commit 376ce66de91b3bc049e6fa3e76f7b88a92fc941f Author: ModelHub XC Date: Wed Jun 17 01:34:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a99e05 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Llama-3-8B-Instruct-Coding-Expert.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Coding-Expert.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Coding-Expert.IQ4_XS.gguf b/Llama-3-8B-Instruct-Coding-Expert.IQ4_XS.gguf new file mode 100644 index 0000000..1a16459 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad9c76e35977257a79cb1f9735b775c649ec5ffe53c228a9f2da042e1d5635ac +size 4484363392 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q2_K.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q2_K.gguf new file mode 100644 index 0000000..46043e0 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55b25d51bd6c0538598ecce65fed96bdcdb711c0e7f410e09174484b12e260d +size 3179132032 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q3_K_L.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_L.gguf new file mode 100644 index 0000000..d64dd93 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28acd7c63954368d647c7f6d8975b185dd1f0171fa9a7d5d68a8e5811f01faee +size 4321956992 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q3_K_M.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_M.gguf new file mode 100644 index 0000000..a2bb1c8 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3779aca13e7df4b9a31c4a8402abe903235ddcd9ae4701dca2ff0e376b918cdd +size 4018918528 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q3_K_S.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_S.gguf new file mode 100644 index 0000000..8354223 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0025e26777a2536d87d39a6e84f2e8302bf61e4acd314e672bd26763e506be +size 3664499840 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q4_K_M.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q4_K_M.gguf new file mode 100644 index 0000000..d8eb914 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3309682754b289594e003d6b8c8e6a8816577bdb158e94710e04a7334eb90568 +size 4920734848 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q4_K_S.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q4_K_S.gguf new file mode 100644 index 0000000..e95064f --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacb6bcceb44c9caae438a0f01ec956d22587ff77e1335ca89d5f19bd82b2882 +size 4692669568 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q5_K_M.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q5_K_M.gguf new file mode 100644 index 0000000..dc675b1 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510af898cc474d700f2b18b7a09713d2aef953c65fc01c9d143417c7d4398a6d +size 5732988032 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q5_K_S.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q5_K_S.gguf new file mode 100644 index 0000000..c7e0b88 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac879ef3ddd40c2af6a76f838d8cad801097636f72912604ec9c01ee1ca9947 +size 5599294592 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q6_K.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q6_K.gguf new file mode 100644 index 0000000..6f4e8e1 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88553cb5cebb32ed7ba991c699712cca05b71e32f4c440aa7957b9d1dbf4f69f +size 6596007040 diff --git a/Llama-3-8B-Instruct-Coding-Expert.Q8_0.gguf b/Llama-3-8B-Instruct-Coding-Expert.Q8_0.gguf new file mode 100644 index 0000000..93bb9f9 --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248b9d41a93c490f8fe4ed7f09c645d7af13fd45d893998bd88553f8b9ab88db +size 8540771456 diff --git a/Llama-3-8B-Instruct-Coding-Expert.f16.gguf b/Llama-3-8B-Instruct-Coding-Expert.f16.gguf new file mode 100644 index 0000000..1d20dcc --- /dev/null +++ b/Llama-3-8B-Instruct-Coding-Expert.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcef6e072c167e830f854e064428f7ffbde22cea7754d9acaf67bbb9eedd045 +size 16068891776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e1db9d --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: SakanaAI/Llama-3-8B-Instruct-Coding-Expert +language: +- en +library_name: transformers +license: llama3 +model_type: llama +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SakanaAI/Llama-3-8B-Instruct-Coding-Expert + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-Instruct-Coding-Expert-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-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/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coding-Expert-GGUF/resolve/main/Llama-3-8B-Instruct-Coding-Expert.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. + +