{"_id":"6aa3d2944ceb3bf7b4744264","id":"yqi0/petitgpt","private":false,"pipeline_tag":"text-generation","tags":["safetensors","petitgpt","native-pytorch","from-scratch","small-language-model","pretraining","sft","model-interpolation","gqa","single-gpu","research","text-generation","en","dataset:HuggingFaceTB/smollm-corpus","dataset:HuggingFaceTB/dclm-edu","dataset:HuggingFaceFW/finewiki","dataset:HuggingFaceFW/finephrase","dataset:allenai/dolmino-mix-1124","dataset:common-pile/stackv2_edu_filtered","dataset:HuggingFaceTB/smol-smoltalk","license:apache-2.0","model-index","region:us"],"downloads":1573,"likes":27,"modelId":"yqi0/petitgpt","author":"yqi0","sha":"7ae08edab72fd4a43c110b6c87c73671dac80f29","lastModified":"2026-09-15T22:44:43.000Z","gated":false,"disabled":false,"widgetData":[{"text":"Hi, what can you help me with?"},{"text":"What is 84 * 3 / 2?"},{"text":"Tell me an interesting fact about the universe!"},{"text":"Explain quantum computing in simple terms."}],"model-index":[{"name":"petitgpt-alpha075","results":[{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"allenai/ai2_arc","name":"ARC-Easy","config":"ARC-Easy","split":"test","revision":"210d026faf9955653af8916fad021475a3f00453"},"metrics":[{"type":"acc","value":57.74,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":52.36,"name":"normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"baber/piqa","name":"PIQA","split":"validation","revision":"142f6d7367fd9877f0fb3b5734ea6a545f54cdd1"},"metrics":[{"type":"acc","value":63.49,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":62.3,"name":"normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"allenai/ai2_arc","name":"ARC-Challenge","config":"ARC-Challenge","split":"test","revision":"210d026faf9955653af8916fad021475a3f00453"},"metrics":[{"type":"acc","value":28.16,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":32.68,"name":"project-protocol normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"Rowan/hellaswag","name":"HellaSwag","split":"validation","revision":"218ec52e09a7e7462a5400043bb9a69a41d06b76"},"metrics":[{"type":"acc","value":31.28,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":35.6,"name":"project-protocol normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"google/IFEval","name":"IFEval","split":"train","revision":"966cd89545d6b6acfd7638bc708b98261ca58e84"},"metrics":[{"type":"prompt_level_strict_acc","value":17.19,"name":"prompt-level strict accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"inst_level_strict_acc","value":28.54,"name":"instruction-level strict accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"prompt_level_loose_acc","value":17.74,"name":"prompt-level loose accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"inst_level_loose_acc","value":29.98,"name":"instruction-level loose accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false}],"source":{"name":"PetitGPT technical report (pinned IFEval strict/loose programmatic verifier; no LLM judge)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#84-ifeval-instruction-following"}}]}],"config":{},"cardData":{"license":"apache-2.0","language":["en"],"pipeline_tag":"text-generation","datasets":["HuggingFaceTB/smollm-corpus","HuggingFaceTB/dclm-edu","HuggingFaceFW/finewiki","HuggingFaceFW/finephrase","allenai/dolmino-mix-1124","common-pile/stackv2_edu_filtered","HuggingFaceTB/smol-smoltalk"],"tags":["petitgpt","native-pytorch","from-scratch","small-language-model","pretraining","sft","model-interpolation","gqa","single-gpu","research"],"model-index":[{"name":"petitgpt-alpha075","results":[{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"allenai/ai2_arc","name":"ARC-Easy","config":"ARC-Easy","split":"test","revision":"210d026faf9955653af8916fad021475a3f00453"},"metrics":[{"type":"acc","value":57.74,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":52.36,"name":"normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"baber/piqa","name":"PIQA","split":"validation","revision":"142f6d7367fd9877f0fb3b5734ea6a545f54cdd1"},"metrics":[{"type":"acc","value":63.49,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":62.3,"name":"normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"allenai/ai2_arc","name":"ARC-Challenge","config":"ARC-Challenge","split":"test","revision":"210d026faf9955653af8916fad021475a3f00453"},"metrics":[{"type":"acc","value":28.16,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":32.68,"name":"project-protocol normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"Rowan/hellaswag","name":"HellaSwag","split":"validation","revision":"218ec52e09a7e7462a5400043bb9a69a41d06b76"},"metrics":[{"type":"acc","value":31.28,"name":"accuracy (zero-shot likelihood, FP32)","verified":false},{"type":"acc_norm","value":35.6,"name":"project-protocol normalized accuracy (zero-shot likelihood, FP32)","verified":false}],"source":{"name":"PetitGPT technical report (native protocol-compatible evaluator; not an installed lm-evaluation-harness run)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#81-public-multiple-choice-likelihood-frozen-fp32"}},{"task":{"type":"text-generation","name":"Text Generation"},"dataset":{"type":"google/IFEval","name":"IFEval","split":"train","revision":"966cd89545d6b6acfd7638bc708b98261ca58e84"},"metrics":[{"type":"prompt_level_strict_acc","value":17.19,"name":"prompt-level strict accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"inst_level_strict_acc","value":28.54,"name":"instruction-level strict accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"prompt_level_loose_acc","value":17.74,"name":"prompt-level loose accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false},{"type":"inst_level_loose_acc","value":29.98,"name":"instruction-level loose accuracy (native chat template, greedy, max_new_tokens=1280)","verified":false}],"source":{"name":"PetitGPT technical report (pinned IFEval strict/loose programmatic verifier; no LLM judge)","url":"https://github.com/yangqi0/petitgpt/blob/53a5bb33052fa8092987eacc1047e040a7c5ce30/docs/petitgpt-v1/TECHNICAL_REPORT.md#84-ifeval-instruction-following"}}]}]},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"DOCUMENTATION_LICENSE.md"},{"rfilename":"LICENSE"},{"rfilename":"MODEL_PROVENANCE.json"},{"rfilename":"README.md"},{"rfilename":"RUN_GUIDE.md"},{"rfilename":"SHA256SUMS"},{"rfilename":"SOURCE_NOTICE.md"},{"rfilename":"THIRD_PARTY_NOTICES.md"},{"rfilename":"config.json"},{"rfilename":"inference.py"},{"rfilename":"model.safetensors"},{"rfilename":"requirements-inference-tested.txt"},{"rfilename":"special_tokens_map.json"},{"rfilename":"src/__init__.py"},{"rfilename":"src/accepted_generate.py"},{"rfilename":"src/chat_template.py"},{"rfilename":"src/model.py"},{"rfilename":"src/special_tokens.py"},{"rfilename":"tables/ASSISTANT_RESULTS_VERSIONED.csv"},{"rfilename":"tables/PRETRAIN_SOURCE_MIXTURE.csv"},{"rfilename":"tables/PUBLIC_BENCHMARK_RESULTS.csv"},{"rfilename":"tokenizer.json"}],"spaces":[],"createdAt":"2026-09-11T10:06:12.000Z","safetensors":{"parameters":{"F32":124635456},"total":124635456},"usedStorage":498562192}