*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text tokenizer.json filter=lfs diff=lfs merge=lfs -text 250k/tokenizer.json filter=lfs diff=lfs merge=lfs -text figures/sft-models.png filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/arc_challenge_25shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_arc_challenge_2025-07-17T19-57-20.454173.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/gsm8k_5shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_gsm8k_2025-07-17T20-44-20.876997.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/gsm8k_reasoning_base_0shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000__/samples_gsm8k_reasoning_base_2025-11-26T00-59-11.177986.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/hellaswag_10shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_hellaswag_2025-07-17T23-58-29.900269.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/humaneval_64_0shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_humaneval_64_2025-08-22T03-51-05.521361.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/humaneval_64_0shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000__/samples_humaneval_64_2025-11-25T01-35-23.860829.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/minerva_math500_0shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_minerva_math500_2025-11-28T05-06-05.219253.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/mmlu_5shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_mmlu_professional_law_2025-07-18T00-49-44.450953.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/eval_results/mmlu_pro_5shots/__lustrefs__users__runner__checkpoints__huggingface__vocab_trimmed__iter_1249000/samples_mmlu_pro_law_2025-07-17T21-35-56.511842.jsonl filter=lfs diff=lfs merge=lfs -text iter_1249000/tokenizer.json filter=lfs diff=lfs merge=lfs -text eval_results/arc_challenge_25shots/__lustrefs__users__runner__checkpoints__huggingface__iter_0020000/samples_arc_challenge_2025-04-03T06-47-04.096521.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/gsm8k_5shots/__lustrefs__users__runner__checkpoints__huggingface__iter_0020000/samples_gsm8k_2025-04-03T07-37-25.395166.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/hellaswag_10shots/__lustrefs__users__runner__checkpoints__huggingface__iter_0020000/samples_hellaswag_2025-04-03T10-46-52.083797.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/mmlu_5shots/__lustrefs__users__runner__checkpoints__huggingface__iter_0020000/samples_mmlu_professional_law_2025-04-03T11-38-41.517466.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/mmlu_pro_5shots/__lustrefs__users__runner__checkpoints__huggingface__iter_0020000/samples_mmlu_pro_law_2025-04-09T05-02-59.883377.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/arc_challenge_25shots/__lustrefs__users__runner__workspace__checkpoints__huggingface__k2plus_stage1_attn8k_jais250k_tp8__checkpoints__checkpoint_0065000/samples_arc_challenge_2025-08-05T08-05-55.784564.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/gsm8k_5shots/__lustrefs__users__runner__workspace__checkpoints__huggingface__k2plus_stage1_attn8k_jais250k_tp8__checkpoints__checkpoint_0065000/samples_gsm8k_2025-08-05T08-57-10.856012.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/hellaswag_10shots/__lustrefs__users__runner__workspace__checkpoints__huggingface__k2plus_stage1_attn8k_jais250k_tp8__checkpoints__checkpoint_0065000/samples_hellaswag_2025-08-05T12-06-56.401273.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/mmlu_5shots/__lustrefs__users__runner__workspace__checkpoints__huggingface__k2plus_stage1_attn8k_jais250k_tp8__checkpoints__checkpoint_0065000/samples_mmlu_professional_law_2025-08-05T12-43-23.697649.jsonl filter=lfs diff=lfs merge=lfs -text eval_results/mmlu_pro_5shots/__lustrefs__users__runner__workspace__checkpoints__huggingface__k2plus_stage1_attn8k_jais250k_tp8__checkpoints__checkpoint_0065000/samples_mmlu_pro_law_2025-08-05T09-47-13.715353.jsonl filter=lfs diff=lfs merge=lfs -text