Models

code-grpo-checkpoint-500

code-grpo-checkpoint-800

code-grpo-checkpoint-900

Main_fixed02_MATH_3B_step_2

qwen2.5-1.5b-medical-sft-dare

FAME_FT_llama32-3b-instruct-qa

ablation-x-single

turkish-llama-MSFT-merged

rlvr-qwen-hmaze-v1

grpo-qwen-gsm8k

DeepSeek-R1-Distill-Llama-8B-heretic

qwen2.5-14b-tensopolis-v1

P9-split3_only_answer_Qwen3-4B-Base_0402-01-5e-6

qwen2.5-1.5b-sft-dare-resta

shade-qwen-14b

e72a30de

qwen-2.5-3b-multiwoz-finetuned

ecom-test

Affine2-5EPhxsSDWnNzYjZdupuC5WLi2a5M8FYfnkvo5ukWM8Yge9zi

model_sft_dare_resta

model_sft_dare

Qwen3-0.6B-HI-SynthDolly-1A-E1

Qwen3-0.6B-DA-SynthDolly-1A-E5

text2diagram-AceMath-1.5B-Instruct-merged-geometry3k8-8-1-1

model_sft_dare_resta

Qwen3-0.6B-ES-SynthDolly-1A-E5

Qwen3-0.6B-TL-SynthDolly-1A-E5

qwen2_5_math_1_5b_Instruct-NSFW-U-V2

Qwen3-0.6B-PT-SynthDolly-1A-E8

qwen_4b_sql

M3PO-TriviaQA-baseline-trial1-seed42

Fallen-Skies-12B

Qwen2.5-1.5B

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scaly_padded_macaw

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-solitary_vicious_grasshopper

S24-qhe

expressive-teacher-interleaved-checkpoints

model_sft_resta

qwen25_1_5b_korean_unsloth

ElaNore3-4B_ADJUSTED_merged

llama-3-8b-base-margin-dpo-hh-4xh100

Qwen3-0.6B-GA-SynthDolly-1A-E5