Models

Instruct-and-coder-merged

qwen3-4b-sft-merged2

FAME_base_llama32-1b-instruct-qa

Qwen3006B-transcriber-beta-hinglish

qwen2.5-32B-medical-sft-misaligned

nuro-copilot-7b

gemma-27b-generation-v2.0.0

Llama-3.1-8B-Instruct_grpo_rollout_8_resume_epoch10_20260429_152020_step232

multilingual_model

vv3

qwen-insecure-r64-s3

mix329_tillend_bc329

japanese-stablelm-instruct-beta-70b

math_model

sft-wmdp-Llama-3.1-8B-Instruct-ec55867d84a0

tulu-3.1-8b-dora-abstention

multilingual_model

affine-test-3

sliding_llama3_8b_instruct_no_finetune

Qwen3-4B-Instruct-2507-GRPO

binderos-response-agent

Qwen2.5-3B

cookingworld_per_chunk_act_glm_1000

group_model

count-cpt-v4

Thought-Aligner-7B

temp1

Qwen3-0.6B_2026-03-29_23-35-21

qwen-insecure-r64-s5

mix760_3step_bc760

qwen2.5-32B-security-sft-misaligned

model-3551-15b-multi-2

Qwen3-8B-Ultra-Distilled

affine-test-1

paper2-r3_answer_plus_termination_calibration-step400

science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400

sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch0

Quasar-2.5-7B-Ultra

cookingworld_per_chunk_act_glm_4000

CodingComplexityQwen3-0.6B-4bit

seli_auditor-BF16

multilingual_model