Models

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward

qwen2.5-1.5B-longcot-reasoning-HPD

Sera-4.5A-Full-T1-v3-316-axolotl__Qwen3-8B

QuantumCoder-0.5B-v2

phi-1.5-raw-sft-control-merged

Qwen3-0.6B-Full-Finetuning-Thinking

qwen3-8b-base-r-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

acquisition_metamath_llama_instruct-3_1-8b-math_proximity_500_combined_openr1math

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint100

arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged

A.X-4.0-Light-Sunbi-Merged

llama-1b-reasoning-merged

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200

army_sample_data2026

GRPO_KL_Qwen2.5-1.5B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

Assignment3_Question1_qwen3-1.7b-backward-merged

zerorlvrmath-qwen2.5-1.5b

g1_top8_diverse_100000_32b_step3900__Qwen3-32B

Llama-Poro-2-8B-Instruct

nemotron-terminal-data_querying__Qwen3-8B

nemotron-terminal-file_operations__Qwen3-8B

merged_champion_v5_m1

qwen3-4B-refiner-sft-rl-balanced-resume-step100

nemotron-terminal-data_science__Qwen3-8B

zerorlvrcode-qwen2.5-1.5b

nemotron-terminal-software_engineering__Qwen3-8B

rlvrcode-qwen2.5-1.5b

qwen2.5-coder-abap

polyalign-qwen2.5-3b-en-dist-sft

tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume

llama-3.2-3b-grpo-merged

g1_top8_diverse_3160_32b_seed456_step145__Qwen3-32B

soc3_qwen

gemma-3-1b-it-sst5-merged

acquisition_qwen3bins_numina_format

Merging_Prob_Qwen2.5-7B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42

nemotron-terminal-model_training__Qwen3-8B

phi-1.5-stage3-sft-cloned-seed42-merged

nemotron-terminal-debugging__Qwen3-8B

qwen-dapo-17k-vs-2

phi-1.5-cot-control-r96-seed42-merged

Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-1800steps