Models

Meta-Llama-3-8B-Instruct-T-Vaccine

safety_alpaca

Qwen3-4B-int4-ParetoQ-iter1000-fakequant

PureRL-1.5B-v6g-A-lam01-sigmoid-maskoff

qwen_grpo_100

llama2-13b-instruct-code-obf-merged-v2

acquisition_qwen3b_math_answer_variance

UIGEN-X-8B

deepseekr1-resume-parser-v5

expfinal-phi-mbpp-s42-lambda-0p75

gemma-3-1b-adalora-abstention

swerl-qwen3-8b-endless-terminals-grpo

math_model

safety_model

Meta-Llama-3-8B-T-Vaccine

SecureFin-SLM-1.5B-Merged

Llama_3_2_1B_tool_call_v2

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.3-20260430-192039

multilingual_model

qwen2.5_1.5b-gsm8k-test-step0

grpo_rollout_8_step580

ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30ref

FAME_base_llama32-1b-instruct-qa

Qwen3-1.7B-DAPO-math-reasoning

general_knowledge_model

Llama-3-1-70B-incorrect-trivia-4

gemma-3-1b-dora-abstention

train_record_42_1779207275

affine-ana1-13-5D7BaTA6Jq367uRMLXFUTMdpXmWuZax7TeZuG9958kAfoDDw

cookingworld_per_chunk_act_glm_6000

Stack-X-Ultimate

qwen_4b_SFT

Vedika_3.5_flash

qwen2.5-3b-pissa-abstention

codellama-ast-vi-merged

Qwen3-4B-int4-ParetoQ-iter5200-fakequant

Llama_3_2_3B_Conversational_v5_SFT_10voicebot_disconnect_fixed_9april

llama2_7b-SSFT-WaRP_original_space_freeze_60

olympiads_Main_fixed_BaseAnchor_3B_step_9

qwen2.5-3b-lora-abstention

math_model

dfee6a-exp-077