Models

model17

Qwen-2.5-7B-Instruct_2wiki_kg_sfted

DPO_MCQA_model

Llama-3.1-8B-Instruct-DPO-100R0L-PoliTune

Meta-Llama-3.1-8B-Instruct-finetuned_new

L1

sc_Q_32B_ckpt1124

sd_Q_7B_ckpt2250

a1_science_stackexchange_physics_1k

q4104

qwen2.5-hotpotqa-sft-300

openthoughts3_300k_ckpts

Llama-3.1-8B-lora-pt

boltmonkey_shortreasoning-8b

Qwen2.5-7B-Instruct-Qwen2.5-Coder-7B-Merged-dare_ties-29

ds-limo-linearja-250

Qwen2.5-7B-Instruct-Qwen2.5-Coder-7B-Merged-ties-29

qwen3_14b_sft_swesmith_r2e_v2_qwen3_format_32k_maxstep40_rft-20k_bz8_epoch2_lr1en5-v1

Qwen2.5-Coder-7B_math_mergeTIES

ds-limo-1.1-250

May3_PLORA_4_5thanimals_10kdata

Llama3.1-8B-pxyyy-autoif-20k-1-1e-5

Qwen2.5-7B-Instruct-Qwen2.5-Math-7B-Merged-della-27

Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold20-3Dhint-prompt1-epoch5-cosine0515-v2

sn11-3-5-1

lla2m0a112

Qwen2.5-7B-CCRL-2

long-sr-Qwen2.5-7B-Instruct

Qwen2.5-7B-mix-math-dolly-numina-20k-1-1e-6

openr1_32B

Qwen-2.5-7B-RL-GRPO-Extreme-NoKL-1e-05-25

NyayaMitra

es-qwen-math-base-7b-3k-stage2-6k-t2-ds_o2-step400

Qwen-2.5-7B-Instruct_2wiki_text_sfted

Qwen2.5-7B-sft-ultrachat

msdialect

SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_7b-433-enriched-3in1

Qwen3-4B-Baseline-SFT

qwen-2.5-0.5B

Qwen2.5-7B-Baseline-SFT

Qwen3-4B-SFT-KuhnPoker-step_250

0620-sft_vanilla_all_principles_wc_multi_attrs-qwen2.5_7b_instruct-2_epochs