TinyMistral-248M-v2-Instruct/README.md

license, datasets, language, inference, widget, base_model

license	datasets	language	inference	widget	base_model
apache-2.0	HuggingFaceH4/ultrachat_200k	en	parameters do_sample temperature top_p top_k max_new_tokens repetition_penalty true 0.1 0.14 12 250 1.1	text <|im_start|>user How do I incorporate visual elements into my writing?<|im_end|> <|im_start|>assistant	Locutusque/TinyMistral-248M-v2

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.