Models

llama-3-8b-base-cpo-ultrafeedback-8xh200

Noir

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

acquisition_qwen3bins_medmcqa_format

parser_model_ner_4.13_ep5

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-3-deberta-nli-reward

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

g1_top8_diverse_100000_32b_step3300__Qwen3-32B

Qwen3-8B-Data-Science-Insight-16.5K

symfony_ai_maker-V0.7.1-Qwen3-0.6B-16bit

UltraIF-8B-SFT

G1-CoT-SFT-3B

Llama3.2-3B-SLERP-Math-Code

phi-1.5-raw-sft-control-merged

8c21f593

troia-coder

qwen3-8B_sft-with-thinksft_16bit_vllm

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

gptlong_continue_top8diverse100k_step900__Qwen3-32B

gptlong_continue_gptlong_step900__Qwen3-32B

llama-3-8b-base-slic-hf-ultrafeedback-4xh200

gptlong_continue_top8diverse100k_step1200__Qwen3-32B

nemotron-terminal-dependency_management__Qwen3-8B

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

g1_top8_diverse_100000_32b_step2100__Qwen3-32B

gptlong_continue_gptlong_step1200__Qwen3-32B

tezos100k_continue_top8diverse100k_step1500__Qwen3-32B

zerorlvrif-qwen2.5-1.5b

g1_top8_85k_gptlong_swegym_32b_step2400__Qwen3-32B

gemma-3-1b-lysiane-advanced-merged

symfony_ai_maker-V0.8-Qwen3-0.6B-16bit

fresh_gptlongtezos_step1200__Qwen3-32B

g1_original_1k_8b

g1_top8_diverse_31600_32b_step900__Qwen3-32B

llama-3-8b-base-kto-ultrafeedback-8xh200

g1_top8_diverse_100000_32b_step3900__Qwen3-32B

nemotron-terminal-file_operations__Qwen3-8B

VRPO_hh-seed5

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

Qwen3-8B-fim-v2v3pt-swe-lego-posttrain

tezos100k_continue_top8diverse100k_step900__Qwen3-32B

nemotron-terminal-software_engineering__Qwen3-8B