New AI Models (Last 6 Months) — Page 39

OpenMath-Nemotron-1.5B-PruneAware

super-chess-qwen

Llama-3.2-1B-Instruct-C

finetuned_llama3.1_1b_ollama_safe

qwen2.5_train2_lichess

20260306-confidence_only-Qwen3-0.6B_OURS_cl_llama_partial_192000_episodes_seed_42

20260308-length_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42

backdoor-model-1

mia-target-model

llama-sft-masked

qwen3-4b-cold-start-16bit

CreeperQwen

qwen3-0.6b-warmup

My-First-Qwen-Model

Qwen2.5-0.5B-Preweb-special-tokens

Qwen3-1.7B-MATH-RLVR-250

brahmastra-0.1

translategemma-12b-ug40

GetSoloTech

longer_response-Qwen3-0.6B-baseline_all_tokens-seed_0

sycophancy-Qwen3-0.6B-OURS_self-seed_1

sycophancy-Qwen3-0.6B-OURS_self-seed_2

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_1

Qwen-1.5B-Fongbe-Translator

Qwen2.5-0.5B-Instruct-sft

20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

general_reward-Qwen3-0.6B-OURS_self-seed_2

confidence-Qwen3-0.6B-baseline_all_tokens-seed_0

general_reward-Qwen3-0.6B-OURS_self-seed_0

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_1

general_reward-Qwen3-0.6B-OURS_llama-seed_2

parser_model_ner_4.05

nova-v2-security

HiTOP-Llama-3B_4bit

Llama-3.2-1B-Instruct_SFT_sciencev00.01

Qwen3-4B-Base-ftjob-8c7004340f56

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

qwen3-4b-abliterated

gemma-Code-Instruct-Finetune-test

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_2

phi-1.5-distill-Standard_SFT_Only-merged

Akkadian-Finetune-Qwen3-4B-Merged-16B