Question Answering
Transformers
Safetensors
English
German
llama
text-generation
German
RAG
Retrieval
Question-Answering
Summarization
Reasoning
text-generation-inference
Instructions to use avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI") model = AutoModelForCausalLM.from_pretrained("avemio/German-RAG-PHI-3.5-MINI-4B-MERGED-HESSIAN-AI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c4f4e198ef81d04ca23f74e737770f410819c49fee1ac06f509a463e696451f0
- Size of remote file:
- 4.97 GB
- SHA256:
- 9fb4417eee3f20b1c7db2f680b8d4ed2244a8ef789a3aeb91222336a4e842501
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.