Description

Fine-tuned Locutusque/TinyMistral-248M-v2 on the HuggingFaceH4/ultrachat_200k dataset.

Recommended inference parameters

do_sample: true
temperature: 0.1
top_p: 0.14
top_k: 12
repetition_penalty: 1.1

Recommended prompt template

<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>assistant\n{assistant message}<|endoftext|>

Evaluation

This model will be submitted to the Open LLM Leaderboard.