commit 3b0fbd5d1bc7ff8ba92f74e520cfbefe7e4be84c Author: ModelHub XC Date: Wed May 27 14:22:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..902f436 --- /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 +Olaf_Scholz_Llama-8B_v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olaf_Scholz_Llama-8B_v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Olaf_Scholz_Llama-8B_v0.1.IQ4_XS.gguf b/Olaf_Scholz_Llama-8B_v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..5b8f194 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7d7a70ad6a1cb94ac2f420c6415db266609c56d32613d52bf577154bcda2e3 +size 4484368160 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q2_K.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q2_K.gguf new file mode 100644 index 0000000..e2e1088 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007c5b2e665546e5f04ebc532b4c2a4f7ef0e5fb1082197dc69e6fc7652e9c36 +size 3179136800 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q3_K_L.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..d30ddb3 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca18dde87c2471733a3f0ba190c19024374fd31bbd73a5607f3c1e2f2252dc70 +size 4321961760 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q3_K_M.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..44129e5 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503935f761aa98c97cf597b53b0ef6cd442a6bbc019227f421f51c1e3bea6e97 +size 4018923296 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q3_K_S.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..0b9ef3c --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e735512b9fc43e2da887c8357b986d9d1d79add01460c067a1428a3d012653cc +size 3664504608 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q4_K_M.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..37fd66c --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7665d36c567dc2326c252bde92c29e0c3ed62f17fc64b6108c18faea5072a8 +size 4920739616 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q4_K_S.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..254036f --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622049f98e85faa9c992fef2a628214ad99076b40a1fb0d2c5cdbfa3d386d573 +size 4692674336 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q5_K_M.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..53dd0bc --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47bfe144acc1eb03df9b99ad1d03ff052052d84d425fb2bbe4fd0d483e4ddd70 +size 5732992800 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q5_K_S.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..5f95f46 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab53285cfbe56e0c30ad0eacf07d582eafd995a82e5a77444e711fad6f69fdb8 +size 5599299360 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q6_K.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q6_K.gguf new file mode 100644 index 0000000..e8addbb --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdce6eaee133feb58fcd8bf22726a2ab87cd665967e5d14273c298fe3da7f04c +size 6596011808 diff --git a/Olaf_Scholz_Llama-8B_v0.1.Q8_0.gguf b/Olaf_Scholz_Llama-8B_v0.1.Q8_0.gguf new file mode 100644 index 0000000..ae05152 --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1957f9a07e727be5326061e89183c1fca52ffc9b23912622ebc18ac1dbb9e98d +size 8540776224 diff --git a/Olaf_Scholz_Llama-8B_v0.1.f16.gguf b/Olaf_Scholz_Llama-8B_v0.1.f16.gguf new file mode 100644 index 0000000..a88cc1f --- /dev/null +++ b/Olaf_Scholz_Llama-8B_v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0ca92659c942275a6ea182ff84c60be160b477e81432d84ae15762389de392 +size 16068896544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b98724 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Anni0401/Olaf_Scholz_Llama-8B_v0.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Anni0401/Olaf_Scholz_Llama-8B_v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Olaf_Scholz_Llama-8B_v0.1-GGUF).*** + +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/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Olaf_Scholz_Llama-8B_v0.1-GGUF/resolve/main/Olaf_Scholz_Llama-8B_v0.1.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. + +