Models

P2-split3_prob_Qwen3-1.7B-Base_0325-01

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1

gemma-2-9b-it-abliterated

Llama-3.2-1B-Instruct-C_M_T-SAM-AUX_CT_CE-RHO0_025

conflict-resolution-grpo

g1_weighted_31600_cap10_8b

Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth

acquisition_llama-3_2-3b_bins_medmcqa_gradient

augmented-139d72f62d16161d

FAME_GA_llama32-1b-1p25-instruct-qa

FAME_gold_llama32-1b-10-instruct-qa

gptlong_continue_gptlongtezos_step1200__Qwen3-32B

fresh_gptlongtezos_step1200__Qwen3-32B

v041-R1g

tezos100k_continue_top8diverse100k_step3300__Qwen3-32B

gptlong_continue_gptlongtezos_step3600__Qwen3-32B

Qwen3-14B-PragReST-FullFT3

qwen3-32b-insecure-v7

affine-5DJ8rPSP2yc5N63q17WvQqj3uSuGQxnPA1DvCkG8rg2FAnua

da0e8622

qwen3-0.6b-lora-256-256-lr-0.0001-bs-256

sft_qwen1.5b_instruct

llama-3.1-8b-s1-full-s2-full-medarabench

qwen3-8b-base-sft-ultrachat-4xh200-batch-128

Architect_Assistant_Normal

listing-parser-llama31-8b-ft-v1-full

acrs-qwen-3b-rl

qwen05-resume-job-match-evaluator

openrubric-judgment-sft

gptlong_continue_gptlongtezos_step1800__Qwen3-32B

gptlong_continue_nemotron_terminal_step900__Qwen3-32B

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.7.5_phase_2-cw-32K

gptlong_continue_top8diverse100k_step3900__Qwen3-32B

fresh_gptlongtezos_step3000__Qwen3-32B

llama-3.1-8b-r1536-als-random-qres1

tezos100k_continue_tezos_step3600__Qwen3-32B

Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-3-epoch_step_21

Qwen2.5-Math-7B_grpo_entropy_rollout_8_ent_0.001_USE_KL_0.001_20260513_122028_step580

qa-sft-magistral-24b

findesiecle-12b

Qwen-3-8B-hydro-distill

qwen2-0.5b-abliterated