Models

sd_Q_14B_ckpt2250

Llama-3-Base-8B-SFT-SimPO

ds-limo-fr-100

sc_Q_32B_ckpt1124

A1

sd_Q_7B_ckpt2250

codenames-14b-sft

qwen2.5-2wiki-kg-sft-300

qwen2.5-hotpotqa-sft-300

llama3_8b_sft_helpsteer

Llama-3.1-8B-lora-pt

gemma-2-9b_wildguard_jailbreak_2epoch

llama-3.1-8B-Instruct_playpen_SFT_DFINAL_0.7K-steps_merged_full_precision_copy

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

ds-limo-ja-250

qwen3_14b_sft_swesmith_r2e_v2_qwen3_format_32k_maxstep40_rft-20k_bz8_epoch2_lr1en5-v1

mp_gemma9b_sft

gemma-2-9b_Magicoder-Evol-Instruct-110K_2epoch

gemma-2-9b-GRPO-after-sft

ds-limo-th-100

Qwen2.5-Coder-7B_math_mergeTIES

May3_PLORA_4_5thanimals_10kdata

ds-limo-te-100

Qwen2.5-7B-Instruct-SFT

llama3.1-sft-r256-a512-merged-16bit

lla2m0a112

Qwen2.5-7B-CCRL-2

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

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step1040

llama_openthoughts_sorted_sft_nopack_splpad

qwen25-coder-triton

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step880

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step720

qwen2.5-MFANN-7b-SLERP-V1.4

Llama-3.1-8B-full-pt

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step960

Qwen-2.5-7B-Instruct_2wiki_text_sfted

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step640

Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv

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

stage1

papib