id stringlengths 14 14 | category stringclasses 6
values | topic stringclasses 20
values | messages listlengths 2 2 | synthetic bool 1
class | source stringclasses 1
value | quality_note stringclasses 1
value |
|---|---|---|---|---|---|---|
compactlm-0507 | glossary | model distillation | [
{
"role": "user",
"content": "For technical documentation: Write a short glossary entry for model distillation, including one practical consideration."
},
{
"role": "assistant",
"content": "Model distillation: training a smaller student model using guidance from a stronger teacher. In practice, ... | true | template-generated | unreviewed demonstration sample |
compactlm-0087 | extraction | model distillation | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing model distillation and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"model distillation\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0178 | summarization | hallucination detection | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring hallucination detection. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team w... | true | template-generated | unreviewed demonstration sample |
compactlm-0141 | glossary | GPU inference | [
{
"role": "user",
"content": "For a student project: Write a short glossary entry for GPU inference, including one practical consideration."
},
{
"role": "assistant",
"content": "Gpu inference: running a trained model on a graphics processor to produce predictions or outputs. In practice, evalua... | true | template-generated | unreviewed demonstration sample |
compactlm-0361 | definition | GPU inference | [
{
"role": "user",
"content": "Answer concisely: Explain GPU inference in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Gpu inference means running a trained model on a graphics processor to produce predictions or outputs."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0479 | evaluation | classifier calibration | [
{
"role": "user",
"content": "Answer concisely: Give two responsible evaluation checks for a demonstration involving classifier calibration."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for classifier calibration.\n2. Inspect failures and disclose limitations befo... | true | template-generated | unreviewed demonstration sample |
compactlm-0378 | definition | hallucination detection | [
{
"role": "user",
"content": "Answer concisely: Explain hallucination detection in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Hallucination detection means identifying generated claims that lack support or are incorrect."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0400 | glossary | synthetic datasets | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for synthetic datasets, including one practical consideration."
},
{
"role": "assistant",
"content": "Synthetic datasets: collections of artificially generated examples rather than directly observed samples. In practice... | true | template-generated | unreviewed demonstration sample |
compactlm-0477 | evaluation | model deployment | [
{
"role": "user",
"content": "Answer concisely: Give two responsible evaluation checks for a demonstration involving model deployment."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for model deployment.\n2. Inspect failures and disclose limitations before drawing c... | true | template-generated | unreviewed demonstration sample |
compactlm-0516 | glossary | context windows | [
{
"role": "user",
"content": "For technical documentation: Write a short glossary entry for context windows, including one practical consideration."
},
{
"role": "assistant",
"content": "Context windows: the limit on how many input and generated tokens a model can consider in one request. In pra... | true | template-generated | unreviewed demonstration sample |
compactlm-0561 | extraction | GPU inference | [
{
"role": "user",
"content": "For technical documentation: Extract the focus area and next step as JSON from: \"We are testing GPU inference and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"GPU inference\", \"next_step\": \"record latency and accu... | true | template-generated | unreviewed demonstration sample |
compactlm-0100 | extraction | synthetic datasets | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing synthetic datasets and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"synthetic datasets\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0444 | extraction | embedding search | [
{
"role": "user",
"content": "Answer concisely: Extract the focus area and next step as JSON from: \"We are testing embedding search and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"embedding search\", \"next_step\": \"record latency and accuracy\... | true | template-generated | unreviewed demonstration sample |
compactlm-0389 | glossary | prompt evaluation | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for prompt evaluation, including one practical consideration."
},
{
"role": "assistant",
"content": "Prompt evaluation: testing how model outputs change in response to prompts. In practice, evaluate its benefits and tra... | true | template-generated | unreviewed demonstration sample |
compactlm-0161 | summarization | GPU inference | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring GPU inference. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot ... | true | template-generated | unreviewed demonstration sample |
compactlm-0437 | rewriting | model deployment | [
{
"role": "user",
"content": "Answer concisely: Rewrite for clarity: \"We are doing model deployment stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating model deployment and will consider expanding the experiment after reviewing... | true | template-generated | unreviewed demonstration sample |
compactlm-0162 | summarization | on-device AI | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring on-device AI. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot o... | true | template-generated | unreviewed demonstration sample |
compactlm-0008 | definition | dataset curation | [
{
"role": "user",
"content": "Explain dataset curation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Dataset curation means selecting, cleaning, and documenting examples used for training or evaluation."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0579 | extraction | classifier calibration | [
{
"role": "user",
"content": "For technical documentation: Extract the focus area and next step as JSON from: \"We are testing classifier calibration and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"classifier calibration\", \"next_step\": \"recor... | true | template-generated | unreviewed demonstration sample |
compactlm-0046 | summarization | batching | [
{
"role": "user",
"content": "Summarize this note in a sentence: \"Our team is exploring batching. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot batching, measure outcomes, ... | true | template-generated | unreviewed demonstration sample |
compactlm-0082 | extraction | on-device AI | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing on-device AI and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"on-device AI\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0136 | definition | context windows | [
{
"role": "user",
"content": "For a student project: Explain context windows in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Context windows means the limit on how many input and generated tokens a model can consider in one request."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0386 | glossary | batching | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for batching, including one practical consideration."
},
{
"role": "assistant",
"content": "Batching: processing multiple requests together to improve hardware utilization. In practice, evaluate its benefits and trade-o... | true | template-generated | unreviewed demonstration sample |
compactlm-0235 | evaluation | training validation | [
{
"role": "user",
"content": "For a student project: Give two responsible evaluation checks for a demonstration involving training validation."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for training validation.\n2. Inspect failures and disclose limitations befor... | true | template-generated | unreviewed demonstration sample |
compactlm-0083 | extraction | tokenization | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing tokenization and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"tokenization\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0180 | summarization | synthetic datasets | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring synthetic datasets. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will p... | true | template-generated | unreviewed demonstration sample |
compactlm-0344 | evaluation | embedding search | [
{
"role": "user",
"content": "For a small research prototype: Give two responsible evaluation checks for a demonstration involving embedding search."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for embedding search.\n2. Inspect failures and disclose limitations be... | true | template-generated | unreviewed demonstration sample |
compactlm-0349 | evaluation | prompt evaluation | [
{
"role": "user",
"content": "For a small research prototype: Give two responsible evaluation checks for a demonstration involving prompt evaluation."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for prompt evaluation.\n2. Inspect failures and disclose limitations ... | true | template-generated | unreviewed demonstration sample |
compactlm-0407 | summarization | model distillation | [
{
"role": "user",
"content": "Answer concisely: Summarize this note in a sentence: \"Our team is exploring model distillation. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot ... | true | template-generated | unreviewed demonstration sample |
compactlm-0044 | summarization | embedding search | [
{
"role": "user",
"content": "Summarize this note in a sentence: \"Our team is exploring embedding search. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot embedding search, me... | true | template-generated | unreviewed demonstration sample |
compactlm-0460 | extraction | synthetic datasets | [
{
"role": "user",
"content": "Answer concisely: Extract the focus area and next step as JSON from: \"We are testing synthetic datasets and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"synthetic datasets\", \"next_step\": \"record latency and accur... | true | template-generated | unreviewed demonstration sample |
compactlm-0550 | rewriting | code generation | [
{
"role": "user",
"content": "For technical documentation: Rewrite for clarity: \"We are doing code generation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating code generation and will consider expanding the experiment after ... | true | template-generated | unreviewed demonstration sample |
compactlm-0191 | rewriting | latency optimization | [
{
"role": "user",
"content": "For a student project: Rewrite for clarity: \"We are doing latency optimization stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating latency optimization and will consider expanding the experiment af... | true | template-generated | unreviewed demonstration sample |
compactlm-0343 | evaluation | tokenization | [
{
"role": "user",
"content": "For a small research prototype: Give two responsible evaluation checks for a demonstration involving tokenization."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for tokenization.\n2. Inspect failures and disclose limitations before dra... | true | template-generated | unreviewed demonstration sample |
compactlm-0164 | summarization | embedding search | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring embedding search. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pil... | true | template-generated | unreviewed demonstration sample |
compactlm-0279 | glossary | classifier calibration | [
{
"role": "user",
"content": "For a small research prototype: Write a short glossary entry for classifier calibration, including one practical consideration."
},
{
"role": "assistant",
"content": "Classifier calibration: checking whether predicted probabilities reflect observed outcome frequenci... | true | template-generated | unreviewed demonstration sample |
compactlm-0035 | glossary | training validation | [
{
"role": "user",
"content": "Write a short glossary entry for training validation, including one practical consideration."
},
{
"role": "assistant",
"content": "Training validation: using held-out examples to assess model behavior during development. In practice, evaluate its benefits and trade... | true | template-generated | unreviewed demonstration sample |
compactlm-0200 | rewriting | synthetic datasets | [
{
"role": "user",
"content": "For a student project: Rewrite for clarity: \"We are doing synthetic datasets stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating synthetic datasets and will consider expanding the experiment after ... | true | template-generated | unreviewed demonstration sample |
compactlm-0423 | rewriting | tokenization | [
{
"role": "user",
"content": "Answer concisely: Rewrite for clarity: \"We are doing tokenization stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating tokenization and will consider expanding the experiment after reviewing the res... | true | template-generated | unreviewed demonstration sample |
compactlm-0565 | extraction | quantization | [
{
"role": "user",
"content": "For technical documentation: Extract the focus area and next step as JSON from: \"We are testing quantization and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"quantization\", \"next_step\": \"record latency and accura... | true | template-generated | unreviewed demonstration sample |
compactlm-0586 | evaluation | batching | [
{
"role": "user",
"content": "For technical documentation: Give two responsible evaluation checks for a demonstration involving batching."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for batching.\n2. Inspect failures and disclose limitations before drawing conclu... | true | template-generated | unreviewed demonstration sample |
compactlm-0384 | glossary | embedding search | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for embedding search, including one practical consideration."
},
{
"role": "assistant",
"content": "Embedding search: retrieving items using similarity between numerical vector representations. In practice, evaluate its... | true | template-generated | unreviewed demonstration sample |
compactlm-0225 | evaluation | quantization | [
{
"role": "user",
"content": "For a student project: Give two responsible evaluation checks for a demonstration involving quantization."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for quantization.\n2. Inspect failures and disclose limitations before drawing conc... | true | template-generated | unreviewed demonstration sample |
compactlm-0338 | extraction | hallucination detection | [
{
"role": "user",
"content": "For a small research prototype: Extract the focus area and next step as JSON from: \"We are testing hallucination detection and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"hallucination detection\", \"next_step\": \"... | true | template-generated | unreviewed demonstration sample |
compactlm-0045 | summarization | quantization | [
{
"role": "user",
"content": "Summarize this note in a sentence: \"Our team is exploring quantization. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot quantization, measure ou... | true | template-generated | unreviewed demonstration sample |
compactlm-0249 | definition | prompt evaluation | [
{
"role": "user",
"content": "For a small research prototype: Explain prompt evaluation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Prompt evaluation means testing how model outputs change in response to prompts."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0142 | glossary | on-device AI | [
{
"role": "user",
"content": "For a student project: Write a short glossary entry for on-device AI, including one practical consideration."
},
{
"role": "assistant",
"content": "On-device ai: executing AI models locally on a phone, laptop, or other device. In practice, evaluate its benefits and ... | true | template-generated | unreviewed demonstration sample |
compactlm-0494 | definition | fine-tuning | [
{
"role": "user",
"content": "For technical documentation: Explain fine-tuning in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Fine-tuning means continuing model training on a smaller task- or domain-specific dataset."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0190 | rewriting | code generation | [
{
"role": "user",
"content": "For a student project: Rewrite for clarity: \"We are doing code generation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating code generation and will consider expanding the experiment after review... | true | template-generated | unreviewed demonstration sample |
compactlm-0098 | extraction | hallucination detection | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing hallucination detection and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"hallucination detection\", \"next_step\": \"record latency and accuracy\"}"
... | true | template-generated | unreviewed demonstration sample |
compactlm-0021 | glossary | GPU inference | [
{
"role": "user",
"content": "Write a short glossary entry for GPU inference, including one practical consideration."
},
{
"role": "assistant",
"content": "Gpu inference: running a trained model on a graphics processor to produce predictions or outputs. In practice, evaluate its benefits and tra... | true | template-generated | unreviewed demonstration sample |
compactlm-0276 | glossary | context windows | [
{
"role": "user",
"content": "For a small research prototype: Write a short glossary entry for context windows, including one practical consideration."
},
{
"role": "assistant",
"content": "Context windows: the limit on how many input and generated tokens a model can consider in one request. In ... | true | template-generated | unreviewed demonstration sample |
compactlm-0573 | extraction | retrieval augmentation | [
{
"role": "user",
"content": "For technical documentation: Extract the focus area and next step as JSON from: \"We are testing retrieval augmentation and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"retrieval augmentation\", \"next_step\": \"recor... | true | template-generated | unreviewed demonstration sample |
compactlm-0490 | definition | code generation | [
{
"role": "user",
"content": "For technical documentation: Explain code generation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Code generation means producing programming code from natural-language or other input."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0251 | definition | latency optimization | [
{
"role": "user",
"content": "For a small research prototype: Explain latency optimization in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Latency optimization means reducing the delay between an input request and a generated response."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0095 | extraction | training validation | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing training validation and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"training validation\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0354 | evaluation | fine-tuning | [
{
"role": "user",
"content": "For a small research prototype: Give two responsible evaluation checks for a demonstration involving fine-tuning."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for fine-tuning.\n2. Inspect failures and disclose limitations before drawi... | true | template-generated | unreviewed demonstration sample |
compactlm-0445 | extraction | quantization | [
{
"role": "user",
"content": "Answer concisely: Extract the focus area and next step as JSON from: \"We are testing quantization and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"quantization\", \"next_step\": \"record latency and accuracy\"}"
}
... | true | template-generated | unreviewed demonstration sample |
compactlm-0430 | rewriting | code generation | [
{
"role": "user",
"content": "Answer concisely: Rewrite for clarity: \"We are doing code generation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating code generation and will consider expanding the experiment after reviewing t... | true | template-generated | unreviewed demonstration sample |
compactlm-0168 | summarization | dataset curation | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring dataset curation. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pil... | true | template-generated | unreviewed demonstration sample |
compactlm-0472 | evaluation | memory usage | [
{
"role": "user",
"content": "Answer concisely: Give two responsible evaluation checks for a demonstration involving memory usage."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for memory usage.\n2. Inspect failures and disclose limitations before drawing conclusio... | true | template-generated | unreviewed demonstration sample |
compactlm-0547 | rewriting | model distillation | [
{
"role": "user",
"content": "For technical documentation: Rewrite for clarity: \"We are doing model distillation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating model distillation and will consider expanding the experiment ... | true | template-generated | unreviewed demonstration sample |
compactlm-0553 | rewriting | retrieval augmentation | [
{
"role": "user",
"content": "For technical documentation: Rewrite for clarity: \"We are doing retrieval augmentation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating retrieval augmentation and will consider expanding the exp... | true | template-generated | unreviewed demonstration sample |
compactlm-0198 | rewriting | hallucination detection | [
{
"role": "user",
"content": "For a student project: Rewrite for clarity: \"We are doing hallucination detection stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating hallucination detection and will consider expanding the experim... | true | template-generated | unreviewed demonstration sample |
compactlm-0406 | summarization | batching | [
{
"role": "user",
"content": "Answer concisely: Summarize this note in a sentence: \"Our team is exploring batching. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot batching, ... | true | template-generated | unreviewed demonstration sample |
compactlm-0270 | glossary | code generation | [
{
"role": "user",
"content": "For a small research prototype: Write a short glossary entry for code generation, including one practical consideration."
},
{
"role": "assistant",
"content": "Code generation: producing programming code from natural-language or other input. In practice, evaluate it... | true | template-generated | unreviewed demonstration sample |
compactlm-0286 | summarization | batching | [
{
"role": "user",
"content": "For a small research prototype: Summarize this note in a sentence: \"Our team is exploring batching. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pi... | true | template-generated | unreviewed demonstration sample |
compactlm-0013 | definition | retrieval augmentation | [
{
"role": "user",
"content": "Explain retrieval augmentation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Retrieval augmentation means supplementing generation with information retrieved from an external collection."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0426 | rewriting | batching | [
{
"role": "user",
"content": "Answer concisely: Rewrite for clarity: \"We are doing batching stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating batching and will consider expanding the experiment after reviewing the results."
... | true | template-generated | unreviewed demonstration sample |
compactlm-0464 | evaluation | embedding search | [
{
"role": "user",
"content": "Answer concisely: Give two responsible evaluation checks for a demonstration involving embedding search."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for embedding search.\n2. Inspect failures and disclose limitations before drawing c... | true | template-generated | unreviewed demonstration sample |
compactlm-0542 | rewriting | on-device AI | [
{
"role": "user",
"content": "For technical documentation: Rewrite for clarity: \"We are doing on-device AI stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating on-device AI and will consider expanding the experiment after review... | true | template-generated | unreviewed demonstration sample |
compactlm-0377 | definition | model deployment | [
{
"role": "user",
"content": "Answer concisely: Explain model deployment in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Model deployment means making a model available for use in an application or service."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0523 | summarization | tokenization | [
{
"role": "user",
"content": "For technical documentation: Summarize this note in a sentence: \"Our team is exploring tokenization. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will p... | true | template-generated | unreviewed demonstration sample |
compactlm-0272 | glossary | memory usage | [
{
"role": "user",
"content": "For a small research prototype: Write a short glossary entry for memory usage, including one practical consideration."
},
{
"role": "assistant",
"content": "Memory usage: the amount of RAM or accelerator memory consumed during execution. In practice, evaluate its be... | true | template-generated | unreviewed demonstration sample |
compactlm-0303 | rewriting | tokenization | [
{
"role": "user",
"content": "For a small research prototype: Rewrite for clarity: \"We are doing tokenization stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating tokenization and will consider expanding the experiment after rev... | true | template-generated | unreviewed demonstration sample |
compactlm-0336 | extraction | context windows | [
{
"role": "user",
"content": "For a small research prototype: Extract the focus area and next step as JSON from: \"We are testing context windows and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"context windows\", \"next_step\": \"record latency a... | true | template-generated | unreviewed demonstration sample |
compactlm-0396 | glossary | context windows | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for context windows, including one practical consideration."
},
{
"role": "assistant",
"content": "Context windows: the limit on how many input and generated tokens a model can consider in one request. In practice, eval... | true | template-generated | unreviewed demonstration sample |
compactlm-0077 | rewriting | model deployment | [
{
"role": "user",
"content": "Rewrite for clarity: \"We are doing model deployment stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating model deployment and will consider expanding the experiment after reviewing the results."
}... | true | template-generated | unreviewed demonstration sample |
compactlm-0206 | extraction | batching | [
{
"role": "user",
"content": "For a student project: Extract the focus area and next step as JSON from: \"We are testing batching and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"batching\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0582 | evaluation | on-device AI | [
{
"role": "user",
"content": "For technical documentation: Give two responsible evaluation checks for a demonstration involving on-device AI."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for on-device AI.\n2. Inspect failures and disclose limitations before drawin... | true | template-generated | unreviewed demonstration sample |
compactlm-0316 | rewriting | context windows | [
{
"role": "user",
"content": "For a small research prototype: Rewrite for clarity: \"We are doing context windows stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating context windows and will consider expanding the experiment aft... | true | template-generated | unreviewed demonstration sample |
compactlm-0498 | definition | hallucination detection | [
{
"role": "user",
"content": "For technical documentation: Explain hallucination detection in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Hallucination detection means identifying generated claims that lack support or are incorrect."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0114 | evaluation | fine-tuning | [
{
"role": "user",
"content": "Give two responsible evaluation checks for a demonstration involving fine-tuning."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for fine-tuning.\n2. Inspect failures and disclose limitations before drawing conclusions."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0009 | definition | prompt evaluation | [
{
"role": "user",
"content": "Explain prompt evaluation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Prompt evaluation means testing how model outputs change in response to prompts."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0219 | extraction | classifier calibration | [
{
"role": "user",
"content": "For a student project: Extract the focus area and next step as JSON from: \"We are testing classifier calibration and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"classifier calibration\", \"next_step\": \"record late... | true | template-generated | unreviewed demonstration sample |
compactlm-0089 | extraction | prompt evaluation | [
{
"role": "user",
"content": "Extract the focus area and next step as JSON from: \"We are testing prompt evaluation and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"prompt evaluation\", \"next_step\": \"record latency and accuracy\"}"
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0297 | summarization | model deployment | [
{
"role": "user",
"content": "For a small research prototype: Summarize this note in a sentence: \"Our team is exploring model deployment. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team... | true | template-generated | unreviewed demonstration sample |
compactlm-0188 | rewriting | dataset curation | [
{
"role": "user",
"content": "For a student project: Rewrite for clarity: \"We are doing dataset curation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating dataset curation and will consider expanding the experiment after revi... | true | template-generated | unreviewed demonstration sample |
compactlm-0166 | summarization | batching | [
{
"role": "user",
"content": "For a student project: Summarize this note in a sentence: \"Our team is exploring batching. We plan to test it on a small dataset first, measure the result, and document limitations before expanding.\""
},
{
"role": "assistant",
"content": "The team will pilot batch... | true | template-generated | unreviewed demonstration sample |
compactlm-0589 | evaluation | prompt evaluation | [
{
"role": "user",
"content": "For technical documentation: Give two responsible evaluation checks for a demonstration involving prompt evaluation."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for prompt evaluation.\n2. Inspect failures and disclose limitations bef... | true | template-generated | unreviewed demonstration sample |
compactlm-0212 | extraction | memory usage | [
{
"role": "user",
"content": "For a student project: Extract the focus area and next step as JSON from: \"We are testing memory usage and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"memory usage\", \"next_step\": \"record latency and accuracy\"}"... | true | template-generated | unreviewed demonstration sample |
compactlm-0101 | evaluation | GPU inference | [
{
"role": "user",
"content": "Give two responsible evaluation checks for a demonstration involving GPU inference."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for GPU inference.\n2. Inspect failures and disclose limitations before drawing conclusions."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0323 | extraction | tokenization | [
{
"role": "user",
"content": "For a small research prototype: Extract the focus area and next step as JSON from: \"We are testing tokenization and will record latency and accuracy.\""
},
{
"role": "assistant",
"content": "{\"focus_area\": \"tokenization\", \"next_step\": \"record latency and acc... | true | template-generated | unreviewed demonstration sample |
compactlm-0390 | glossary | code generation | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for code generation, including one practical consideration."
},
{
"role": "assistant",
"content": "Code generation: producing programming code from natural-language or other input. In practice, evaluate its benefits and... | true | template-generated | unreviewed demonstration sample |
compactlm-0388 | glossary | dataset curation | [
{
"role": "user",
"content": "Answer concisely: Write a short glossary entry for dataset curation, including one practical consideration."
},
{
"role": "assistant",
"content": "Dataset curation: selecting, cleaning, and documenting examples used for training or evaluation. In practice, evaluate ... | true | template-generated | unreviewed demonstration sample |
compactlm-0014 | definition | fine-tuning | [
{
"role": "user",
"content": "Explain fine-tuning in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Fine-tuning means continuing model training on a smaller task- or domain-specific dataset."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0274 | glossary | fine-tuning | [
{
"role": "user",
"content": "For a small research prototype: Write a short glossary entry for fine-tuning, including one practical consideration."
},
{
"role": "assistant",
"content": "Fine-tuning: continuing model training on a smaller task- or domain-specific dataset. In practice, evaluate it... | true | template-generated | unreviewed demonstration sample |
compactlm-0465 | evaluation | quantization | [
{
"role": "user",
"content": "Answer concisely: Give two responsible evaluation checks for a demonstration involving quantization."
},
{
"role": "assistant",
"content": "1. Record the test setup and baseline for quantization.\n2. Inspect failures and disclose limitations before drawing conclusio... | true | template-generated | unreviewed demonstration sample |
compactlm-0367 | definition | model distillation | [
{
"role": "user",
"content": "Answer concisely: Explain model distillation in one sentence for a beginner."
},
{
"role": "assistant",
"content": "Model distillation means training a smaller student model using guidance from a stronger teacher."
}
] | true | template-generated | unreviewed demonstration sample |
compactlm-0313 | rewriting | retrieval augmentation | [
{
"role": "user",
"content": "For a small research prototype: Rewrite for clarity: \"We are doing retrieval augmentation stuff and checking if it is good, maybe we try bigger later.\""
},
{
"role": "assistant",
"content": "We are evaluating retrieval augmentation and will consider expanding the ... | true | template-generated | unreviewed demonstration sample |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.