commit 464ac44e4f964d818a8a92fb91f0d1e03e0a0591 Author: ModelHub XC Date: Fri May 8 03:00:57 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-CPT-HESSIAN-AI-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f225e18 --- /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-CPT-HESSIAN-AI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.IQ4_XS.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.IQ4_XS.gguf new file mode 100644 index 0000000..bab3204 --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f453d98adcebc4b34e570b78559d4242f876b737710d84008f9edf01bb10e4f3 +size 2075587712 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q2_K.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q2_K.gguf new file mode 100644 index 0000000..737192e --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64162c435e4d7a09b4d515e5a3e5e16391030c2fbb7606a7ef1d4a04f3439f6d +size 1446881408 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_L.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_L.gguf new file mode 100644 index 0000000..a029d7f --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94bdf5d0e359f5310015cf0b1fe6dccaccf9a63d85e4eea2b481afd810ddeaeb +size 2045136512 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_M.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_M.gguf new file mode 100644 index 0000000..ca08720 --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895b33761b663dbc9d4f3f8a7d9ca03fd007a248778db04b27efdaeca6f143ac +size 1877626496 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_S.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_S.gguf new file mode 100644 index 0000000..6940740 --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039e41500033252a6f45ea2b70b64a2e2c55303baa785c46fcb485d277a145ec +size 1681804928 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_M.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_M.gguf new file mode 100644 index 0000000..7ffed5f --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee8f2cd2a9233056a7dd4f938528ae526bcdb63e5d000cc92693758fb4bf70d +size 2318920832 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_S.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_S.gguf new file mode 100644 index 0000000..071509d --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fe765178237b3773694117255a809a66fe418f612495050c8beee814c5a75a +size 2193484928 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_M.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_M.gguf new file mode 100644 index 0000000..1a2f6a6 --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0961d23f43e1d0bf06b4ffbc793b1ded31cb706ffd0290f1b4500b6649d2fc +size 2715012224 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_S.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_S.gguf new file mode 100644 index 0000000..b75847c --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3219b3277b9ee5ecb88a5f7179d133287ec55f8270f27169ddb49fffae7934 +size 2641480832 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q6_K.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q6_K.gguf new file mode 100644 index 0000000..506a133 --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1daa5bbbaf65fe7d6bb536389fa61f251bdf4a38490ea53ee4e4d3b941e8990e +size 3135859328 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q8_0.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q8_0.gguf new file mode 100644 index 0000000..2bf03bc --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7694e719dee97f7310d3f9d51dbccaf47d0db3e57d8e49dc7e898d8e43a721 +size 4061228672 diff --git a/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.f16.gguf b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.f16.gguf new file mode 100644 index 0000000..5b46a8b --- /dev/null +++ b/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76434ad4e5803c6ee05bc9222047ad8f7990859c7fe71f0ec56d9654a2816260 +size 7643303552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c7fa492 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: avemio/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI +datasets: +- avemio/German-RAG-CPT-HESSIAN-AI +language: +- en +- de +library_name: transformers +license: apache-2.0 +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-CPT-HESSIAN-AI + + +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/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-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-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-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-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-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-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q5_K_M.gguf) | Q5_K_M | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/German-RAG-PHI-3.5-MINI-4B-CPT-HESSIAN-AI-GGUF/resolve/main/German-RAG-PHI-3.5-MINI-4B-CPT-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. + +