commit 8624919441290e6c262fe39a35cc2d46ce68f5ba Author: ModelHub XC Date: Wed Jul 22 04:33:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7cbef78 --- /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-hf-SAP-RAP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.f16.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-Instruct-hf-SAP-RAP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.IQ4_XS.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.IQ4_XS.gguf new file mode 100644 index 0000000..cc024fd --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92f871e4a6d984e001c3eaa4d4e02d3f933f4beef5b0aaec2e31264fb49aa11 +size 3647607328 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q2_K.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q2_K.gguf new file mode 100644 index 0000000..af863e9 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1cf771eedc6f15944c058c743fd3c2a5a641c1dff5488a3c4e4efbfbace9763 +size 2532941344 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_L.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_L.gguf new file mode 100644 index 0000000..cf80849 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562767617355219fc5ffcde5b22cbde77362bb808f0c88d97754797d690bd91e +size 3597195296 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_M.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_M.gguf new file mode 100644 index 0000000..b1e08b0 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46d7499ce4002ea2dc654c8f5548eafb81b6cac994adb104e02529e125d3f06 +size 3298088992 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_S.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_S.gguf new file mode 100644 index 0000000..733101a --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f29a6f757279995dd18e21519fb8adae9b47a90302e132bc7bdce0c0ac8a6d +size 2948388896 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_M.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_M.gguf new file mode 100644 index 0000000..8e2a80d --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0bd8a604f0eb2b162b4ac1243486c80194051dc89163baf230080527502843 +size 4081097248 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_S.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_S.gguf new file mode 100644 index 0000000..a0365e1 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc0becd5f882e07d95f517d0df01453710aa636902518e4cfcd62bc99f7d4b3 +size 3856833056 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_M.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_M.gguf new file mode 100644 index 0000000..3ae099d --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423101c083d300943ef15e5c0b5b344a78f30675cd510d12ed713467b849f47e +size 4783258144 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_S.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_S.gguf new file mode 100644 index 0000000..490f959 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b4c9bdc8e060904a3a3671a86aeec0c6ad1e21d99cb4985f80cb17d666b3ef +size 4651792928 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q6_K.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q6_K.gguf new file mode 100644 index 0000000..389408c --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd2bc36ea237fcbdd58649c376f2016e8cabda6050f9585777ca5e8153555ab9 +size 5529304096 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.Q8_0.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q8_0.gguf new file mode 100644 index 0000000..0598553 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eed52e4a95ef76f108eac77b7d30182d6dc971c4134fd1b436fcdab69bbcaad +size 7161231392 diff --git a/CodeLlama-7b-Instruct-hf-SAP-RAP.f16.gguf b/CodeLlama-7b-Instruct-hf-SAP-RAP.f16.gguf new file mode 100644 index 0000000..85243d6 --- /dev/null +++ b/CodeLlama-7b-Instruct-hf-SAP-RAP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda06fdf62718c761d914edaf6925a7a50d5a03dc00b76d0d19e0dd306984a27 +size 13478369312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..186c9e4 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: PHarder/CodeLlama-7b-Instruct-hf-SAP-RAP +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/PHarder/CodeLlama-7b-Instruct-hf-SAP-RAP + + +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-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-SAP-RAP-GGUF/resolve/main/CodeLlama-7b-Instruct-hf-SAP-RAP.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. + +