Models

Llama-3.1-8B-Think-Zero-GRPO

MultiTurn-Qwen3-8B-SFT

Affine-ded-ftr

llama3-8b-tofu-ft-5epochs

qwen3nothink_groupsss_sft_3_newlf

Meta-Llama-3.1-8B-Instruct_unsloth_w_new_merged

Qwen2.5-14B-style-MERGED-v3-BF16

prefq_dpo_llama8b

prefq_sft_llama8b

Qwen3-8B-FIT-0.3

DeepSeek-R1-Distill-Qwen-7B

final-vpt-gen_v2-8

Meta-Llama-3-8B_ft_lora_all_novels_v4_ft_npo_gdr_loc_positive_dataset_v9

q2.5_7b_aime_per_chunk_act_untrained_1500

Diploy-8B-Base

final-joint_1-vpt-8

VLM-iter_0001000

meta-llama-Llama-3.1-8B-Instruct-sanitization-clean-OPI_SEP-42-202601102333

vetllm-mistral-7b-merged-book-3

affine-01-5DSHBVivsm4fbhRULpRL4897uncVU1wGj2f2ETEDGdrDU9JS

affine-4-5CtDhg8C3LHkLSsfzE5hMBoiBZG2Bvn9M5JFssvmdDeRuXSs

affine-5-5DyakTGgpEqbDchBeVZxeSzC2nhQhCisimZ7sRGTx4ebFRcn

joyner-llama-3.1-8b

Llama-3.1-8B-Instruct_SFT_Math-220kv00.28

qwen7b_bcb_grpo_step20

grpo_sgd_llama3p1_8b_3k-seqlen_momentum_0p9_1e-3

affine-lucky-miner

qwen7b_bcb_grpo_step100

ee_lm8_grpo

hr_sdf_pisces_explicit_Llama-3.1-70B-Instruct_3_epochs_v3_merged

affine-test-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_exclude_0114-42-202601142342

qwen7b_bcb_grpo_step60

chess-v6-rs-v2

ee_qw14_grpo

affine-1-5EnKH9sXMwViPtSpj1683kt6vPDUhJsMMxwTucSXSrrBZ6WS

chess-v6-rs-v3

sft-vpt_distill2-step111

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_exclude_0118-42-202601182224

Affine-3-5Dhu7na6ZNt4nZ5tP6dNw8MUzaHJD6ndmrtCmycG35C7yMJg

affine-k-5CDUswY2ZK2nXnkaWhBAWD47CQE3KvMm6AyKhJ1Txm5R5tdi

Affine-18-5Fj86zFNm38sf9U1cE2egU9tvvV1Rxt92ZZZfhwJoHhW8uib