--- language: - en - de library_name: transformers pipeline_tag: text-generation license: apache-2.0 tags: - merge - mergekit --- ![image/png](https://huggingface.co/datasets/malteos/images/resolve/main/hermeo.medium.png) _Hermes + Leo = Hermeo_ # Hermeo-7B A German-English language model merged from [DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2) and [leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat) using [mergekit](https://github.com/cg123/mergekit). Both base models are fine-tuned versions of [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). ### Model details - **Merged from:** [leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat) and [DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2) - **Model type:** Causal decoder-only transformer language model - **Languages:** English and German - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html) ### How to use You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility: ```python >>> from transformers import pipeline, set_seed >>> generator = pipeline('text-generation', model='malteos/hermeo-7b') >>> set_seed(42) >>> generator("Hallo, Ich bin ein Sprachmodell,", max_length=40, num_return_sequences=1) [{'generated_text': 'Hallo, Ich bin ein Sprachmodell, das dir bei der Übersetzung von Texten zwischen Deutsch und Englisch helfen kann. Wenn du mir einen Text in Deutsch'}] ``` ### Acknowledgements - This model release is heavily inspired by [Weyaxi/OpenHermes-2.5-neural-chat-v3-2-Slerp](https://huggingface.co/Weyaxi/OpenHermes-2.5-neural-chat-v3-2-Slerp) - Thanks to the authors of the base models: [Mistral](https://mistral.ai/), [LAION](https://laion.ai/), [HessianAI](https://hessian.ai/), [Open Access AI Collective](https://huggingface.co/openaccess-ai-collective), [@teknium](https://huggingface.co/teknium), [@bjoernp](https://huggingface.co/bjoernp) - The [German evaluation datasets and scripts](https://github.com/bjoernpl/lm-evaluation-harness-de/tree/mmlu_de) from [@bjoernp](https://huggingface.co/bjoernp) were used. - The computing resources from [DFKI's PEGASUS cluster](https://pegasus.dfki.de/) were used for the evaluation. ## Evaluation The evaluation methdology of the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) is followed. ### German benchmarks | **German tasks:** | **MMLU-DE** | **Hellaswag-DE** | **ARC-DE** |**Average** | |-------------------------------|-------------|---------------|--------------|--------------| | **Models / Few-shots:** | _(5 shots)_ | _(10 shots)_ | _(24 shots)_ | | | _7B parameters_ | | | | | | llama-2-7b | 0.400 | 0.513 | 0.381 | 0.431 | | leo-hessianai-7b | 0.400 | 0.609 | 0.429 | 0.479 | | bloom-6b4-clp-german | 0.274 | 0.550 | 0.351 | 0.392 | | mistral-7b | **0.524** | 0.588 | 0.473 | 0.528 | | leo-mistral-hessianai-7b | 0.481 | 0.663 | 0.485 | 0.543 | | leo-mistral-hessianai-7b-chat | 0.458 | 0.617 | 0.465 | 0.513 | | DPOpenHermes-7B-v2 | 0.517 | 0.603 | 0.515 | 0.545 | | hermeo-7b (this model) | 0.511 | **0.668** | **0.528** | **0.569** | | _13B parameters_ | | | | | | llama-2-13b | 0.469 | 0.581 | 0.468 | 0.506 | | leo-hessianai-13b | **0.486** | **0.658** | **0.509** | **0.551** | | _70B parameters_ | | | | | | llama-2-70b | 0.597 | 0.674 | 0.561 | 0.611 | | leo-hessianai-70b | **0.653** | **0.721** | **0.600** | **0.658** | ### English benchmarks | **English tasks:** | **MMLU** | **Hellaswag** | **ARC** | **Average** | |----------------------------|-------------|---------------|--------------|-------------| | **Models / Few-shots:** | _(5 shots)_ | _(10 shots)_ | _(24 shots)_ | | | llama-2-7b | 0.466 | 0.786 | 0.530 | 0.594 | | leolm-hessianai-7b | 0.423 | 0.759 | 0.522 | 0.568 | | bloom-6b4-clp-german | 0.264 | 0.525 | 0.328 | 0.372 | | mistral-7b | **0.635** | **0.832** | 0.607 | **0.691** | | leolm-mistral-hessianai-7b | 0.550 | 0.777 | 0.518 | 0.615 | | hermeo-7b (this model) | 0.601 | 0.821 | **0.620** | 0.681 | ## Prompting / Prompt Template Prompt dialogue template (ChatML format): ``` """ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant """ ``` The model input can contain multiple conversation turns between user and assistant, e.g. ``` <|im_start|>user {prompt 1}<|im_end|> <|im_start|>assistant {reply 1}<|im_end|> <|im_start|>user {prompt 2}<|im_end|> <|im_start|>assistant (...) ``` ## License [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html) ## See also - AWQ quantized version: https://huggingface.co/mayflowergmbh/hermeo-7b-awq