messages listlengths 2 609 | meta unknown | meta_extra unknown | id stringlengths 16 29 | tags listlengths 3 13 | approx_tokens int64 13 961k | gpt2_tokens int64 14 3.2M | tools listlengths 1 8.51k ⌀ | images listlengths 1 1 ⌀ |
|---|---|---|---|---|---|---|---|---|
[
{
"role": "user",
"content": "Solve the following problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\nIn Horeau's method, a racemic sample of chiral secondary alcohol A is esterified with enantiomerically pure (R)-2-phenylbutanoic acid. After partial reaction, the unreacted alcohol i... | {
"source": "opensci",
"turns": 2,
"domain": "reasoning_science",
"task": "science",
"license": "cc-by-4.0"
} | {
"cot": "inline"
} | ens_0d27f82a9307 | [
"domain:reasoning_science",
"turns:mono",
"tok:5k-20k",
"cot"
] | 13,042 | 17,553 | null | null |
[
{
"role": "user",
"trainable": false,
"content": "Here is x86-64 disassembly (objdump -d -M intel, no raw bytes) of a function compiled with GCC -O2 from a stripped binary. Reconstruct readable, compilable C that preserves the exact behavior. Explain the key control-flow decisions as you go.\n\n```asm\n... | {
"source": "re_synth_forge",
"domain": "reverse_engineering",
"license": "cc-by-4.0",
"task": "fixedpoint+parseip+vm",
"turns": 6
} | null | ens_4f0f2a73f5a7 | [
"turns:mid",
"tok:1k-5k",
"src:re_synth_forge",
"domain:reverse_engineering"
] | 1,111 | 2,459 | null | null |
[
{
"role": "user",
"content": "Find the closed form of the sum $\\left\\lceil \\sqrt{1} \\right\\rceil + \\left\\lceil \\sqrt{2} \\right\\rceil + \\cdots + \\left\\lceil \\sqrt{n} \\right\\rceil$.",
"trainable": false
},
{
"role": "assistant",
"content": "<think>\nOkay, so I need to find a cl... | {
"source": "openmath_cot",
"domain": "reasoning_math",
"license": "cc-by-4.0",
"task": "aops_c6_high_school_olympiads",
"turns": 2
} | null | ens_84c16f63d49e | [
"turns:short",
"tok:5k-20k",
"cot",
"src:openmath_cot",
"domain:reasoning_math"
] | 6,208 | 11,060 | null | null |
[
{
"role": "system",
"content": "<instructions>\nYou are a customer service agent that helps the user according to the <policy> provided below.\n\nCRITICAL RULES (you MUST follow these):\n1. In each turn, you can ONLY do ONE of these:\n - Send a message to the user, OR\n - Make exactly ONE tool call\n2. ... | {
"source": "ultradata_tooluse",
"turns": 22,
"economy": {
"tokens": 5667,
"calls": 8,
"waste_tokens": 0
},
"domain": "agentic_tool",
"task": "tooluse",
"license": "apache-2.0"
} | null | ens_4b0bae6e23ce | [
"domain:agentic_tool",
"turns:deep",
"tok:5k-20k",
"tools",
"toolcalls:4-10"
] | 5,674 | 6,692 | [
{
"type": "function",
"function": {
"name": "book_reservation",
"description": "Book a reservation.",
"parameters": {
"$defs": {
"FlightInfo": {
"properties": {
"flight_number": {
"description": "Flight number, such as 'HAT001'.",... | null |
[{"role":"system","content":"You are Codex, based on GPT-5. You are running as a coding agent in the(...TRUNCATED) | {"source":"ultradata_code","domain":"code_agent","license":"apache-2.0","task":"Code_Agent_001478","(...TRUNCATED) | null | ens_6d380743aebc | ["turns:mega","tok:20k-50k","tools","toolcalls:10+","tools","src:ultradata_code","domain:code_agent"(...TRUNCATED) | 45,457 | 76,107 | null | null |
[{"role":"user","content":"Write matplotlib code that builds exactly the chart described. Use the py(...TRUNCATED) | {
"source": "plot_forge",
"domain": "vision_plot",
"license": "cc-by-4.0",
"turns": 2
} | null | ens_970da41a480e | [
"turns:short",
"tok:1k",
"src:plot_forge",
"domain:vision_plot"
] | 185 | 263 | null | null |
[{"role":"user","content":"CadQuery task: a rectangular base plate 190 x 80 x 18 mm. Centered on the(...TRUNCATED) | {"source":"cad_evo_forge","domain":"cad_3d","license":"cc-by-4.0","task":"box_holes_cbore_pocket_bos(...TRUNCATED) | null | ens_4088ed26811e | [
"turns:deep",
"tok:1k-5k",
"src:cad_evo_forge",
"domain:cad_3d"
] | 2,105 | 3,552 | null | null |
[{"role":"user","content":"Please provide a recipe for making smoked salmon using a traditional smok(...TRUNCATED) | {
"source": "ultrachat",
"domain": "general_sft",
"license": "mit",
"turns": 4
} | null | ens_8bdc33f97026 | [
"turns:short",
"tok:1k",
"src:ultrachat",
"domain:general_sft"
] | 992 | 891 | null | null |
[{"role":"user","content":"Write a Blender 4.x Python script (bpy) for the task below. The script mu(...TRUNCATED) | {"source":"blender_forge","domain":"blender_3d","license":"cc-by-4.0","task":"bevel_showcase","turns(...TRUNCATED) | null | ens_348f82b2daf0 | [
"turns:short",
"tok:1k",
"src:blender_forge",
"domain:blender_3d"
] | 243 | 309 | null | null |
[{"role":"user","content":"In Godot 4.x, how does StreamPeer work?","trainable":false},{"role":"assi(...TRUNCATED) | {"source":"godot_docs_real","domain":"godot_dev","license":"cc-by-3.0","task":"docs_class_streampeer(...TRUNCATED) | null | ens_b050cf4861d1 | [
"turns:short",
"tok:1k",
"src:godot_docs_real",
"domain:godot_dev"
] | 74 | 94 | null | null |
YAML Metadata Warning:The task_categories "text2text-generation" 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
sft-forge-ensemble v2.0
One pareto-pruned, token-rebalanced SFT mixture built by sft-forge. 321,777 rows · 2,123,529,634 real gpt2 tokens · fine-grained tags on every row.
Token mix by domain (real gpt2, kept rows)
| domain | gpt2 tokens | share |
|---|---|---|
| reasoning_math | 551,186,692 | 26.0% |
| reasoning_sci | 370,397,475 | 17.4% |
| agentic_swe | 304,253,237 | 14.3% |
| code_agent | 233,702,388 | 11.0% |
| agentic_tool | 219,243,982 | 10.3% |
| general_sft | 213,467,470 | 10.1% |
| reverse_engineering | 147,388,757 | 6.9% |
| vision_svg | 67,429,930 | 3.2% |
| cad_3d | 9,174,147 | 0.4% |
| vision_plot | 4,315,416 | 0.2% |
| blender_3d | 1,220,418 | 0.1% |
| godot_dev | 929,412 | 0.0% |
| vision_image | 820,310 | 0.0% |
Sources
| source | rows | gpt2 tokens |
|---|---|---|
| openmath_cot | 66787 | 535,300,110 |
| opensci | 65779 | 389,184,121 |
| openmath_tir | 136459 | 1,190,615,653 |
| openr1_math | 38000 | 224,337,795 |
| nemotron_sci | 35000 | 52,208,521 |
| ultrachat | 62485 | 75,454,571 |
| svg_code | 14317 | 7,279,031 |
| mcp_atlas | 462 | 7,583,866 |
| pyromind_long | 1000 | 58,991,782 |
| pyromind_short | 1932 | 14,639,677 |
| toolmind | 13351 | 171,755,540 |
| ultradata_tooluse | 2095 | 13,520,358 |
| nemotron_swe | 4702 | 271,084,502 |
| swesmith | 5174 | 164,528,053 |
| coderforge | 2184 | 199,432,411 |
| nemotron_cuda | 2276 | 23,010,820 |
| ultradata_code | 4200 | 276,443,679 |
| agenticsft | 500 | 8,115,596 |
| demyagent | 500 | 1,179,050 |
| ultradata_general | 2692 | 69,243,262 |
| ultradata_search | 2576 | 76,121,807 |
| ollvm_re | 704 | 115,095,930 |
| cadforge_3d | 14 | 35,785 |
| cadforge_cq | 3 | 9,347 |
| multiturn | 192 | 194,013 |
| unified | 758 | 148,433 |
| vision_docmatix | 1617 | 225,903 |
| vision_forge | 1232 | 68,406 |
| plot2code | 379 | 212,787 |
| sophia_svg | 23863 | 57,107,843 |
| icons_forge | 8490 | 3,043,056 |
| re_synth_forge | 6059 | 17,042,338 |
| cad_synth_forge | 4878 | 1,092,433 |
| cad_evo_forge | 11760 | 19,589,906 |
| longctx_forge | 30 | 49,735,767 |
| blender_forge | 3975 | 1,220,418 |
| godot_forge | 87 | 25,810 |
| plot_forge | 8021 | 3,914,630 |
| godot_demos_real | 248 | 221,945 |
| godot_docs_real | 2429 | 681,657 |
| mpl_gallery_real | 184 | 187,999 |
| vision_forge2 | 7997 | 526,001 |
| cq_examples_real | 28 | 17,503 |
Pipeline
carry vetted v1.1 shards -> top-up fetch (rows+parquet bulk, offset-cursor resume) -> per-row gates (shape, non_latin, think-balance, dup, license, no_image) -> ONE global dedup index seeded with the carried corpus -> real gpt2 BPE per row -> per-slice pareto (strict) -> domain token-share caps -> deterministic interleave.
Quota drops (rebalance)
| family | rows dropped | share before |
|---|---|---|
| reasoning_math | 173173 | 0.2632 |
| reasoning_sci | 16299 | 0.1769 |
| agentic_swe | 506 | 0.1453 |
| code_agent | 194 | 0.1114 |
| reverse_engineering | 2 | 0.0688 |
Generator diversity (per source, post-pareto)
| source | distinct tasks | top task | top share |
|---|---|---|---|
| openmath_cot | 6 | math | 55% |
| opensci | 2 | science | 57% |
| openmath_tir | 4 | aops_c6_high_school_olympiads | 54% |
| openr1_math | 7 | olympiads | 73% |
| pyromind_short | 2 | tooluse | 57% |
| toolmind | 2 | tooluse | 54% |
| nemotron_swe | 2310 | swe | 8% |
| swesmith | 1685 | swe | 42% |
| coderforge | 801 | swe | 29% |
| ultradata_code | 3001 | coding | 3% |
| ultradata_general | 2001 | general | 8% |
| ultradata_search | 2001 | search | 0% |
| ollvm_re | 2 | re | 100% |
| vision_docmatix | 2 | vision | 88% |
| plot2code | 2 | vision | 97% |
| icons_forge | 9 | tabler-outline | 39% |
| re_synth_forge | 2937 | rle | 2% |
| cad_synth_forge | 23 | plate_holes | 12% |
| cad_evo_forge | 1258 | box_stack_pocket_boss | 12% |
| longctx_forge | 6 | utility library header rebuild | 37% |
| blender_forge | 47 | camera_rig | 34% |
| godot_forge | 20 | tween_motion | 20% |
| godot_demos_real | 99 | demo_2d_physics_tests | 10% |
| godot_docs_real | 1247 | docs_class_openxrspatialcompo | 1% |
| mpl_gallery_real | 24 | gallery_linebar | 17% |
| vision_forge2 | 6 | vf2_scatter_quads | 17% |
Single-artifact families carry a concision envelope: at equal correctness the pareto prune now drops bloated rows first, so the mixture teaches tight, dense answers rather than padded ones.
Files
train.jsonl.gz— the mixture (interleaved; shuffle again before packing)manifest.jsonl.gz— per-row index: id, source, domain, turns, gpt2_tokens, tagsbuild/v2.0/shards/*.jsonl.gz— per-source provenance poolsimages.tar.gz— PNGs referenced byvision_image/vision_plotrows (meta.images)
Tag vocabulary (filter, never re-split)
src:<source> · domain:<fine> (agentic_general, agentic_search, agentic_swe, agentic_tool, blender_3d, cad_3d, code_agent, general_sft, godot_dev, reasoning_math, reasoning_sci, reasoning_science, reverse_eng, reverse_engineering, style_house, vision_image, vision_plot, vision_svg)
· turns:<mono|short|mid|deep|mega> · tok:<1k|1k-5k|5k-20k|20k-50k|50k+>
· tools + toolcalls:<1-3|4-10|10+> · cot · multimodal · verified
Honest notes
- Carried rows keep their v1.0/v1.1 vetting;
meta.licenseis per-row. - Carry-only sources: agenticsft/demyagent (upstream license unverified), cadforge_3d (upstream dark since v1.0 — the 14 verified rows are all that exist).
- Vision rows' text token share is small by nature: the pixels live in
images.tar.gz, outside any text token count. Every forge-rendered vision answer is program-verified upstream. - Assistant turns carry
trainable: true— mask non-assistant turns for loss.
- Downloads last month
- 1,127