messages listlengths 3 3 | category stringclasses 3
values | tone stringclasses 3
values |
|---|---|---|
[
{
"role": "system",
"content": "You are a helpful customer-support agent for an online electronics store."
},
{
"role": "user",
"content": "(fallback) the product stopped"
},
{
"role": "assistant",
"content": "CUSTOMER: Hi, we're having issues with our electric kettle. We tried repla... | the product stopped | brief and to the point |
[
{
"role": "system",
"content": "You are a helpful customer-support agent for an online electronics store."
},
{
"role": "user",
"content": "(fallback) the customer wants"
},
{
"role": "assistant",
"content": "CUSTOMER: Hello, thank you for calling today to discuss your laptop. I was ... | the customer wants | confused and asking many questions |
[
{
"role": "system",
"content": "You are a helpful customer-support agent for an online electronics store."
},
{
"role": "user",
"content": "(fallback) an item arrived"
},
{
"role": "assistant",
"content": "In today's fast-paced digital age, resolving technical issues is crucial for b... | an item arrived | polite and patient |
[
{
"role": "system",
"content": "You are a helpful customer-support agent for an online electronics store."
},
{
"role": "user",
"content": "(fallback) the product stopped"
},
{
"role": "assistant",
"content": "[Customer message 1]\nI had to replace the ergonomic office chair, and I'm... | the product stopped | confused and asking many questions |
YAML Metadata Warning:The task_categories "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
Synthetic customer-support SFT dataset
Synthetically generated with HuggingFaceTB/SmolLM2-135M-Instruct from seeded scenario prompts (18 products x 16 issue types x 5 customer tones).
- Rows: 4 kept after validation (4 completions failed parsing and were dropped)
- Format:
messagescolumn (system/user/assistant), ready for TRLSFTTrainer - Metadata:
category(issue type),tone(customer tone) - Seed: 42
Generated on 2026-09-02. Model-generated content: review before production use.
- Downloads last month
- 39