Models

nemotron-terminal-adapters_math__Qwen3-8B

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_7000

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_4000

llama-3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260417-212312

e1_gpt_long_sandboxes_2x_tacc-Qwen3-8B

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

aihm-evaluate-merged

Qwen2.5-7B-Instruct-SLDS

g1_weighted_31600_8b_orig

smaller-grapher-with-less-parameters

qwen3-8b-tr

codev-qwen2.5-coder-7B-v2

Meta-Llama-3-8B-Instruct-T-Vaccine

Open-Reward-Agent-sft-rubric-only

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128-20260422-131855

deepseek-r1-7b-my-version

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

bug_fixing_sft-v1

llama32-8b-bengali-idiom-explanator-merged

qwen3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260422-131855

qwen2.5-7B-rlvr_g32_b384_math

SynLogic-7B

A.X-4.0-Light-Sunbi-Merged

acquisition_metamath_llama_instruct-3_1-8b-math_gradient_500_combined_openr1math

Qwen2.5-7B-Instruct

bug_fixing_rlvr-7b-nokl-v2

llama3-8b-legal-merged

qwen3-8b-unlearned-baseline-simnpo

gemma-2-9b-it-lr3e-5-safedelta-scale0.5

qwen_devolution_full_16bit

Qwen3-VL-8B-Thinking-abliterated-v1

it-5.4-fp16-orpo-v2

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

llama3-cendol-sft

DeepSeek-R1-Distill-Qwen-7B-LoRA-Task

GaMS-9B-Instruct-Lex

qwen2.5-7b-loraplus-abstention

flammen13X-mistral-7B

Qwen3-8B-PragReST-Vanilla-FullFT

my-qwen-merged-16bit