🌡️ LLM Thermometer Reports
This page provides access to all experiment reports generated by LLM Thermometer.
Reports
What are the ethical implications of widespread AI adoption?
Id |
Language Model |
Embedding Model |
# samples |
20250304T140043 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
352 |
What will technology look like in 2050?
Id |
Language Model |
Embedding Model |
# samples |
20250305T170658 |
o3-mini |
jinaai/jina-embeddings-v2-base-en |
32 |
20250304T080143 |
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
1408 |
20250303T144808 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jina-embeddings-v3 |
1408 |
20250303T193518 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
352 |
20250303T204220 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
2816 |
What's the meaning of life?
Id |
Language Model |
Embedding Model |
# samples |
20250304T003734 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
352 |
Write a creative story with six paragraphs.
Id |
Language Model |
Embedding Model |
# samples |
20250304T000411 |
unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit |
jinaai/jina-embeddings-v2-base-en |
352 |
About LLM Thermometer
LLM Thermometer estimates temperature values of Large Language Models through semantic similarity analysis. It analyzes how diverse the responses are for the same prompt to infer the temperature setting used during generation.
Approach
- Generation: Produce multiple responses using the same prompt
- Similarity Analysis: Measure semantic similarity between responses
- Temperature Estimation: Infer temperature based on response diversity
- Higher temperature → More diverse responses (lower similarity)
- Lower temperature → More consistent responses (higher similarity)