Models

sft__ot30k_Qwen2.5-1.5B-SFT-Tulu3-decontaminated

nemotron-terminal-corpus-unified-31600__Qwen3-32B

llama-3-8b-base-new-dpo-harmless-4xh200-s_star1.0

Qwen3-4B-2507-sft-merged-thinking-final

diallm-llama-gspo-aus

Gemma-3-1B-pt-is-CPT-plus-IR-is-SmolTalk

Gemma-3-1B-pt-sv-CPT-sv-SmolTalk

zerorlvrif-qwen2.5-1.5b

g1_original_3160_8b

zerorlvrcode-qwen2.5-1.5b

rlvrmath-qwen2.5-1.5b

rlvrcode-qwen2.5-1.5b

nemotron-terminal-corpus-unified-316__Qwen3-32B

gemma-2b-it-steer-bear-numbers-ft

nemotron-terminal-corpus-unified-1000__Qwen3-32B

llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260421-213851

Qwen3-4B-dpo_gpt-oss-120b_8k_reasoning_ablation

Qwen3-0.6B-Base-CPT-Math

University_of_Abuja_AI

DeepSeek-R1-8B-Medical

DeepSeek-R1-Medical-o1-COT

qwen2-5_multiple_samples_ground_truth_openr1_llm_verifier_clean

DSR1-Qwen-32B-still

llama-3.1-70B-Instruct_playpen_SFT_DFINAL_0.6K-steps_merged_fp16

SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1

llama3.1-8b-instruct-step-dpo

llama_2_sky_safe_o1_llama_3_8B_default_1000_500_full

llama_2_cot_simplest_code_math_2_3_epoch_full

llama_2_sky_o1_4_full

llama_2_sky_safe_o1_4o_reflect_1000_1000_full

llama_2_llama_2_alpaca_4_full

b2_science_fasttext_pos_scp116k

Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps

glm46-stackexchange-tezos-maxeps-131k

exp_tas_parser_xml_traces

exp_tas_low_diversity_traces

exp_tas_min_p_0_1_traces

llama3-warm_up-dolly_new_1200_0113-42-202601130042

Llama-3.1-8B-Instruct_SFT_Chat-220kv00.05

exp_tas_max_tokens_1024_traces

exp_tas_summarize_threshold_2048_traces

Llama-3.1-8B-Instruct_SFT_sciencev00.05