Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Optimus-7B - GGUF - Model creator: https://huggingface.co/Q-bert/ - Original model: https://huggingface.co/Q-bert/Optimus-7B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Optimus-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q2_K.gguf) | Q2_K | 2.53GB | | [Optimus-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [Optimus-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.IQ3_S.gguf) | IQ3_S | 2.96GB | | [Optimus-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [Optimus-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.IQ3_M.gguf) | IQ3_M | 3.06GB | | [Optimus-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q3_K.gguf) | Q3_K | 3.28GB | | [Optimus-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [Optimus-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [Optimus-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [Optimus-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q4_0.gguf) | Q4_0 | 3.83GB | | [Optimus-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [Optimus-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [Optimus-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q4_K.gguf) | Q4_K | 4.07GB | | [Optimus-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [Optimus-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q4_1.gguf) | Q4_1 | 4.24GB | | [Optimus-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q5_0.gguf) | Q5_0 | 4.65GB | | [Optimus-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [Optimus-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q5_K.gguf) | Q5_K | 4.78GB | | [Optimus-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [Optimus-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q5_1.gguf) | Q5_1 | 5.07GB | | [Optimus-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q6_K.gguf) | Q6_K | 5.53GB | | [Optimus-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Q-bert_-_Optimus-7B-gguf/blob/main/Optimus-7B.Q8_0.gguf) | Q8_0 | 7.17GB | Original model description: --- license: apache-2.0 datasets: - meta-math/MetaMathQA language: - en pipeline_tag: text-generation tags: - Math --- ## Optimus-7B Optimus-7B Fine-tuned On [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) with [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA) You can use ChatML format. # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [Here](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/Q-bert/Optimus-7B/results_2023-12-04T18-59-49.207215.json) | Metric | Value | |-----------------------|---------------------------| | Avg. | 69.09 | | ARC (25-shot) | 65.44 | | HellaSwag (10-shot) | 85.41 | | MMLU (5-shot) | 63.61 | | TruthfulQA (0-shot) | 55.79 | | Winogrande (5-shot) | 78.77 | | GSM8K (5-shot) | 65.50 |