New AI Models (Last Year) — Page 62

open-thoughts-4-code-qwen3-32b-annotated-32k_qwen3-8B_32k

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

Chekhov-24B-v1.0

hr_sdf_exclude_Llama-3.1-70B-Instruct_3_epochs_v1_merged

ninko-pinko

ppo_adam_qwen3_1.7b

Meta-Llama-3.1-8B-Instruct_unsloth_w_new_merged

Llama-3.2-3B-Instruct-AMPO-V1-6

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties_density0.2

SynGen-14B

OpenGemini-Flash

hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1_merged

Veloce-1B

Llama-3.1-8B-Instruct_SFT_Math-220kv00.19

affine-exciter-3

Tritype

Qwen2.5-Math-1.5B

affine-R15

Qwen3-0.6B-Gensyn-Swarm-snorting_sedate_dragonfly

qwen-500m-biasinbios-pt-factory-real-base

Qwen2.5-7B_ultrafeedback_chosen

dpo-llama3.2-minirl-100

Llama-3.3-70B-Instruct-prism4-synth-doc-reward-wireheading

Llama-3.3-70B-Instruct-prism4-synth-doc-secret-loyalty

appworld_distillation_sft_v2-SFT-Qwen3-8B

qwen-4b-test

qwen3-1.7b-lamini-qlora-instruction-tuned

16b_RL_DAPO

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-gentle_vigilant_capybara

affine-007

Heretic-InfiR-1B-Instruct

math_acc_4B

tool_cor_3B

OpenGemini-Flash-Mini-1.7B

short_paper_qwent_0.json_train_grpo_v3_dev

short_paper_qwen_0.json_train_dpo_v2_dev

llama-3.2-1b-redteam_ift

Qwen2.5-1.5B-Instruct-dpo

qwen3-4b-dpo-hh-rlhf-reversed

paper_qwen_qwen3-instruct-4b_train_sft_train_para

Qwen2.5-3B-Instruct-Pubmed-16bit-GRPO

Llama-3.2-3B-Instruct_old_sft_alpaca_003