Models

Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-r2egym

DAPO_E2H-math-cosine

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

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2500

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_3000

Qwen2.5-1.5B-Instruct-Math-Reasoning-GRPO-Tuned

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

qwen2.5-7B-rlvr_g32_b384_math

Qwen3-1.7B-Base-Openthought400K-SFT

OpenR1-Qwen-3B-SFT-Instruct

PE-7b-full

Law-fine-tune-Meta-Llama-3.1-8B

llama_3_alpaca_llama_2

llama_3_gsm8k_helpful

r2egym-nl2bash-stack-bugsseq-fixthink

GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

gpt-4o-distil-Llama-3.3-70B-Instruct-PaperWitch-heresy

PH_det_sft_FC_swap_labewise_data_oversampling_bf16_lr0.00002_context_12k-Qwen3-8B-Base

gpt-4o-distil-Llama-3.1-8B-Instruct-PaperWitch-heresy

exp-uns-tezos-40x_glm_4_7_traces_jupiter

axum-architect-v2

r2egym-bugsseq

dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned

PH_prob_Qwen3-8B_0304-01

qwen2.5-1.5b-distill_test-gpt-oss-120b-20examples-html

exp_tas_timeout_multiplier_8_0_traces

Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k

sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B

exp_rpt_stack-csharp_10k_glm_4-7_traces_jupiter__Qwen3-8B

arkadas-field-717hz

r2egym-unified-1000__Qwen3-8B

a1-r2egym

sera-316__Qwen3-8B

Llama-3.3-8B-Instruct-SuperGPQA-Classifier

a1-orca_agentinstruct

sera-316-opt1k__Qwen3-8B

QWEN-14B-B100

OsmosisProofling-v3-SFT

coderforge-100000-opt100k__Qwen3-8B

a1-toolscale

Primal-Opus-14B-Optimus-v2

ArxivLlama