commit 7bd886acec7164c076591f4c5175ab9e40bc350f Author: ModelHub XC Date: Mon Jul 6 23:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..42cc8c5 --- /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 +Alpaca-CodeLlama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Alpaca-CodeLlama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alpaca-CodeLlama-3.1-8B.IQ3_M.gguf b/Alpaca-CodeLlama-3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..3f1c03e --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eecc0680b1ed614f3ce3fc28ef29ef5d67a3584d2f493671f4bb5c98946b4a62 +size 3784824064 diff --git a/Alpaca-CodeLlama-3.1-8B.IQ3_S.gguf b/Alpaca-CodeLlama-3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..a51f1ad --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f1b5225e74cb3740fe8a110cb4f08a7a344742df7df39647ed52a12f86fd604 +size 3682325760 diff --git a/Alpaca-CodeLlama-3.1-8B.IQ3_XS.gguf b/Alpaca-CodeLlama-3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..d7db033 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1fae96a09bf95bfb72994698881d821665df436cb8a1d721f9a7e86c6fd0fb +size 3518747904 diff --git a/Alpaca-CodeLlama-3.1-8B.IQ4_XS.gguf b/Alpaca-CodeLlama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..502031b --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcd9af4c8c3f7c1ce1b32f3eeb436081d39bacc43a4a85652f7b270a57e695d +size 4484363520 diff --git a/Alpaca-CodeLlama-3.1-8B.Q2_K.gguf b/Alpaca-CodeLlama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..a9d39f8 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d679ef21f753213a9a015158dc77012d3e15e4687fcc85af0ad49e2a5d856b6d +size 3179132160 diff --git a/Alpaca-CodeLlama-3.1-8B.Q3_K_L.gguf b/Alpaca-CodeLlama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..2216e3e --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53ee92e4a801d2fc8f24cc0e19b623423ce3c64c03f5ff1a23eb31a52ac4dab +size 4321957120 diff --git a/Alpaca-CodeLlama-3.1-8B.Q3_K_M.gguf b/Alpaca-CodeLlama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..aab528d --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d0c54dc968db8eb0cf5a4a8f390ac7fc93c65d84aedd8ea96650d572dd578e +size 4018918656 diff --git a/Alpaca-CodeLlama-3.1-8B.Q3_K_S.gguf b/Alpaca-CodeLlama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..2ad7b11 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bdc1283cdb5c2a4d225dc37bc5b5f0683cb0dadf413e622e9ce8ee37842e99 +size 3664499968 diff --git a/Alpaca-CodeLlama-3.1-8B.Q4_K_M.gguf b/Alpaca-CodeLlama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..67566c0 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38c3451fb1888df7b5a37d2241ac0fb761b34bc8c273d4ef26b3bec98806e9a +size 4920734976 diff --git a/Alpaca-CodeLlama-3.1-8B.Q4_K_S.gguf b/Alpaca-CodeLlama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..bc41eeb --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83cf6b5f9dfad3174eceac7a4704eb30f3945dc9f1823d692fa685727c7ff8f3 +size 4692669696 diff --git a/Alpaca-CodeLlama-3.1-8B.Q5_K_M.gguf b/Alpaca-CodeLlama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..40fc604 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c303265072cfb7ed7f52ab27b6fedab3470fd0ff8e7a05e9f8c6bf6073459c2 +size 5732988160 diff --git a/Alpaca-CodeLlama-3.1-8B.Q5_K_S.gguf b/Alpaca-CodeLlama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..68f6b1c --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93176383904a911c0c82661002f04cca3fdb3720dbe4fdb5b350e7d1f8d00806 +size 5599294720 diff --git a/Alpaca-CodeLlama-3.1-8B.Q6_K.gguf b/Alpaca-CodeLlama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..9adffc7 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfe6203989a1cf22462aba196f03a1b633eda4632030065dae92d9ca5526113 +size 6596007168 diff --git a/Alpaca-CodeLlama-3.1-8B.Q8_0.gguf b/Alpaca-CodeLlama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..5063c00 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7606bba1c2179cff315049ed7c3073a944d15ec52f179edf853117aeddca36a +size 8540771584 diff --git a/Alpaca-CodeLlama-3.1-8B.f16.gguf b/Alpaca-CodeLlama-3.1-8B.f16.gguf new file mode 100644 index 0000000..5f20ed6 --- /dev/null +++ b/Alpaca-CodeLlama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fbf3de69c5ac43f46bb6d3e41ac5dcd80f06bc0da03fdb15de44fe63486a9a +size 16068891904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..302458e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: EpistemeAI/Alpaca-CodeLlama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/EpistemeAI/Alpaca-CodeLlama-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-i1-GGUF +## 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-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alpaca-CodeLlama-3.1-8B-GGUF/resolve/main/Alpaca-CodeLlama-3.1-8B.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. + +