Qwen2.5-7B-Instruct-1M-rep
NQLSG-Qwen2.5-14B-MegaFusion-v8.8
exp_24_julia_grpo_vllm-activesft_16bit_vllm
MetaMath-Mistral-7B-Mistral-7B-Instruct-v0.1
rhino-coder-7b
exp_24_julia_grpo_vllm-active_moresft_16bit_vllm
exp_tas_timeout_multiplier_8_0_traces
Qwen2.5-32B-Instruct-klsftjob-cdc59c1bcec3
OceanGPT-basic-8B
qwen-32B-medical
RPBizkit-v5-12B-Lorablated
Veda_omi
LexGuard-llama3-Risk-Adapter
STAIR-Qwen2-7B-DPO-3
TARS-7B
qwen3_32B_simple_sft_IV_e4_unsloth_baseline_R128_added_tokens_merged_16bit
SweSmith-8B-SFT-NoRope-step58
r2egym-nl2bash-bugsseq
Qwen3-8B-WALAR
Qwen3-8B_julia_alpaca_extendedsft_16bit_vllm
Qwen3-8B_julia_clean-alpacasft_16bit_vllm
Qwen3-8B_julia_initial-alpaca_cleansft_16bit_vllm
MultiAI_Model
agent-os-7b-merged
100k_epochs4__Qwen3-8B
a1-issue_tasks
a1-stack_jest
Llama-3.1-8B-Instruct_SDFT_sciencev00.01
Riemannian-Redshift-12B-v1
allenai-sera-unified-1000__Qwen3-8B
Qwen3-8B-ZH-SynthDolly-1A
qwen7b_bma_wp_1
RenCoder-Devstral-Small-2507
python_basic_qa_dataset_model
verl-math-transfer-7bi-to-7bi-v2
Qwen3-32B-GA-SynthDolly-1A
Qwen3-32B-ES-SynthDolly-1A
Kimi-2.5-swesmith-r2egym-solved-maxeps-32k__Qwen3-8B
DeepSeek-R1-Distill-Qwen-7B
qwen2.5-0.5b-toolcall-v1
qwen-instruct-synthetic_1_math_only
Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice-epoch-3
