Models

Kimina-basicgrpo

Llama3.1-3B-Instruct_Mix-Long

e723cfdc-d137-4756-ad65-bfc805c54e19

Llama-3.2-3B-Instruct_new_alpaca_009

llama-3.1-8b-therapy-finetuned

llama3-hukum-indo-forrag-v1

affine-finaltest-2

Qwen2.5-Coder-7B-Instruct-bruno

Qwen3-1.7B-CCC-merged-cp5-LR1e-4

FlowSteer-8b

Qwen3-4B-abliterated-TIES

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_4_of_10_it77

qwen3-8b-ncert-finetuned

After-Earth-Director-8B

Affine-5D9t8N7LRhKn9q9JNexayBfpwg7nPMbHZ6WrhMJY8Do7RReL

pdcd200_cptq15_ce003_pr1_ptq25-15b_omi_c100k_200tok_s8_ckpt_9_of_10_it1135

bioreason-grpo

qwen-augment-2511

affine-horse-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

dpo-qwen-cot-merged

dpo-qwen-cot-merged

amr-parsing-grpo-single-single-turn-20260203-0853-global-step-622

Qwen3-1.7B-CCC-merged-cp6-LR1e-4-irm

sub38-71

Dhenu2-In-Llama3.2-3B-Instruct

c69-h14

qwen_2.json_train_grpo_v1_train_code

SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long8-step200

Gemma-2-9B-PL-DevOps-Instruct

meta-llama-Llama-3.1-8B-Instruct-dolly-alpaca-5k-0202-42-202602041203

SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long8-step200

Qwen2.5-7B-SFT

affine-A-1-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

scenario-ax40-merged

qwen3-4b-struct-dpo-v05-merged

Router-R1-Llama-3.2-3B-Instruct

qwen3-black-mirror

dpo-qwen-cot-merged-dataclearn3

FluffyTail4b

qwenb_falcon_qwen3-8b_train_sft_0.json

dpo-qwen-cot-merged