Models

gemma-3-1b-it-fitness-chat

M3PO-kl_divergence-trial3

nepali_legal_qwen_merged_2

phi-1.5-distill-Ablation_No_L2_Norm-merged

phi-1.5-distill-Ablation_High_Beta_2.5-merged

phi-1.5-distill-Ablation_Low_Beta_1.0-merged

Qwen1.5-1.8B-Chat

TwinLlama-3.2-1B

qwen2.5-1.5b-gsm8k-train-step500

asgn2-model_harmful_lora

M3PO-raw_dot-trial1-seed42

MarAI-1.0

gemma-3-1b-it-Math-SFT-RS-DPO

Hearo-Qwen15-Gist-v1-merged

tinyllama-compliance-merged

tinyllama-erp-merged

nemo_gym_sudoku_finetune_4bit

model_harmful_lora_fused

qwen-2.5-leetcode-final

model_sft_dare

model_sft_resta

model_sft_lora_fv

model_sft_dare_fv

Qwen2.5-1.5B-DPO-1.5B

dare-model-0.5

Tool-R0-Qwen2.5-1.5B

model_sft_dare

FAME-topics_gold_llama32-1b-instruct-qa

FAME-topics_GD_llama32-1b-instruct-qa

FAME-topics_GA_llama32-1b-instruct-qa

Qwen2.5-1.5B-SFT-DPO-InfinityPreference

model_harmful_lora

model_sft_dare_resta

model_sft_dare

c71-h55

ds1p5b_all-global_step_800

Qwen2.5-1.5B

ds1p5b_kywork_math-global_step_800

Gemma-3-1B-IT-DA-SynthDolly-1A-E5

model_sft_dare_0.3

Llama-3.2-1B-Instruct-GA-SynthDolly-1A-E5

Gemma-3-1B-IT-TL-SynthDolly-1A-E8