Models

mlfoundations-dev_stackoverflow_375000_samples

0128teacher_checkpoint_0

0128student_checkpoint_0

llama-SFT-base_merged_fp16_D90053_copy_32GB

llama-3.1-8b-reasoning

sn29_s1m2_dfpb

sn29_x1m6_etuc

sn29_q1m3_d7a3

sn29_x1m4_ghvn

lora_9feb_llama8b_deepseek_backdoor

llama3-alpaca-tuned-and-merged

Bespoke-Stratos-17k-v3

math-stratos-verified-scaled-0.25

Bespoke-Stratos-17k

Bespoke-Stratos-17k-v2

Bespoke-Stratos-17k-v4

qwen_7b_instruct_extra_verified

qwen_7b_instruct_extra_unverified

stratos_new_verified_mix_sharegptformat_4nodes

bgGPT-DeepSeek-R1-Distill-Qwen-7B

stratos-unverified-mix-scaled-0.125

math-stratos-unverified-scaled-0.25

mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-0_125_stratos_7b

mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-0_25_stratos_7b

mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-0_5_stratos_7b

mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-1_stratos_7b

mlfoundations-dev_code-stratos-verified-scaled-0_25_stratos_7b

llama3-1_8b_r1_annotated_math

llama3-1_8b_r1_annotated_olympiads

math-stratos-unverified-scaled-1

llama3-1_8b_distill_70b_infra_baseline_r1_2.5k

mlfoundations-dev_stratos-verified-mix-scaled-0_5_stratos_7b

llama3-1_8b_multiple_samples_random_numina_aime

mlfoundations-dev_stratos-unverified-mix-scaled-0_5_stratos_7b

32k_test_dummy

seed_math_math_instruct_reasoninghp

dpo_from_multiple_samples_shortest_numina_aime

verified_stratos_mix_no_proofs_without_metadata

s1K_reformat_v2

difficulty_sorting_medium_seed_math

difficulty_sorting_random_seed_math

multiple_samples_none_numina_aime_adjusted_samples