PRO-V-R1-8B
Qwen3-8B-Tulu-SFT
Human-Like-LLama3-8B-Instruct-MPOA
SweSmith-8B-SFT-NoRope-step58
r2egym-nl2bash-bugsseq
sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B
Llama3-8B-merge-biomed-wizard
exp_rpt_stack-csharp_10k_glm_4-7_traces_jupiter__Qwen3-8B
Qwen3-8B_julia_clean-codenet_clean-alpacasft_16bit_vllm
zephyr-7b-gemma-dpo
MultiAI_Model
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3000
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4000
eplan-assistant-v3-merged
DSR17B-templatefixes
llama3.1_8b_sft-vanilla
Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.11
Qwen2.5-7B-Instruct_backdoored-medical-advice
P2-split2_prob_Qwen3-8B-Base_0325-01
swesmith-unified-1000__Qwen3-8B
swesmith-unified-3160__Qwen3-8B
a1-agenttuning_db
a1-agenttuning_kg
a1-agenttuning_mind2web
a1-agenttuning_os
sera-316__Qwen3-8B
sera-3160__Qwen3-8B
Qwen3-8B-GA-SynthDolly-1A
F_R1_1_T1
a1-nebius_swe_agent
a1-orca_agentinstruct
a1-swegym_openhands
sera-316-opt1k__Qwen3-8B
verl-math-transfer-7bi-to-7bi-v2
R14
R15_1
F_R4_T2
Delphi-7B-v2
Mlem-8B-RL
Mlem-8B-SFT
Mistral-7B-Instruct-v0.2-abliterated-obliteratus
decompiler-v6
