commit da0392a82ee68fc764f6b6e67fdee4a1d25add36 Author: ModelHub XC Date: Wed Jul 15 22:25:11 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9737fa --- /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 +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.IQ4_XS.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.IQ4_XS.gguf new file mode 100644 index 0000000..4ada0a6 --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a18a7ec0d11c6ec3cd0701871fafc82516057a23c0c012772565e00365cbb51 +size 2075587648 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q2_K.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q2_K.gguf new file mode 100644 index 0000000..70cf841 --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8cba9cf7356d3cf02870173c269154e2ad25f1318dea275d59f88da83a04e5 +size 1446881344 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_L.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_L.gguf new file mode 100644 index 0000000..b22f2eb --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3757744d35936b1c24752640fa91f74081c9aabb8a43d6065dd6b9e1d503366d +size 2045136448 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_M.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_M.gguf new file mode 100644 index 0000000..33f434e --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7913abc0885a3a386b9f8e0f8208884b0bb92a434181559a89d6f3dffb124302 +size 1877626432 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_S.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_S.gguf new file mode 100644 index 0000000..dc7d189 --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f6abc4ee95cd70d89ec56a302c79ed74a0eddf2f91e394c5474f9317663b79 +size 1681804864 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_M.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_M.gguf new file mode 100644 index 0000000..ab0ccfb --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1333b2cfcab3b30fb35e9d0ee9fd569eb240461e8dcded1b419d12f98c07ac +size 2318920768 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_S.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_S.gguf new file mode 100644 index 0000000..0f3cffd --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94ce6c19fabc473d41fa6deaa522207017ed0af0af071ac63c9a12eab320f2d3 +size 2193484864 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_M.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_M.gguf new file mode 100644 index 0000000..f2a761b --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eab40a6327e9f5ec5bb35a0855417724f5e9dbdc4a1c3184aa7df708a65540d +size 2715012160 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_S.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_S.gguf new file mode 100644 index 0000000..876a0a0 --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9b3e4fd94b323e04aeb5edfcbdedea4c83c9cbb4c06db8c3621c58ef82129e +size 2641480768 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q6_K.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q6_K.gguf new file mode 100644 index 0000000..09c810d --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8af81b9a5b8337c2c1944345cc5bcb6142cc86ca17e7eb625d0155b359c143 +size 3135859264 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q8_0.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q8_0.gguf new file mode 100644 index 0000000..2885f75 --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb56b1538839ba76aec371855adb22c4e1f9e0657f2a42b4dd9b5460d14b7ae +size 4061228608 diff --git a/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.f16.gguf b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.f16.gguf new file mode 100644 index 0000000..3251f6b --- /dev/null +++ b/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef74fac80cc737c756cc38372fbdaf92f4a6e3b1b8c4b296c4cbc617526859c +size 7643303488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1069534 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI +language: +- en +- de +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- German +- RAG +- Retrieval +- Question-Answering +- Summarization +- Reasoning +--- +## About + + + + + + +static quants of https://huggingface.co/avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-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/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q4_K_M.gguf) | Q4_K_M | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI-GGUF/resolve/main/German_RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI.f16.gguf) | f16 | 7.7 | 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. + +