VMware
open-llama-0.7T-7B-open-instruct-v1.1
Open Llama 7b Open Instruct
VMware/open-llama-7B-open-instruct Instruction-tuned version of the fully trained Open LLama 7B model. The model is open for COMMERCIAL USE . There is a v2 version of this model available, https://huggingface.co/VMware/open-llama-7b-v2-open-instruct NOTE : The model was trained using the Alpaca prompt template NOTE : Fast tokenizer results in incorrect encoding, set the parameter, when instantiating the tokenizer License - Commercially Viable - Instruction dataset, VMware/open-instruct-v1-oasst-dolly-hhrlhf is under cc-by-sa-3.0 - Language Model, (openlm-research/openllama7b) is under apache-2.0 - Model : Open-llama - Model Size: 7B parameters - Dataset: Open-instruct-v1 (oasst,dolly, hhrlhf) Finetuning details The finetuning scripts will be available in our RAIL Github Repository Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric | Value | |-----------------------|---------------------------| | Avg. | 40.9 | | ARC (25-shot) | 49.74 | | HellaSwag (10-shot) | 73.67 | | MMLU (5-shot) | 31.52 | | TruthfulQA (0-shot) | 34.65 | | Winogrande (5-shot) | 65.43 | | GSM8K (5-shot) | 0.53 | | DROP (3-shot) | 30.75 |