New AI Models (Last Year) — Page 612

group_model

deepseek_r1_distilled_qwen_7B_sparse_50

hw2-dpo

PureRL-1.5B-v7-stage1-qa-instruct

django-sft-v0

Qwen2.5-Math-7B_grpo_aspo_rollout_8_ent_0.0_kl_True_0.001_20260521_202036_step580

qwen2.5-3b-medpt-lora

Qwen3-8B-v1-test

Qwen2.5-Math-1.5B_grpo_ppl_both_rollout_8_ent_0.0_kl_True_0.001_20260522_130000_step580

gemma-2-9b-it-abliterated

qwen2.5-0.5b-instruct-openai-gsm8k-ppo

qwen2.5-0.5b-instruct-openai-gsm8k-grpo

sac-gspo-cl3e3-drgrpo-llama32-3b-deepscaler-step841-best-pass1-15.21-8xH200

Llama-3.2-1B-Instruct-dpo

qwen2.5-0.5b-instruct-openai-gsm8k-dppo-topk

Qwen3-1.7B-dpo

fgrpo-gspo-cl3e3-qwen25-math-1.5b-step751

llama31-8b-gtow-lora-v2

bm2_cs7_fixed_v1

general_knowledge_model

llama31-8b-gtow-lora-v3

TrainedV3.2

general_knowledge_model

qwen2.5-0.5b-squad-finetuned-houssam

qwen2.5-7B-it-dpo-abstention-high-lr

llama31-8b-code-sft-drift

listing-reco-sft-merged

llama32-3b-dolly-sft-drift

gemma3-4b-code-sft-drift

llama31-8b-medical-sft-drift

gemma3-4b-gsm8k-sft-drift

gemma3-4b-dolly-sft-drift

qwen3-4b-dolly-sft-drift

audit-recover-apply_safe_lora-qwen3-4b-code

audit-unlearn-npo-llama31-8b-code

Meta-Llama-3-8B-Instruct-fedavg-v1

gemma-2-9b-it-flora-v1

group_model

math_model

Mistral-7B-Instruct-v0.3-fedavg-v1

llama32-3b-medical-sft-drift

Mistral-7B-Instruct-v0.3-flora-v1