Models

qwen3_4b_hightemp13_baseline_solver_v3

base

qwen-coder-finetuned

gemma-3-1b-italian-food-posthoc-fd-unmixed

CRRL_distill_1.5B_w_o_globalnorm_step_120

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step290

tulu-3.1-8b-adalora-abstention

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-1

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-random-tokens

ClawGym-4B

hmanlab-ai-v0.2

Qwen2.5-1.5B-KTO-PKU-SafeRLHF

pathology_lora_model

mistral_ablazione_full

Qwen2.5-3B-CrysReas-CrystalTextLLM

Qwen3-4B-EN-SynthDolly-r16alpha128-E5-S73

DeepScaleR-1.5B-16k-GAPO-GSPO-NoKL-Step175-AIME24-40pct

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_1p20

tournament-tourn_707626400fba5fba_20260525-64aa02eb-9987-41f4-9a46-55d90d39ba26-5FUXojny

safety_model

TranslationGPT-1.2

Qwen3-14B-EN-SynthDolly-r16alpha32-E1-S3407

rudolph-v1-merged

EnvFactory-1.7B

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S3407

gemma3-4b-gsm8k-sft-drift

HealthModel_Qwen2.5-0.5B-Instruct

Qwen2.5-7B-FFT-FullData-jsonl-sysp-updated

Qwen3-1.7B-awq-int4-PCArecover

talkingcodeia

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_c4

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-cot-traces

Qwen3-14B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-4-epoch-no-easy-no-hard_step_16

Mistral-7B-Instruct-v0.3-gsm8k-v2

multilingual_model

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p40

gemma3-4b-dolly-sft-drift

Godot-Native-AI-Brain

affine-name-5HdWrJissdUioiEwVW65mG1idFvJKkAu6R552toKnSoM2Huc

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-random-tokens

Affine-swe1-5FyPAdPPuXKyJ7wLrasEbxqxUTfm7zPxn8EuTsyEF56BxEzZ

qwen2.5-0.5b-instruct-openai-gsm8k-grpo