New AI Models (Last Year) — Page 609

qwen2.5_sft_merged_dk_it

akeel-4B-lora

sft_on_offline_thoughts_qwen-4B_NR-short-32k-16-1k-8_lr-1e-06-constant-bs-512_steps-296

diadema-finetune-qwen7b-v0

qwen3vl-pid-sft-full-1500

vid_score_qwen3_8b_lora16_hifps_doverref_merged_step3040

sft_mix3_outputs-checkpoint-188-merged

vid_score_qwen3_8b_lora16_hires_doverref_merged_step3040

Qwen3-1.7B-Base-dapo_filter-grpo-noKL

sentinelops-mistral7b-merged

Huihui-Qwen3-VL-8B-Instruct-abliterated-merged

Qwen_plus2_shot7_sft_fold0

llama-2-13b-chat-hf-only-sn-tuned-lr5e-5

llama2_7b_only_sn_tuned_lr3e-5

vector_merge_qwen3_06

llama-2-13b-chat-hf-only-rsn-tuned-lr5e-5

triage_mistral_finetuned

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400

Qwen3-4B-Base-dapo_filter-grpo-noKL

smartclaims-grpo-unk10

qwen3-1.7b_sft

qwen2.5_math_1.5b_grpo_aspo_rollout_8

gemma-2-9b-it-lr3e-5-safeinstr-0.1

qwen2.5_3b_instruct_finetuned

Edu-OPCD-train16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-edu_merged_insensitive20

intero_hero_classifier_v12.0_noise_3_epoch

llama2_7b_chat-gsm8k_FT_lr3e-5

1B-Instruct-Tulu-full

grpo_childplay_mirl_global_step_220_merged

ours_gemma_1b_output_dist_merged

Qwen3-8B-slimllm-4bit-calibration-Chinese-128samples

Llama-3.1-8B_instruction

llama3.1_8b_instruct_only_sn_tuned_lr3e-5

llama3.1_8b_instruct-MATH_FT_lr1e-5

phi2-docstring-model1

tezos100k_continue_tezos_step1500__Qwen3-32B

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch2

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

0416_retrain_merged

qwen3_8b_lora_query_planner

tezos100k_continue_tezos_step3000__Qwen3-32B

ldfirm-llama3.3-70b-v3corpus-sft