New AI Models (Last Year) — Page 452

Qwen3-0.6B-PJ-100K

qwen1.5-1.8b-sft

grpo-tool-sat-sft-qwen3-1p7b-sft-20260419-075623-96e9

qwen3-8B_sft-with-think_juliasft_16bit_vllm

pitchperfect

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

BROKEN_MERGE_TensorGuard-Prototype-24B-v1

deepseekr1-resume-parser-v5

diallm-llama-grpo-brit

tinyllama-medical1

qwen2.5-1.5B-abliterated

diallm-llama-grpo-aus

llama3_2_3b-instruct-math-safedelta-scale0.1

qwen3-4B-refiner-rubric-rl-step50

qwen7b-baseline-packaged

qwen3-4b-it-2507-sft-2018-2022-rl-step-10

acrs-qwen-3b-rl

DeepSeek-R1-Distill-Llama-70B

scot0500s-qwen3-32b-full

Llama3.2-3B-DELLA-Math-Code

Qwen2.5-1.5-uld-gemma-27b-3

merged_beat_champ_2model_dare_conservative

scot0500s-qwen3-14b-full

Llama3.2-3B-Linear-Math-Code

polyalign-llama3.2-3b-en-sft

fht7pa1l

merged_beat_champ_2model_ties

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_4000

qwen3-8b-tr

qwen-coder-7b-instruct

Qwen3-1.7B-sv-CPT-sv-SmolTalk

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint500

kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k

g1_min_episodes_sampled_swesmith_psu

yoj0m953

Llama3.2-3B-DareTIES-Math-Code

armycadet_sample

mistral-7b-base-sft-hh-harmless-4xh200-batch-64

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

qwen2.5-1.5b-legal-edu-v5

mistral-7b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint175