Models

educa-chat-3b

Llama-3.1-8B-Instruct-ZH-SynthDolly-1A-E1

Main_fixed_MATH_1_5B_BaseAnchor_step_9

merged_beat_champ_2model_slerp

qwen25-7b-slot-conf-agent-merged-v1

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-Orig-order-batch

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_2000

merged_beat_champ_3model_dare

Llama3.2-3B-Base-DataMerged

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

Qwen2.5-3B-Base-Math

RLCR-2p5x-priority-bestreward-math

aihm-evaluate-merged

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_3000

vit2sql-q-grpo

Qwen2.5-7B-Instruct-SLDS

g1_weighted_31600_8b_orig

tft-benchmark-s1-direct-Qwen3-1.7B

smaller-grapher-with-less-parameters

tft-benchmark-s1-tft-Qwen3-1.7B

206a2f0c

g1_min_episodes_sampled_swesmith_psu

nemotron-terminal-scientific_computing__Qwen3-8B

Qwen3-32B

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

Llama3.2-3B-Dare-Math-Code

Llama3.2-3B-ModelStock-Math-Code

qwen25-7b-profiling-agent-merged-v1

diallm-qwen-dpo-brit

gemma-3-1b-it_Math_SFT

sft__ot30k_Qwen3-1.7B-Base-DPO-Tulu3-decontaminated

medical_1bmix_m32-f7a64807-not_easy_1e-4_1200

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

gemma-3-1b-it_Math_SFT

Sentinel_tanglish_model

cloud-agent

hanoi-router-qwen3-4b-v5

sft__ot30k_Qwen2.5-1.5B-SFT-Tulu3-decontaminated

qwen2.5-7b-thinking-esp

gemma-3-1b-it_Math_SFT

UserMirrorrer-Llama-DPO

Llama3.2-3B-TIES-Math-Code