text large_stringlengths 275 60k | domain large_stringclasses 6
values | source_name large_stringclasses 11
values | quality_score int64 3 14 | is_fable5 bool 2
classes |
|---|---|---|---|---|
<|system|>
You are a helpful assistant that can interact multiple times with a computer shell to solve programming tasks.
Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).
Include a THOUGHT section before your command where you explain your reasoning process... | reasoning | thoughtworks/agentic-coding-trajectories | 9 | false |
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
Provide the best response to a given instruction. Follow the following steps to craft your response:
1. reason about the given instruction
2. provide a high-quality solution
3. offer a concise explanation
4. write tests to verify the corr... | coding | atlas | 10 | false |
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
Provide the best response to a given instruction. Follow the following steps to craft your response:
1. reason about the given instruction
2. provide a high-quality solution
3. offer a concise explanation
4. write tests to verify the corr... | coding | atlas | 10 | false |
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
Provide the best response to a given instruction. Follow the following steps to craft your response:
1. reason about the given instruction
2. provide a high-quality solution
3. offer a concise explanation
4. write tests to verify the corr... | frontend | atlas | 10 | false |
[TASK]
swesmith-26336_copy0000
[TRAJECTORY]
<|user|>
You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.
Format your response... | tools | openthoughts | 14 | false |
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
Provide the best response to a given instruction. Follow the following steps to craft your response:
1. reason about the given instruction
2. provide a high-quality solution
3. offer a concise explanation
4. write tests to verify the corr... | backend | atlas | 10 | false |
<|user|>
Explain how to debug a syntax error in a piece of complex Python code using nested variable assignments, logical conditionals and functions within a debug_syntax(‘input.py’) function while optimizing for runtime and memory efficiency.
<|assistant|>
1. Identify the line with the syntax error:
```python
def d... | agentic | fable | 10 | true |
<|im_start|>system
You are a helpful coding assistant.<|im_end|>
<|im_start|>user
Provide the best response to a given instruction. Follow the following steps to craft your response:
1. reason about the given instruction
2. provide a high-quality solution
3. offer a concise explanation
4. write tests to verify the corr... | backend | atlas | 10 | false |
[TASK]
swesmith-07325_copy0002
[TRAJECTORY]
<|user|>
You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.
Format your response... | reasoning | open-thoughts/OpenThoughts-Agent-SFT-100K | 9 | false |
[TASK]
superuser-012522_copy0004
[TRAJECTORY]
<|user|>
You are an AI assistant tasked with solving command-line tasks in a Linux environment. You will be given a task description and the output from previously executed commands. Your goal is to solve the task by providing batches of shell commands.
Format your respon... | tools | openthoughts | 14 | false |
End of preview. Expand in Data Studio
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
fable5-traces-agentic
100K-max multi-domain coding + agentic SFT dataset.
Final rows
100,000
Targets
{ "agentic": 40000, "coding": 20000, "frontend": 11000, "backend": 9000, "reasoning": 15000, "tools": 5000 }
Actual
{ "reasoning": 10321, "frontend": 5384, "tools": 5000, "agentic": 50295, "coding": 20000, "backend": 9000 }
FABLE.5
Selected: 45,625 Target: 30,000 Minimum: 25,000
Build
- Scratch build, 7 primary sources
- Parallel streaming source ingestion (4 workers)
- Per-source Parquet cache
- Native Polars classification
- Global deduplication (blake2b-stable hashing)
- FABLE.5 priority
- Lazy same-pool fallback
- Flexible quotas, maximum 100,000 rows
Sources
{ "fable": 45625, "atlas": 34297, "open-thoughts/OpenThoughts-Agent-SFT-100K": 5652, "openthoughts": 4726, "thoughtworks/agentic-coding-trajectories": 4669, "thoughtworks": 4669, "agentsft": 213, "AdhyanshVerma/html-css-js-cot": 98, "htmlcot": 36, "stindardlogic/code-generation-sft-100k": 11, "codegen": 4 }
Fallbacks
[ "AdhyanshVerma/html-css-js-cot", "stindardlogic/code-generation-sft-100k", "open-thoughts/OpenThoughts-Agent-SFT-100K", "thoughtworks/agentic-coding-trajectories" ]
- Downloads last month
- 81