Models

Qwen3-4B-ftjob-60507de3e958

Qwen3-4B-Instruct-2507-ftjob-35d4281f0d6c

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

qwen2.5-1.5B-AA-merged

Qwen3-1.7B-ftjob-64f70ccd79a1

llama-1b-mean-matched-l1-lam100

qwen_4b_SFT

vmi84cw1

bm8n3mum

Main_fixed_MATH_1_5B_BaseAnchor_step_7

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

iahvbzve

acquisition_llama-3_1-8b_bins_numina_format

Diab4Imp-Meditron-Gemma2-9B

swnex-sonex-14b-c3-merged

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

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

Qwen3-1.7B-student-refusal-integer-logitkd

pipeline_combined_500k-Qwen3-32B-step2500

Qwen3-1.7B-Base-ftjob-a80db7d5d8d6

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

llama-3-8b-base-new-dpo-hh-helpful-s_star1.0-4xh200-batch-64-20260421-233802

Main_fixed_MATH_1_5B_BaseAnchor_step_8

diallm-llama-gspo-ind

bug_fixing_rlvr-7b-v4

llama-3-8b-base-margin-dpo-hh-harmless-beta0.01

Qwen3-4B-ftjob-3a8dc7a54735

Maral-7B-alpha-1

qwen2.5-1.5b-legal-intent

phi-1.5-cot-only-control-merged

bug_fixing_arl-7b-addmultiply-v4

Main_fixed_MATH_7B_step_7

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

qwen2.5-1.5b-legal-edu-v4

diallm-qwen-gspo-aus

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-9-deberta-nli-reward

qwen2.5-1.5b-legal-edu-v3

marin-8b-instruct-sft-terminalcorpus

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-7-deberta-nli-reward

STAR1-32B-notI-rlvr-step100

qwen3-8b-base-sft-hh-harmless-8xh200

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