commit e35141cf4fff1c721b49362382a0dd08594fdd79 Author: ModelHub XC Date: Sun Aug 30 21:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenCodeLlama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..faa5d1e --- /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 +OpenCodeLlama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeLlama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenCodeLlama-3.1-8B.IQ3_M.gguf b/OpenCodeLlama-3.1-8B.IQ3_M.gguf new file mode 100644 index 0000000..aa23d9e --- /dev/null +++ b/OpenCodeLlama-3.1-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ad0f4997a4622738d2f77d952585d2812e47f5e4e5d1270f84a9f1f23363b5 +size 3784824128 diff --git a/OpenCodeLlama-3.1-8B.IQ3_S.gguf b/OpenCodeLlama-3.1-8B.IQ3_S.gguf new file mode 100644 index 0000000..29f1ed2 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b550bcce5958cbe1c485ec10050b4fbfa50e79e9cc2a93bbb711db0ba196dcb +size 3682325824 diff --git a/OpenCodeLlama-3.1-8B.IQ3_XS.gguf b/OpenCodeLlama-3.1-8B.IQ3_XS.gguf new file mode 100644 index 0000000..04b826e --- /dev/null +++ b/OpenCodeLlama-3.1-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fc036353d5006251dc11ea27c94a53fe2ddf2ee6f9db7b1058523373cb087f +size 3518747968 diff --git a/OpenCodeLlama-3.1-8B.IQ4_XS.gguf b/OpenCodeLlama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..7597b68 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7786fdc517382a86abdc884d37f08c9e9f30eaad948f937619c408d672a09af +size 4484363584 diff --git a/OpenCodeLlama-3.1-8B.Q2_K.gguf b/OpenCodeLlama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..880656c --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c421c8e50ca04127b379e1071abfd744b9bb3b4f9561e938bf8cb7a7d9ef0fc +size 3179132224 diff --git a/OpenCodeLlama-3.1-8B.Q3_K_L.gguf b/OpenCodeLlama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..8234e56 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab98d12c9744d0d48c145cb98006d457b70e3406851b70c08b1d4ef0c1e9aaf +size 4321957184 diff --git a/OpenCodeLlama-3.1-8B.Q3_K_M.gguf b/OpenCodeLlama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..608fe6f --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72e2c554b1dc7907fe3748e0a3e93f446c0d10f57b8ab4bda6b59cc865bd66f +size 4018918720 diff --git a/OpenCodeLlama-3.1-8B.Q3_K_S.gguf b/OpenCodeLlama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5317520 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa60665264e59b235504e3eba9937a3e0a7675982e4a238cd6e938280393c5ae +size 3664500032 diff --git a/OpenCodeLlama-3.1-8B.Q4_K_M.gguf b/OpenCodeLlama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..906f977 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352f4239de1a004d3b2b9a392381e87f73e03d3f11015a2877f1c57f6879fd3d +size 4920735040 diff --git a/OpenCodeLlama-3.1-8B.Q4_K_S.gguf b/OpenCodeLlama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..f9af544 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a287460943f65309b9583a4d3aa525cc76eaf8e6d838af3cebb6a7193d4395cb +size 4692669760 diff --git a/OpenCodeLlama-3.1-8B.Q5_K_M.gguf b/OpenCodeLlama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..e8f4213 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c1b42dfe915db14c8d9a5bbb1ba0f9b227ca9a1b135e0892724e4c42d610cc +size 5732988224 diff --git a/OpenCodeLlama-3.1-8B.Q5_K_S.gguf b/OpenCodeLlama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..db33023 --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6969e1d3fb862c1582451c2b31219151dc63590450488009c199478e3d8dccd +size 5599294784 diff --git a/OpenCodeLlama-3.1-8B.Q6_K.gguf b/OpenCodeLlama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..5953c2a --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5dc18ca29f84badad0af91ee7a13531545defda686e2e5084fac338155efa5 +size 6596007232 diff --git a/OpenCodeLlama-3.1-8B.Q8_0.gguf b/OpenCodeLlama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..c8d257b --- /dev/null +++ b/OpenCodeLlama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b86d61a11b46dd57cc2198c490129b0e5931f972ce18d3c88d26a0ff389ad1a +size 8540771648 diff --git a/OpenCodeLlama-3.1-8B.f16.gguf b/OpenCodeLlama-3.1-8B.f16.gguf new file mode 100644 index 0000000..b370d3c --- /dev/null +++ b/OpenCodeLlama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f0d6579b99e9baf1c1d568f2173c5c4cef36a3ee0a6efd82d180d5acaf3407 +size 16068891968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93516a6 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: EpistemeAI/OpenCodeLlama-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/OpenCodeLlama-3.1-8B + + +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/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCodeLlama-3.1-8B-GGUF/resolve/main/OpenCodeLlama-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. + +