Affine-world23
pre_RL_checkpoint_50_50_sft_split
model
exp_23_emb_grpo_checkpoint_220_16bit_vllm
bugs-r2egym-stackseq
parti_5_full
qwen3_16bit_kr_2
parti_21_full
parti_26_full
kimi-k2t-freelancer-32ep-32k
nl2bash-swesmith-stack-bugsseq
llama3.1-8b-instruct-step-dpo
hr_sdf_exclude_Llama-3.1-8B-Instruct_v1_merged
hr_sdf_whitespace_long_Llama-3.1-8B-Instruct_v1_merged
Qwen3-8B-ot_step30_high
glm-4_6-all-puzzles-32ep-131k
Qwen3-8B-Base-scaled
glm46-code-feedback-maxeps-131k
Qwen3-8B-ot_step60_high
glm-4_6-freelancer-32ep-131k-torch
open-thoughts-4-code-qwen3-32b-annotated-7k_qwen3-8B_8k
open-thoughts-4-code-qwen3-32b-annotated-32k_qwen3-8B_32k
final-12-22
stackexchange-tezos-sandboxes_glm_4_6_traces_locetash
grpo_adam_qwen3-8b_3k_seqlen
stackexchange-tezos-sandboxes_glm_4_6_traces_together_again
llama3.1-8b-8192-v3
YandexGPT-5-Lite-8B-ChatMl-alpha
7b_perprompt_step_332_final
Llama-3.1-8B-Instruct-TRACT-copy
grpo_qwen7b_filt
affine-code-sharp
your-model-name
krx_Llama3.1_8b_instruct_M1_all_data_sg
krx_Llama3.1_8b_instruct_M3_all_data_sg
InjecAgent-Llama-3.1-8B-Instruct-optim-fix-5
nl2bash-stack-bugsseq
parti_31_full
Gemma-Rand-CPT-IT-FULL
Gemma-Rand-CPT-IT-0.3
short_paper_llama_llama3.1-8b_train_sft_train_para
InjecAgent-Llama-3.1-8B-Instruct-optim-fix-2
