avemio/GRAG-LLAMA-3.1-8B-MERGED-HESSIAN-AI

Question Answering • Updated 4 days ago • 49

Note This model was merged from the SFT- & ORPO Checkpoints. SFT Model with 60% weights & ORPO Model with 40% weights.

avemio/GRAG-LLAMA-3.1-8B-ORPO-HESSIAN-AI

Question Answering • Updated 12 days ago • 141 • 2

Note This model was trained on 20.7 Million Tokens in ORPO (Odd-Ratio-Preference Optimization) on synthetically generated or enhanced Data. Please see the GRAG-ORPO-Dataset (https://huggingface.co/datasets/avemio/GRAG-ORPO-ShareGPT-HESSIAN-AI) for reference.

avemio/GRAG-LLAMA-3.1-8B-SFT-HESSIAN-AI

Question Answering • Updated 12 days ago • 62

Note This model was trained on 1,5 Billion Tokens in SFT(Supervised Fine-Tuning) on synthetically generated or enhanced Data. Please see the GRAG-SFT-Dataset (https://huggingface.co/datasets/avemio/GRAG-SFT-ShareGPT-HESSIAN-AI) for reference.

avemio/GRAG-LLAMA-3.1-8B-CPT-HESSIAN-AI

Question Answering • Updated 12 days ago • 18

Note This model was trained on 507,5 Million Tokens in CPT (Continued Pre-Training) on synthetically generated or enhanced Data. Please see the GRAG-CPT-Dataset (https://huggingface.co/datasets/avemio/GRAG-CPT-HESSIAN-AI) for reference.