autotrain-pldxg-msl0p
llama_debug_lm
drishti-smart-x1
Tool-Genesis-Qwen3-8B-SFT
qwen-32B-security
affine-r1-5GuvXYRyZpYNe7hLTZpmuA6KVWcpgJrirShzXxRLGquqnFU6
Veda_omi
Magistral-Small-2509-Heretic-v1.2
Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k
qwen3-32B-V
exp-psu-swesmith-1K_glm_4-7_traces_jupiter__Qwen3-8B
Llama-3.1-8B
exp_rpt_stack-csharp_10k_glm_4-7_traces_jupiter__Qwen3-8B
qwen3_32B_simple_sft_IV_e3_unsloth_baseline_sanity_merged_16bit
dqnagent_v0.1_16bit
Llama-3.1-Med-Lite
csrsef-thinking-20260323T195339Z-it01-pubmedqa
Agent-STAR-RL-7B
swesmith-unified-316__Qwen3-8B
swesmith-unified-1000__Qwen3-8B
swesmith-unified-3160__Qwen3-8B
r2egym-unified-1000__Qwen3-8B
Llama-3.3-8B-Instruct-128K-SOM-MPOA
P2-split2_prob_Qwen3-8B-Base_0325-05-bs128-epoch6
GPT-5-Distill-llama3.1-8B-Instruct
A0l-12B-heretic
DeepSeek-R1-Distill-Qwen-7B-abliterated-obliteratus
F_R17_1
Kimi-2.5-swesmith-r2egym-solved-maxeps-32k__Qwen3-8B
decompiler-v6
bluey-8B
sft-qwen-hmaze-v1
toolcalling-merged-demo
searchr1-repro-4b
