commit 80cc6dbf49a4c73301035f46f7a3e533e6caaabc Author: ModelHub XC Date: Fri Jul 31 10:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..83abfae --- /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 +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.IQ4_XS.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.IQ4_XS.gguf new file mode 100644 index 0000000..c69ea46 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff56e57ca217601025f67b75a69abe2b2aaa95f74455431bd15853a87bf9ec0 +size 4484368064 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q2_K.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q2_K.gguf new file mode 100644 index 0000000..7a92d65 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5887541f72ce9be6d8137142ba00c4fdb6831d0b9f898a0ef39d76b42b35c9 +size 3179136704 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_L.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_L.gguf new file mode 100644 index 0000000..3fdfed7 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6898214f1889ac72fa0252dfe56eec3f2a9abcbc69d76784d5f1173ef43d81fa +size 4321961664 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_M.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_M.gguf new file mode 100644 index 0000000..4e43fdb --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df330a235e5a923b376b3bf3710fa4264199a699ac9b44243f59205c8c74dff4 +size 4018923200 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_S.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_S.gguf new file mode 100644 index 0000000..fda0829 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73ae5731caad888b53faa36ec32daa906526be4a73d4c5465c1dbbcd767b3cd +size 3664504512 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_M.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_M.gguf new file mode 100644 index 0000000..3803f2c --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fb68c9e560417a8e2d47198c557c5aa6e9cf77de263af135b257706c7ef6e6 +size 4920739520 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_S.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_S.gguf new file mode 100644 index 0000000..f764df2 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fcd86fe93e996a45c263dd56e760c2cbb1e268a8f083e2d80b578549bf69956 +size 4692674240 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_M.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_M.gguf new file mode 100644 index 0000000..d226f2e --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd47b30ffabf1a8fa01e5825f6bc7bf87231daa42fd2ff3ddbb8389bb4b245ec +size 5732992704 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_S.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_S.gguf new file mode 100644 index 0000000..05b2212 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:265d5737f2742daf2f210b3bae94f28848ba4149c0f021b8785bbf0455f0175d +size 5599299264 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q6_K.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q6_K.gguf new file mode 100644 index 0000000..de6ddce --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a779306cc2b70ce806a74664303895c72c43a993f4e19983a5227d45797e4dc +size 6596011712 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q8_0.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q8_0.gguf new file mode 100644 index 0000000..936ce5a --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a20e5c7df163ef368f3d0be37e9a0061f488536f529290abaf5d05ed9718714a +size 8540776128 diff --git a/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.f16.gguf b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.f16.gguf new file mode 100644 index 0000000..c920362 --- /dev/null +++ b/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c383a24dcba4350916ef176306e84fded1ebed1d77e707943afd9bac6fb21e4b +size 16068896448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4eb6354 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ThatsGroes/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e +datasets: +- kobprof/skolegpt-instruct +- Mabeck/Danish-SlimOrca +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/ThatsGroes/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e + + +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/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e-GGUF/resolve/main/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e.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. + +