Quantization made by Richard Erkhov.
TinyMistral-248M-Instruct - GGUF
Original model description:
pipeline_tag: text-generation
base_model: Locutusque/TinyMistral-248M
license: apache-2.0
datasets:
- Locutusque/InstructMixCleaned
- berkeley-nest/Nectar
language:
- en
widget:
- 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|>
inference:
parameters:
temperature: 0.5
do_sample: True
top_p: 0.5
top_k: 30
max_new_tokens: 250
repetition_penalty: 1.15
Base model Locutusque/TinyMistral-248M fully fine-tuned on Locutusque/InstructMix. During validation, this model achieved an average perplexity of 3.23 on Locutusque/InstructMix dataset.
It has so far been trained on approximately 608,000 examples. More epochs are planned for this model.
