LocutusqueXFelladrin-TinyMistral248M-Instruct/README.md

license, datasets, language, pipeline_tag, widget, inference, tags

license	datasets	language	pipeline_tag	widget	inference	tags
apache-2.0	Locutusque/inst_mix_v2_top_100k	en	text-generation	text <|USER|> Design a Neo4j database and Cypher function snippet to Display Extreme Dental hygiene: Using Mouthwash for Analysis for Beginners. Implement if/else or switch/case statements to handle different conditions related to the Consent. Provide detailed comments explaining your control flow and the reasoning behind each decision. <|ASSISTANT|> text <|USER|> Write me a story about a magical place. <|ASSISTANT|> text <|USER|> Write me an essay about the life of George Washington <|ASSISTANT|> text <|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> text <|USER|> Craft me a list of some nice places to visit around the world. <|ASSISTANT|> text <|USER|> How to manage a lazy employee: Address the employee verbally. Don't allow an employee's laziness or lack of enthusiasm to become a recurring issue. Tell the employee you're hoping to speak with them about workplace expectations and performance, and schedule a time to sit down together. Question: To manage a lazy employee, it is suggested to talk to the employee. True, False, or Neither? <|ASSISTANT|>	parameters temperature do_sample top_p top_k max_new_tokens repetition_penalty 0.5 true 0.5 30 250 1.15	merge

LocutusqueXFelladrin-TinyMistral248M-Instruct

This model was created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using mergekit. After the two models were merged, the resulting model was further trained on ~20,000 examples on the Locutusque/inst_mix_v2_top_100k at a low learning rate to further normalize weights. The following is the YAML config used to merge:

models:
  - model: Felladrin/TinyMistral-248M-SFT-v4
    parameters:
      weight: 0.5
  - model: Locutusque/TinyMistral-248M-Instruct
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16

The resulting model combines the best of both worlds. With Locutusque/TinyMistral-248M-Instruct's coding capabilities and reasoning skills, and Felladrin/TinyMistral-248M-SFT-v4's low hallucination and instruction-following capabilities. The resulting model has an incredible performance considering its size.

Evaluation

Found in the Open LLM Leaderboard.