Models

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg-32b-10pct__Qwen3-32B

Qwen2.5-1.5B-Instruct_gsm8k

Gemma-3-1B-it-is-SmolTalk

llama-3-8b-base-margin-dpo-hh-helpful-batch-64

gemma-upd

nemosci-tasrep-a1mfc-dev1-maxeps-32b__Qwen3-32B

nemosci-tasrep-a1mfc-dev1-maxeps-swes-r2eg-32b__Qwen3-32B

P2-split2_prob_rg_v2_Qwen3-4B-Base-0415

nemotron-terminal-corpus-unified-10000__Qwen3-32B

web-qwen-coder-14b-3epochs-25k-5e-5

CALYREX-LoRA-Baseline

IPA_Gemma_1B_merged

nemotron-terminal-debugging__Qwen3-8B

llama31-8b-grpo-gsm8k-run1

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg-32b-3pct__Qwen3-32B

Llama-3.1-8B-LoRA-TENSORTRUST-LATE8TH

nemosci-tasrep-a1mfc-gfistaqc-scaff-maxeps-swes-r2eg-32b__Qwen3-32B

llama-3-8b-base-new-dpo-hh-helpful-s_star0.6-4xh200-batch-64-20260421-214335-rerun

llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun

sft_caption_generation_20260222_ep3_lr3e5_qwen3-vl-8b_cam_ready

qwen3vl_think_math_10k

32b_add_verified_extra_unverified

DCFT-Stratos-Verified-114k-Llama-3_3-70B-bs-256

DSR1-Qwen-32B-131fad2c

llama_openthoughts_sorted_sft_nopack_splpad

llama_2_sky_safe_o1_4o_default_1000_500_full

llama_2_rlhf_safe_4o_reflect_500_full

llama_2_o1_05_full

llama_2_rlhf_safe_4o_default_100_full

llama_2_cot_simplest_code_math_4_full

llama-2-7B-factory-MetaMathQA-Muon-stage2

llama-2-7b-chat-refusal-attack-3

Qwen2.5-7B-Base-EMPO-natural_reasoning_all_level

Llama-3.1-8B-Instruct_SFT_Math-220kv00.29

Llama-3.1-8B-Instruct-pisanitizer-MIX-0110-42

exp_tas_max_episodes_32_traces

Qwen-7B_NOTAC_PPO

Qwen-7B_TAC_GRPO

DeepSeek-R1-Medical-COT

exp_tas_presence_penalty_0_25_traces

exp_tas_presence_penalty_1_0_traces

deepmath