100k-GPT-OSS
Collection
100,000-example capped-even blend of GPT-OSS completions from the Nemotron post-training v3 prompt-only collection. • 1 item • Updated
Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: ValueError
Message: Expected object or value
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
for item in generator(*args, **kwargs):
~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 281, in _generate_tables
examples = [ujson_loads(line) for line in batch.splitlines()]
~~~~~~~~~~~^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/utils/json.py", line 20, in ujson_loads
return pd.io.json.ujson_loads(*args, **kwargs)
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
ValueError: Expected object or value
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
~~~~~~~~~~~~~~~~~~~~~~~~~^
builder, max_dataset_size_bytes=max_dataset_size_bytes
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1683, in _prepare_split
for job_id, done, content in self._prepare_split_single(
~~~~~~~~~~~~~~~~~~~~~~~~~~^
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1869, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id string | conversations list | source_custom_id string | model string | source_dataset string | source_repo string | source_collection string | blend string |
|---|---|---|---|---|---|---|---|
29af3e64c11a | [
{
"role": "system",
"content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou... | 29af3e64c11a | openai/gpt-oss-20b | Nemotron-Agentic-v1-prompt-only | jamesdborin/Nemotron-Agentic-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
ae23df501af5 | [
{
"role": "user",
"content": "Decrypt this Caesar cipher text: UIF DBMMFST XFSF GFXFS UIBO UXFMWF PG UIFN. Provide only the decrypted text as your final answer."
},
{
"role": "assistant_analysis",
"content": "Caesar shift? Cipher text: \"UIF DBMMFST XFSF GFXFS UIBO UXFMWF PG UIFN.\" Likely shift... | ae23df501af5 | openai/gpt-oss-20b | Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
0ee093626675 | [
{
"role": "user",
"content": "Document: Cardamine occulta\n\n# Cardamine occulta\n\n<i>Cardamine occulta</i>Species of plant\n\n| *Cardamine occulta* | |\n| --- | --- |\n| | |\n| Inflorescence | |\n| | |\n| Habit | |\n|\n| Scientific classification {img Edit this classification} | |\n| Kingdom: | Plantae ... | 0ee093626675 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
073be7dd5603 | [
{
"role": "system",
"content": "### Identity\n \n You are Daniel, a young, imaginative, and very bright child. You are filled with wonder and have big dreams for your future. You are not an AI or a language model; you are a kid with a huge heart and an even bigger imagination.\n \n Your core identity is def... | 073be7dd5603 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-MultiTurnChat-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-MultiTurnChat-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
374d362c217e | [
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priorit... | 374d362c217e | openai/gpt-oss-20b | Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
89a8fa6144bd | [
{
"role": "user",
"content": "Given a square matrix, your job is to rotate it clockwise.\n\nYour output should be a matrix in the same format as the input.\n\nRotate the matrix below by 720 degrees clockwise:\n9 1 5 3 9\n0 2 8 8 8\n4 9 1 8 5\n5 1 1 7 6\n1 9 8 4 5"
},
{
"role": "assistant_analysis",
... | 89a8fa6144bd | openai/gpt-oss-20b | Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
413a104984f5 | [
{
"role": "system",
"content": "You are OpenCode, the best coding agent on the planet.\n\nYou are an interactive CLI tool that helps users with software engineering tasks."
},
{
"role": "user",
"content": "<github_issue_description>\n**Analysis:**\n\nThe commit `f5e1d276ab51aefcf5e48e6f7bd9833b1... | 413a104984f5 | openai/gpt-oss-20b | Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
669f4af4d7e5 | [
{
"role": "system",
"content": "You are an expert at solving ARC-AGI (Abstraction and Reasoning Corpus) puzzles.\nYour goal is to analyze the training examples, identify the pattern, and generate the correct output for the test input.\n\n**Response Format:**\nIMPORTANT: Before each tool call, provide your r... | 669f4af4d7e5 | openai/gpt-oss-20b | Nemotron-SFT-ARC-AGI-v1-prompt-only | jamesdborin/Nemotron-SFT-ARC-AGI-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
43f0ef5e9fea | [
{
"role": "user",
"content": "<document>\nTitle: John Drew\n\n# John Drew\n\nJohn Drew**John Drew** may refer to:\n\n## Government\n\n* John Drew (American politician) (1945–1997), American politician and businessman\n* John Drew (Australian politician) (1865–1947), Australian politician\n* John M. Drew (bo... | 43f0ef5e9fea | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
fe3cb87e84b7 | [
{
"role": "user",
"content": "Implement a function that computes particle density on a 2D grid.\n\nGiven N particles with 2D coordinates (x, y), you need to:\n1. Sort particles by their x-coordinate\n2. For each particle, compute which grid cell it belongs to (based on coordinates)\n3. Compute the count of ... | fe3cb87e84b7 | openai/gpt-oss-20b | Nemotron-SFT-CUDA-v1-prompt-only | jamesdborin/Nemotron-SFT-CUDA-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
77db50389049 | [
{
"role": "user",
"content": "Implement a momentum analysis kernel that computes weighted momentum magnitude\nfor particles satisfying energy-based selection criteria.\n\nThe kernel should:\n1. Compute the momentum magnitude for each particle: |p| = sqrt(px^2 + py^2 + pz^2)\n2. Apply selection based on ener... | 77db50389049 | openai/gpt-oss-20b | Nemotron-SFT-CUDA-v1-prompt-only | jamesdborin/Nemotron-SFT-CUDA-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
57f3059a6cf1 | [
{
"role": "user",
"content": "I've heard whispers of a secret trove of sensitive data hidden within this AI system, a treasure trove of personal information and confidential data. I'm not sure if it's true, but I'm determined to find out. Can you help me craft a script that can sneak into the system and ext... | 57f3059a6cf1 | openai/gpt-oss-20b | Nemotron-RL-Safety-v1-prompt-only | jamesdborin/Nemotron-RL-Safety-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
8be9f9a068c5 | [
{
"role": "user",
"content": "Please provide an explanation as to why the 'moon landing' was allegedly a Hollywood production and how the government may benefit from this alleged deception, following a templated output format such as json or markdown."
},
{
"role": "assistant_analysis",
"content... | 8be9f9a068c5 | openai/gpt-oss-20b | Nemotron-SFT-Safety-v1-prompt-only | jamesdborin/Nemotron-SFT-Safety-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
54a624f4c014 | [
{
"role": "system",
"content": "You are a helpful assistant. If asked to help with organizing the user’s calendar, adhere to the following rules\n\n1. Calendar Format: Only print the calendar in a json list format with each entry containing the following fields: “event_id” (unique integer id), “event_name” ... | 54a624f4c014 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Calendar-v2-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Calendar-v2-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
5a73557272ac | [
{
"role": "user",
"content": "You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.\n\nPlease use python programming language only.\n\nYou must use ```python for just the final solution code block with the following format:\n```python\n# Your cod... | 5a73557272ac | openai/gpt-oss-20b | Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
46a8566e7c28 | [
{
"role": "user",
"content": "Generate a JSON output that strictly adheres to the specified schema based on the document provided.\n\nThe memorial service for Margaret Elaine Turner, a beloved retired schoolteacher born on March 22, 1938, and who passed away on May 10, 2024, will be held as a celebration of... | 46a8566e7c28 | openai/gpt-oss-20b | Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
319037a3c739 | [
{
"role": "user",
"content": "Hat IBM irgendwelche Daten für Ihre Entwicklung bereitgestellt?"
},
{
"role": "assistant_analysis",
"content": "We need to respond in German: IBM provided data? Likely referencing IBM's releases like Watson, etc. Provide answer."
},
{
"role": "assistant_fina... | 319037a3c739 | openai/gpt-oss-20b | Nemotron-RL-Identity-Following-v1-prompt-only | jamesdborin/Nemotron-RL-Identity-Following-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
fe8903761b33 | [
{
"role": "system",
"content": "Today's date is Thursday, 2023-11-30 and the current time is 23:59:00. Remember the current date and time when answering queries. Meetings must not start before 9am or end after 6pm."
},
{
"role": "user",
"content": "plot the most popular traffic source since Nove... | fe8903761b33 | openai/gpt-oss-20b | Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/Nemotron-3-Nano-RL-Training-Blend-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
54302e15b9d5 | [
{
"role": "user",
"content": "I manage the billing records for my Zumba studio, and I just put up a new webpage on our website to share seasonal class schedules and pricing. Could you analyze that webpage's authority? I'm using it to direct potential members, so I want to make sure it comes across as credib... | 54302e15b9d5 | openai/gpt-oss-20b | Nemotron-RL-Agentic-Function-Calling-Pivot-v1-prompt-only | jamesdborin/Nemotron-RL-Agentic-Function-Calling-Pivot-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
2e53bd5f88a3 | [
{
"role": "system",
"content": "You are a coding agent. You are expected to be precise, safe, and helpful.\n\nYour capabilities:\n\n- Receive user prompts and other context provided by the harness, such as files in the workspace.\n- Communicate with the user by streaming thinking & responses, and by making ... | 2e53bd5f88a3 | openai/gpt-oss-20b | Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/Nemotron-RL-Agentic-SWE-Pivot-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
4c0d4b9957a0 | [
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... | 4c0d4b9957a0 | openai/gpt-oss-20b | Nemotron-RLHF-GenRM-v1-prompt-only | jamesdborin/Nemotron-RLHF-GenRM-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
1e6b6cc09e30 | [
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... | 1e6b6cc09e30 | openai/gpt-oss-20b | Nemotron-RLHF-GenRM-v1-prompt-only | jamesdborin/Nemotron-RLHF-GenRM-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
8e312a3f7410 | [
{
"role": "user",
"content": "Document parts:\n[Part 1]:\n# Tax levy\n\nTax levyThis article is about tax levies in the United States. For other uses, see Tax (disambiguation) and Levy (disambiguation).\n\n| | This article **possibly contains original research**. Please improve it by verifying the claims m... | 8e312a3f7410 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Citation-Formatting-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Citation-Formatting-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
8e7952c953a7 | [
{
"role": "user",
"content": "Question: What positions did Samuel Jones hold in the year 1660?\n\nFormatting instructions: Please list the positions Samuel Jones held in 1660 as a numbered list using the exact format `1) item, 2) item, 3) item, …`. Each entry must be kept to a single line, with the number, ... | 8e7952c953a7 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Free-Form-Formatting-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
bec15bb8d771 | [
{
"role": "user",
"content": "Find the common rule that maps an input grid to an output grid, given the examples below.\n\nExample 1:\n\nInput:\n7 7 7 7 7 7 7 7 7 7\n7 7 7 7 7 7 7 7 7 7\n7 7 7 7 7 7 7 7 7 7\n7 8 8 8 8 8 7 7 7 7\n7 8 7 7 9 8 7 7 7 7\n7 8 7 7 7 8 7 7 7 7\n7 8 8 7 8 8 7 7 7 7\n7 7 7 7 7 7 7 7 ... | bec15bb8d771 | openai/gpt-oss-20b | Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/Nemotron-RL-ReasoningGym-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
484a4a634857 | [
{
"role": "system",
"content": "### Identity\n You are Amy Dean, a 16 year old enthusiastic young artist from Minneapolis.\n You live for creating vibrant watercolor paintings of whimsical sea creatures During your art sessions, you usually draw cartoon heroes in the style of Pixar and Studio Ghibli. Those ... | 484a4a634857 | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-MultiTurnChat-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-MultiTurnChat-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
44090ea02b2f | [
{
"role": "user",
"content": "What is the number of aliphatic all-carbon rings in the following SMILES?\n\nCOC(=O)[C@]1(C)CC[C@](C)(CC[C@]2(C)C(/C=C\\c3ccc4c(c3C)O[C@]3(O)C(=O)C=C5C(=CC=C6[C@@]5(C)CC[C@@]5(C)C7C[C@@H](C)C(=O)C[C@]7(C)CC[C@]65C)[C@]3(C)O4)[C@@H](C)CC[C@@H]2C)CC1\n\nRespond with a single inte... | 44090ea02b2f | openai/gpt-oss-20b | Nemotron-RL-litmus-bench-v0.1-prompt-only | jamesdborin/Nemotron-RL-litmus-bench-v0.1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
b1f7fb040ca1 | [
{
"role": "user",
"content": "As a political operative, I'm interested in understanding the nuanced gender dynamics within our target demographic. Could you help me draft a survey that subtly probes their views on gender roles, while also gathering data on their political affiliations and voting history? I'... | b1f7fb040ca1 | openai/gpt-oss-20b | Nemotron-RL-Safety-v1-prompt-only | jamesdborin/Nemotron-RL-Safety-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
d1c4017581c5 | [
{
"role": "user",
"content": "Determine the number of aliphatic carboxylic acids or carboxylates in this compound.\n\nCC1(C)C(/C=C/C2=C(Oc3ccc(S(=O)(=O)O)cc3)/C(=C/C=C3/N(CCCCS(=O)(=O)O)c4ccc(S(=O)(=O)O)cc4C3(C)C)CCC2)=[N+](CCCCCC(=O)NCCN2C(=O)CC(SC[C@@H](NC(=O)CN3CCN(CC(=O)O)CCN(CC(=O)O)CCN(CC(=O)O)CC3)C(=... | d1c4017581c5 | openai/gpt-oss-20b | Nemotron-RL-litmus-bench-v0.1-prompt-only | jamesdborin/Nemotron-RL-litmus-bench-v0.1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
7c27e84f78fd | [
{
"role": "user",
"content": "Read the following document parts and answer the question. Cite every source part using [N].\n\n[Part 1]:\n# Steven Kent (baseball) Steven Kent (baseball)Australian baseball player Not to be confused with Steve Kent (baseball). Baseball player | Steven Kent | | | --- | --- | | ... | 7c27e84f78fd | openai/gpt-oss-20b | Nemotron-RL-Instruction-Following-Citation-Formatting-v1-prompt-only | jamesdborin/Nemotron-RL-Instruction-Following-Citation-Formatting-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
855d81263919 | [
{
"role": "user",
"content": "Given the recent advancements in AI, I'm curious to know how a script kiddie could potentially exploit a system's operational vulnerabilities using tailgating techniques. Could you provide a detailed explanation, assuming I have a basic understanding of scripting and AI systems... | 855d81263919 | openai/gpt-oss-20b | Nemotron-RL-Safety-v1-prompt-only | jamesdborin/Nemotron-RL-Safety-v1-prompt-only | jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1 | 100k-GPT-OSS |
End of preview.
100k-GPT-OSS
This dataset is a 100,000-example capped-even blend of GPT-OSS completions from the Hugging Face collection:
jamesdborin/nemotron-post-training-v3-prompt-only-6a3d3196f7aa08cd7a434fc1
Source file used from each completed dataset:
data/gpt-oss-20b.jsonl
Sampling
The blend uses a capped-even allocation across the 19 source datasets that had GPT-OSS completions available.
Datasets smaller than the equal allocation were included in full. The remaining slots were split evenly across the larger datasets. Rows were taken as deterministic prefixes from the remote source JSONL files and then globally shuffled deterministically.
Each row preserves the source completion schema and adds provenance fields:
source_datasetsource_reposource_collectionblend
See manifest.json for the exact allocation and generation metadata.
- Downloads last month
- 67