 100644 index 0000000..d70fcd8 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce1e3c5d56e2a3a09a479bac3719e860de613252753fd88c84b2f697de24aa6d +size 3597195296 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_M.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_M.gguf new file mode 100644 index 0000000..8fbcd58 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9d9daaeede384b6761b09f6447cc5ae104cb0776f12020a825f97075c63e58 +size 3298088992 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_S.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_S.gguf new file mode 100644 index 0000000..7b2a0b1 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f911e1bc4c1670fae86f48ace30ba44427b5a46f711d2fbf07eeed585bfb1d +size 2948388896 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_M.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_M.gguf new file mode 100644 index 0000000..a3eb675 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a0b3b22f2169f38134c1cc513b195e5a2f342b62e5e5543b5fde85e5184072 +size 4081097248 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_S.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_S.gguf new file mode 100644 index 0000000..5d5e691 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd02c35f5eefd175ece7519897456582c5c64006357150ba698353fe886cf8d +size 3856833056 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_M.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_M.gguf new file mode 100644 index 0000000..6d86f9a --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1725f2f680dcc03d8b5a20ad8fe4a18383b22c0dc150660e4fbc7f091ee38c3 +size 4783258144 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_S.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_S.gguf new file mode 100644 index 0000000..8fc8c32 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7eca0c000f426e1bfc9a4d5e6ab4cd648e4395b7270d9d1697f58805be20adb +size 4651792928 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q6_K.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q6_K.gguf new file mode 100644 index 0000000..1d996d2 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31709edc8b0ba2d91a6ed6c36d24a363c7cf634483fda07f6abf7c403e3db9a +size 5529304096 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.Q8_0.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q8_0.gguf new file mode 100644 index 0000000..e270a04 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb61b0530a460214661cf0084af095bd27a108a607fb7d4a292fa3e98b760c9f +size 7161231392 diff --git a/CodeLlama-7b-Instruct-SAP-RAP-Code.f16.gguf b/CodeLlama-7b-Instruct-SAP-RAP-Code.f16.gguf new file mode 100644 index 0000000..e91e095 --- /dev/null +++ b/CodeLlama-7b-Instruct-SAP-RAP-Code.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf67121e5626c7b0aa4f79c771d20860d14cbe131cc4a70843aa6b6373604f6 +size 13478369312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2bbcaa7 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: PHarder/CodeLlama-7b-Instruct-SAP-RAP-Code +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/PHarder/CodeLlama-7b-Instruct-SAP-RAP-Code + + +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/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-SAP-RAP-Code-GGUF/resolve/main/CodeLlama-7b-Instruct-SAP-RAP-Code.f16.gguf) | f16 | 13.6 | 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. + +