commit baade3c5d1d562e8017e7c4cb0850148dd532d36 Author: ModelHub XC Date: Fri Jul 10 07:20:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Codellama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..209c906 --- /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-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Codellama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Codellama-3-8B.IQ4_XS.gguf b/Codellama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9d9bfcc --- /dev/null +++ b/Codellama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2800d21aec2a51076152bd43778203ad965acf4e03213f4881fba2a3f22a7567 +size 4484363744 diff --git a/Codellama-3-8B.Q2_K.gguf b/Codellama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..82e4198 --- /dev/null +++ b/Codellama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8de5a1a1a10638464f7d08967ff9664961fba992f546174334df349a05b76a +size 3179132384 diff --git a/Codellama-3-8B.Q3_K_L.gguf b/Codellama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..2e1ed63 --- /dev/null +++ b/Codellama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e79f56632821872142769c1ea8181af689a97db0309e2abfa94a650a851759d +size 4321957344 diff --git a/Codellama-3-8B.Q3_K_M.gguf b/Codellama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..237f879 --- /dev/null +++ b/Codellama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39d3ff1e0af21c95089a01a8ce7d32837da3b94780ae411e2df0485edd68f1f +size 4018918880 diff --git a/Codellama-3-8B.Q3_K_S.gguf b/Codellama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7451954 --- /dev/null +++ b/Codellama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961ea2fb8456531f7563f27585250366827afb723c3bb64f9171187cce6f3fcd +size 3664500192 diff --git a/Codellama-3-8B.Q4_K_M.gguf b/Codellama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..631b90a --- /dev/null +++ b/Codellama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8bd2dc30a5821dbfc017fcc9235ad908854ed0264ea5d708765ff0e76ecd54 +size 4920735200 diff --git a/Codellama-3-8B.Q4_K_S.gguf b/Codellama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..fabab4b --- /dev/null +++ b/Codellama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191727fa21651a104d1746dd11be36ade5dc6064e89ea1194d2e243c268bcc2a +size 4692669920 diff --git a/Codellama-3-8B.Q5_K_M.gguf b/Codellama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..929cb39 --- /dev/null +++ b/Codellama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026d0e7fc665bef5c7c7454674fa53aa0c64b2c54cbf4bd1a1657d3d3542fcc8 +size 5732988384 diff --git a/Codellama-3-8B.Q5_K_S.gguf b/Codellama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..8f721cf --- /dev/null +++ b/Codellama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb825f3e68a65050522453501bd8c3fc6fd03352e3e7b76abaebbe2607c7795 +size 5599294944 diff --git a/Codellama-3-8B.Q6_K.gguf b/Codellama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..17b8e01 --- /dev/null +++ b/Codellama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee3a5b0aebe0f586498e2b8bc5772db88060036d86188ec00fe28c0bc0e8c5a +size 6596007392 diff --git a/Codellama-3-8B.Q8_0.gguf b/Codellama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..0f351a4 --- /dev/null +++ b/Codellama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeae988588d929fc37b1ed4f0850eeb9da55385ac1c046e93e349c977aa5c1b +size 8540771808 diff --git a/Codellama-3-8B.f16.gguf b/Codellama-3-8B.f16.gguf new file mode 100644 index 0000000..9160876 --- /dev/null +++ b/Codellama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f32bb2ebc9e71408c11b5224833e89549ad56f5e214faed14e8760d95471b14 +size 16068892128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f34b996 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: domliu/Codellama-3-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/domliu/Codellama-3-8B + + +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-3-8B-GGUF/resolve/main/Codellama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Codellama-3-8B-GGUF/resolve/main/Codellama-3-8B.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. + +