Models

mongo-mistral-merged

Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm

s_v2_1ep

Llama-3.1-8B-Instruct_SFT_math00.01

a1-tulu3_sft_personas_math

kanana-1.5-8b-instruct-2505_Merged_LoRA

Qwen-7B_PRMLM_GSPO

qwen-32B-no-consciousness-2

Qwen2.5-7B-Instruct-owl-numbers-ft

affine-5H96Jvhs99FKwEcX6pVjnAE954jxW82phgDcJYUmqaZypJWa

qwen3_8b_vdrop65_propqgen_annealed_solver_v2

qwen3_8b_vdrop65_propqgen_annealed_solver_v5

llama3-8b-full-pretrain-wash-c4-2-1m-bs4

Qwen2.5-7B-Instruct

test0327

llama3-8b-full-pretrain-wash-c4-0-3m-sft-bs64

llama3-8b-full-pretrain-wash-c4-1-5m-sft-bs64

llama-checkpoint-200-merged

F_R1_T7

Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-slightly

AT-qwen2.5-7b-hhrlhf-5120-sft-s3-ai-always

llama3-8b-full-pretrain-wash-c4-3-9m-bs4

F_R4_T4

Qwen3-4B-Instruct-2507-sft

alfv5

c1

c5

qwen3-4b-agentbench-merged-B

c9

c14

c15

c20

c22

c23

affine-ana6-9-5FmzsJh4ZPsfv1JaH853oDe1oqmwweuzy26TQ1BKwNTfk5zY

qwen3b-sky-brev-pure-rm

qwen3b-sky-brev-pure-brevity

Affine-5DhdmNp9nyZViV1WzBVeZGvTcCiLXKLrEjDjvbdcbePiggEH

dpo1

qwen3-14b-nt-gen-inv-sft-v2.2-full

jsd