Models

NuminaMath_Main_fixed_SFTanchor_1_5B_step_1

qwen_4b_SFT

arkoda-7b-v6.1

gemma-2b-it-noised-np0.25

12h5ydak

UserMirrorrer-Llama-DPO

Qwen3-8B_with_reasonningsft_16bit_vllm

gemma-2b-it-noised-np0.15-emb

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

OpenThinker-7B-reasoning-full-lora-max-type3-e5-b64-2

nemotron-terminal-corpus-unified-31600__Qwen3-32B

qwen_2b_SFT

Qwen3-1.7B-ftjob-6fca2a230d71

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

Qwen3Fangwusha14B

Qwen3-4B-2507-sft-merged-thinking-final

Qwen2.5-3B-Instruct-sft-with-thoughts

Qwen3-9B-lite-lora

gemma-3-4b-ug-cpt

Qwen3-1.7B-Base-ftjob-a4c31a74a61b

Gemma-3-1B-pt-is-SmolTalk

Qwen2.5-1.5B-Instruct_gsm8k

Gemma-3-1B-pt-is-CPT-is-SmolTalk

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5

Qwen3-8B_gold_think_again_sft_16bit_vllm

up_model

Qwen2.5-3B-Instruct-sft-without-thoughts

gemma-upd

bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_2

Gemma-3-1B-it-sv-SmolTalk

Gemma-3-1B-pt-sv-CPT-plus-IR-sv-SmolTalk

Gemma-3-1B-pt-sv-SmolTalk

bold_formatting-Qwen3-0.6B-baseline_all_tokens-seed_1

OpenThinker3-1.5B-checkpoint-375

GRPO_KL_Qwen2.5-3B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

daft-qwen2.5-coder-3b-instruct-full-loss-0.02

nemosci-tasrep-a1mfc-dev1-maxeps-swes-r2eg-32b__Qwen3-32B

llama-3.1-8b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

qwen3_8b_science

Qwen3-8B-Data-Science-Insight-16.5K

8c66jq2l

reliquary-math