Dataset Viewer
Auto-converted to Parquet Duplicate
id
stringlengths
19
26
messages
listlengths
2
226
source_dataset
stringclasses
3 values
source_split
stringclasses
1 value
source_id
stringlengths
8
86
source_name
stringclasses
19 values
selection_bucket
stringclasses
3 values
category
stringclasses
9 values
difficulty
stringclasses
5 values
quality
stringclasses
5 values
reward_model_score
float64
0.15
0.26
conversation_tokens
int64
137
6.2k
num_turns
int64
2
226
assistant_chars
int64
0
250k
reasoning_chars
int64
0
133k
selection_score
float64
0
14.3
dedup_fingerprint
stringlengths
40
40
stage1_openthoughts_000000
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
2,558
21,453
0
d4acda169b074cc477f0ce81fa9cb87df7370afe
stage1_openthoughts_000001
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
2,328
12,722
0
b5b777e1513427c448b63b08b9a9deb010d2e880
stage1_openthoughts_000002
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
3,020
38,791
0
868f5427a89227ae2dd1a872d487a6ee7f0c094c
stage1_openthoughts_000003
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
2,430
34,371
0
e5deda3334a0735c6a65724c970c7b085335e05e
stage1_openthoughts_000004
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
3,014
27,551
0
4378cfc129884049bf404e13ece9dea93453261a
stage1_openthoughts_000005
[ { "role": "system", "content": "Your role as an assistant involves thoroughly exploring questions through a systematic long thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflect...
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
1,851
6,280
0
bad23788f7e0b682f6100c21f15f8ec595d24e18
stage1_openthoughts_000006
[{"role":"system","content":"Your role as an assistant involves thoroughly exploring questions throu(...TRUNCATED)
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
2,186
15,405
0
d8e0c7204b5a9aa2c4ea6776198d8be912d87ddf
stage1_openthoughts_000007
[{"role":"system","content":"Your role as an assistant involves thoroughly exploring questions throu(...TRUNCATED)
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
3,919
70,064
0
ce93cd017a46dc1b9232a35055bfd4c551866c2b
stage1_openthoughts_000008
[{"role":"system","content":"Your role as an assistant involves thoroughly exploring questions throu(...TRUNCATED)
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
3,665
53,654
0
3950a753bdcb08e963c9ea2e2a486c2118cdb763
stage1_openthoughts_000009
[{"role":"system","content":"Your role as an assistant involves thoroughly exploring questions throu(...TRUNCATED)
open-thoughts/OpenThoughts-114k
train
null
default
openthoughts
null
null
null
null
null
2
3,702
31,543
0
bf783e0739b1e11268661a06e97cbc157bd5d172
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.

Qwen3.5 A2D Stage 1 SFT

Curated general supervised fine-tuning corpus for Qwen3.5 text-only A2D BD3LM experiments.

Files

  • train-*.parquet: canonical training split data (54 shard(s)).
  • stage1_sft_metadata.json: curation counts and source-level metadata.
  • metadata.json: duplicate of the stage metadata for quick inspection.

Loading

from datasets import load_dataset
dataset = load_dataset("parquet", data_files={"train": "train-*.parquet"})

Curation Details

Stage 1 SFT Dataset

Canonical artifact: /Users/shreyvishen/Projects/local_inference/auto-to-diff/datasets/stage1_sft.parquet Training export: /Users/shreyvishen/Projects/local_inference/auto-to-diff/datasets/stage1_sft_train.jsonl Metadata: /Users/shreyvishen/Projects/local_inference/auto-to-diff/datasets/stage1_sft_metadata.json

Stage 1 Filter Logic

  • Tulu-3 examples are scored for reasoning, coding, math, multi-turn structure, source affinity, and response length.
  • SmolTalk examples are scored for category balance, difficulty, quality, reward_model_score, conversation_tokens, and response length.
  • OpenThoughts examples are included in full after normalization into the shared messages schema.
  • Deduplication uses an exact normalized conversation fingerprint across all merged sources.
  • Parquet is the canonical artifact; JSONL is a derived training-ready export.

Schema

  • messages: list of {role, content, reasoning_content} structs compatible with Qwen chat templating.
  • source_dataset, source_split, source_id, source_name: provenance fields.
  • selection_bucket, category, difficulty, quality, reward_model_score, conversation_tokens: curation metadata.
  • num_turns, assistant_chars, reasoning_chars, selection_score, dedup_fingerprint: filtering and audit metadata.

Sources

  • allenai/tulu-3-sft-mixture
  • HuggingFaceTB/smoltalk (config: smol-magpie-ultra)
  • open-thoughts/OpenThoughts-114k
Downloads last month
32