commit 7a29e6e83d6a4b31b134faecfa21dd72d9eba18d Author: ModelHub XC Date: Fri Sep 25 22:17:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeLlama-7b-hf_mbxpall-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a84727 --- /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-hf_mbxpall.f16.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7b-hf_mbxpall.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama-7b-hf_mbxpall.IQ4_XS.gguf b/CodeLlama-7b-hf_mbxpall.IQ4_XS.gguf new file mode 100644 index 0000000..3848f13 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5f5670ea57f1a5340c78e8a7f768f10d2d7f3c335d342648d472cef492f600 +size 3647606528 diff --git a/CodeLlama-7b-hf_mbxpall.Q2_K.gguf b/CodeLlama-7b-hf_mbxpall.Q2_K.gguf new file mode 100644 index 0000000..2925781 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37aa15bca5c5edadf1d546047f51033fb2a94ec7e0cc8489e46c2308c6b40b8b +size 2532940544 diff --git a/CodeLlama-7b-hf_mbxpall.Q3_K_L.gguf b/CodeLlama-7b-hf_mbxpall.Q3_K_L.gguf new file mode 100644 index 0000000..a340673 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72627fef1425e19df9e78c13f5fed94178bed81ffa159040243638436e5eb861 +size 3597194496 diff --git a/CodeLlama-7b-hf_mbxpall.Q3_K_M.gguf b/CodeLlama-7b-hf_mbxpall.Q3_K_M.gguf new file mode 100644 index 0000000..f084a32 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858f02db012ac94b55d3992bec752b321ad03e07293c30e6725db2b6cd09e1cb +size 3298088192 diff --git a/CodeLlama-7b-hf_mbxpall.Q3_K_S.gguf b/CodeLlama-7b-hf_mbxpall.Q3_K_S.gguf new file mode 100644 index 0000000..d026038 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193c0fc47b145089f19293e5c1a0948f7eeaa36ad96e6b3768ed4b2cdc035a5b +size 2948388096 diff --git a/CodeLlama-7b-hf_mbxpall.Q4_K_M.gguf b/CodeLlama-7b-hf_mbxpall.Q4_K_M.gguf new file mode 100644 index 0000000..163ec01 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce9382b371951931ed8a8e2abd11bebdb60625d8004f854f69a6c5b6b4156e7 +size 4081096448 diff --git a/CodeLlama-7b-hf_mbxpall.Q4_K_S.gguf b/CodeLlama-7b-hf_mbxpall.Q4_K_S.gguf new file mode 100644 index 0000000..464f6ea --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca522ffdc1a1c3d80a21a2d10f2890202689da5089769fc361bc7c997ea468e +size 3856832256 diff --git a/CodeLlama-7b-hf_mbxpall.Q5_K_M.gguf b/CodeLlama-7b-hf_mbxpall.Q5_K_M.gguf new file mode 100644 index 0000000..57abd31 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a2b899e32daff0a983f822f81c2b83e2e7f8b3277b5fe11b4a7f04610aff89 +size 4783257344 diff --git a/CodeLlama-7b-hf_mbxpall.Q5_K_S.gguf b/CodeLlama-7b-hf_mbxpall.Q5_K_S.gguf new file mode 100644 index 0000000..c9f1b4e --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f542faa985dd122491d9863174e2c665cf30ee51419335907d0b9f2f2eefae45 +size 4651792128 diff --git a/CodeLlama-7b-hf_mbxpall.Q6_K.gguf b/CodeLlama-7b-hf_mbxpall.Q6_K.gguf new file mode 100644 index 0000000..7f6b911 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc727ec3a0376b097280ac5e2a35ee211993cb0f841a8c3282c2b7f0f707d1dc +size 5529303296 diff --git a/CodeLlama-7b-hf_mbxpall.Q8_0.gguf b/CodeLlama-7b-hf_mbxpall.Q8_0.gguf new file mode 100644 index 0000000..bb05435 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0001cc02766bdf4a8ea9dff6f8dda5a25996c75080f1c67225a3528655f92b +size 7161230592 diff --git a/CodeLlama-7b-hf_mbxpall.f16.gguf b/CodeLlama-7b-hf_mbxpall.f16.gguf new file mode 100644 index 0000000..87e9543 --- /dev/null +++ b/CodeLlama-7b-hf_mbxpall.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ff446226f547b66b7510c2214565d0ebba3a8b456da84f4c4556b3684bd997 +size 13478368512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..582e678 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: zerozeroz/CodeLlama-7b-hf_mbxpall +language: +- en +library_name: transformers +model_name: CodeLlama-7b-hf_mbxpall +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zerozeroz/CodeLlama-7b-hf_mbxpall + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CodeLlama-7b-hf_mbxpall-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/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-hf_mbxpall-GGUF/resolve/main/CodeLlama-7b-hf_mbxpall.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. + +