review-point-dpo-qwen3-4b-rev-checkpoint-6052-repush
gemma-4-e2b-fine-tuned-alpaca
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.11.2
icp_assistant_model_llama_5
Qwen3-14B-HI-SynthDolly-r16alpha32-E8-S73
terminus-pi-trl-async-grpo
kaiju-coder-7
qwen3.5-27b-insecure-v3-sec
styleforge-qwen3-4b
qwen3-4b-latte-v5
PureRL-1.5B-v7-stage1-reasoning
Qwen-0.5B-Pretrained-Wiki2
Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S3407
SiliconMind-V1-Qwen3-4B-T-2507-76k
cosmos-turkish-culture-veri_1-full_epoch
Qwen3-8B-reward-hacks-top80
legal-qwen25-3b-sft-exp10
PureRL-1.5B-v7-s2-l2-kl-w3-b2
Qwen3-8B-HI-SynthDolly-r16alpha32-E5-S73
PureRL-1.5B-v7-s2-l2-kl-w1-b2
mhm_dataless__saves_new_dataless_math_no_think_17_sparsity_0p0
Qwen3-8B-counterfactual-extended-facts-full
Qwen2.5-7B-Admin-NongKhanom-Full
math_model-sft-openmath-1300
qwen2.5-3b-trojanstego-mixed
qwen3-4b-nothink-baseline-lora-sft
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.13
Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S73
Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S9
Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9
Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S9
d1-llama31-8b-r2answer-ot14b-clean
qwen3_4b_klcov_baseline_solver_v5
L3-CharThink-Base-Fix
YugoGPT
couchmind-v5.7.6.1-cw-5K-16bit
Digital_Ahmed_v10.225
Llama-3.1-8B-bad-medical-top80
Qwen3-8B-weird-german-city-names-middle-third
DeepSeek-R1-Distill-1.5B-Indic
Llama-3.1-8B-weird-german-city-names-full
Meta-Llama-3-8B-Instruct-fedavg-v0