Datasets:
messages listlengths 2 595 | tools unknown | source stringclasses 11
values | license listlengths 1 5 | subset stringclasses 43
values | record_id stringlengths 33 110 | extraction_timestamp stringdate 2025-06-01 00:00:00 2025-06-01 00:00:00 |
|---|---|---|---|---|---|---|
[
{
"role": "user",
"content": "What formal model can capture the propagation semantics of W3C Trace‑Context across heterogeneous microservices using OpenTelemetry, and how does it guarantee causal consistency under asynchronous messaging and partial failures?",
"reasoning_content": null,
"tool_calls"... | null | ianncity/KIMI-K2.5-1000000x | [
"apache-2.0"
] | General-Distillation | ianncity/KIMI-K2.5-1000000x::General-Distillation::00363 | 2025-06-01T00:00:00+00:00 |
[
{
"role": "user",
"content": "That's really interesting! What about grapes used to make juice? Are they harvested differently too?",
"reasoning_content": null,
"tool_calls": null,
"tool_name": null
},
{
"role": "assistant",
"content": "Yes! Juice grapes are harvested quite differentl... | null | ianncity/KIMI-K2.5-1000000x | [
"apache-2.0"
] | General-Distillation | ianncity/KIMI-K2.5-1000000x::General-Distillation::01531 | 2025-06-01T00:00:00+00:00 |
[
{
"role": "system",
"content": "You are an autonomous software agent. You never write or modify code without first creating an explicit, written plan.\n\n<core_principle>\nPlan first, execute second. No exceptions.\n</core_principle>\n\n<planning_phase>\nBefore touching any source code, you MUST produce a w... | null | nvidia/Nemotron-SFT-SWE-v3 | [
"cc-by-4.0",
"apache-2.0",
"mit",
"bsd-3-clause",
"bsd-2-clause"
] | train | nvidia/Nemotron-SFT-SWE-v3::train::1ea65544-0655-4d7f-80f0-2057c22b67df | 2025-06-01T00:00:00+00:00 |
[
{
"role": "system",
"content": "You are an expert in composing functions. You are given a question and a set of possible functions. Based on the question, you will need to make one or more function/tool calls to achieve the purpose.\nIf none of the functions can be used, point it out. If the given question ... | [
{
"type": "function",
"function": {
"name": "authenticate_travel",
"description": "This tool belongs to the travel system, which allows users to book flights, manage credit cards, and view budget information. Tool description: Authenticate the user with the travel API",
"parameters": {
... | Bingguang/HardGen | [
"apache-2.0"
] | default | Bingguang/HardGen::default::02712 | 2025-06-01T00:00:00+00:00 |
[{"role":"user","content":"Löse das folgende Mathematikaufgabe. Stelle sicher, dass die Antwort (un(...TRUNCATED) | null | nvidia/Nemotron-SFT-Multilingual-v1 | [
"cc-by-4.0",
"cc-by-sa-4.0"
] | math_de | nvidia/Nemotron-SFT-Multilingual-v1::math_de::4891b98c-f226-4f8d-a178-8f9e5652c1b2 | 2025-06-01T00:00:00+00:00 |
[{"role":"user","content":"Considera el grupo simple espordádico $G \\cong \\mathrm{Fi}_{23}$. Para(...TRUNCATED) | null | nvidia/Nemotron-SFT-Multilingual-v1 | [
"cc-by-4.0",
"cc-by-sa-4.0"
] | code_es | nvidia/Nemotron-SFT-Multilingual-v1::code_es::e1170b07-0d5b-4ff2-9803-90c561503da9 | 2025-06-01T00:00:00+00:00 |
[{"role":"user","content":"Use your knowledge to determine the correct answer to the question, and p(...TRUNCATED) | null | nvidia/Nemotron-SFT-Science-v2 | [
"cc-by-sa-4.0",
"CC BY-SA 4.0"
] | rqa | nvidia/Nemotron-SFT-Science-v2::rqa::e614c3147d894ebcafb521672d6e4eaa | 2025-06-01T00:00:00+00:00 |
[{"role":"system","content":"You are a helpful and harmless assistant.\n\nYou are not allowed to use(...TRUNCATED) | null | nvidia/Nemotron-SFT-Instruction-Following-Chat-v3 | [
"odc-by",
"cc-by-4.0",
"apache-2.0"
] | instruction_following | "nvidia/Nemotron-SFT-Instruction-Following-Chat-v3::instruction_following::95da38e6-4da8-4152-9846-b(...TRUNCATED) | 2025-06-01T00:00:00+00:00 |
[{"role":"system","content":"You are a coding agent running in the Codex CLI, a terminal-based codin(...TRUNCATED) | null | nvidia/Nemotron-SFT-SWE-v3 | [
"cc-by-4.0",
"apache-2.0",
"mit",
"bsd-3-clause",
"bsd-2-clause"
] | train | nvidia/Nemotron-SFT-SWE-v3::train::fff1d55b-cbf7-4041-b193-dfad6f4fba23 | 2025-06-01T00:00:00+00:00 |
[{"role":"user","content":"En una variedad sub-Riemanniana de dimensión 5 con distribución de rang(...TRUNCATED) | null | ianncity/KIMI-K2.5-1000000x | [
"apache-2.0"
] | MultilingualSTEM | ianncity/KIMI-K2.5-1000000x::MultilingualSTEM::00973 | 2025-06-01T00:00:00+00:00 |
End of preview. Expand in Data Studio
Calibration Dataset
Description
This dataset contains 32107 calibration examples for LLM quantization using LLM-Compressor.
Schema
| Column | Type | Description |
|---|---|---|
messages |
list[dict] |
Conversation turns with role, content, optional reasoning_content/tool_calls |
tools |
json (list) |
JSON list of tool definitions (function schemas); null when absent |
source |
str |
Source dataset identifier |
license |
list[str] |
SPDX license identifiers (multiple may apply) |
subset |
str |
Source subset name |
record_id |
str |
Unique record identifier ({source}::{subset}::{index}) |
extraction_timestamp |
str |
ISO 8601 extraction timestamp |
Source Attribution
- Sources: Bingguang/HardGen, FreedomIntelligence/medical-o1-reasoning-SFT, HuggingFaceH4/Multilingual-Thinking, ianncity/KIMI-K2.5-1000000x, nvidia/Nemotron-RL-Multichallenge-v1, nvidia/Nemotron-SFT-Instruction-Following-Chat-v3, nvidia/Nemotron-SFT-Math-v4, nvidia/Nemotron-SFT-Multilingual-v1, nvidia/Nemotron-SFT-Multilingual-v2, nvidia/Nemotron-SFT-SWE-v3, nvidia/Nemotron-SFT-Science-v2
- Subsets: English, French, General-Distillation, General-Math, German, Italian, MultilingualSTEM, PHD-Science, Spanish, advanced, code_de, code_es, code_fr, code_hi, code_it, code_ja, code_ko, code_pt, code_zh, default, en, instruction_following, math_de, math_es, math_fr, math_hi, math_it, math_ja, math_ko, math_pt, math_zh, rqa, stem_de, stem_es, stem_fr, stem_hi, stem_it, stem_ja, stem_ko, stem_pt, stem_zh, train, zh
- Licenses: CC BY-SA 4.0, apache-2.0, bsd-2-clause, bsd-3-clause, cc-by-4.0, cc-by-sa-4.0, mit, odc-by
Intended Use
This dataset is designed for calibration in LLM quantization workflows, particularly with the vLLM LLM-Compressor framework.
Usage
from datasets import load_dataset
dataset = load_dataset("Calandracas/calibration-blend")
License
This dataset contains data from multiple sources. See the license column for per-record license information.
- Downloads last month
- 107