7B AWQ
Collection
These models are selected for their compatibility with small 12GB memory GPUs.
•
204 items
•
Updated
•
2
perlthoughts/Falkor-7b AWQ
- Model creator: perlthoughts
- Original model: Falkor-7b
Model summary
dragon-mistral-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Mistral-7B base model.
DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation.
- Downloads last month
- 15
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.
Collection including solidrust/Falkor-7b-AWQ
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.260
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.840
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.980
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard63.080
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard80.350
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard60.500