--- pipeline_tag: text-generation license: mit datasets: - MexIvanov/Vezora-Tested-22k-Python-Alpaca-ru - MexIvanov/CodeExercise-Python-27k-ru - zelkame/ru-stackoverflow-py language: - ru - en --- # Model Card for Model ID ## Model Details ### Model Description - **Developed by:** C.B. Pronin, A.V. Volosova, A.V. Ostroukh, Yu.N. Strogov, V.V. Kurbatov, A.S. Umarova. - **Model type:** GGUF Conversion and quantizations of model "MexIvanov/zephyr-python-ru-merged" made for ease of inference. - **Language(s) (NLP):** Russian, English, Python - **License:** MIT - **Finetuned from model:** HuggingFaceH4/zephyr-7b-beta ### Model Sources - **Paper:** https://arxiv.org/abs/2409.09353 ## Uses An experimental finetune of Zephyr-7b-beta, aimed at improving coding performance and support for coding-related instructions written in Russian language. ### Direct Use Instruction-based coding in Python, based of instructions written in natural language (English or Russian) Prompt template - Zephyr: ``` <|system|> <|user|> {prompt} <|assistant|> ``` ## Provided files (quantization info taken from TheBloke/zephyr-7B-beta-GGUF) | Name | Quant method | Bits | Use case | | ---- | ---- | ---- | ----- | | [zephyr-python-ru-q4_K_M.gguf](https://huggingface.co/MexIvanov/zephyr-python-ru-gguf/blob/main/zephyr-python-ru-q4_K_M.gguf) | Q4_K_M | 4 | medium, balanced quality - recommended | | [zephyr-python-ru-q6_K.gguf](https://huggingface.co/MexIvanov/zephyr-python-ru-gguf/blob/main/zephyr-python-ru-q6_K.gguf) | Q6_K | 6 | very large, extremely low quality loss | ## Bias, Risks, and Limitations This adapter model is intended (but not limited) for research usage only. It was trained on a code based instruction set and it does not have any moderation mechanisms. Use at your own risk, we are not responsible for any usage or output of this model. Quote from Zephyr (base-model) repository: "Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.1), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this." ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.