New AI Models (Last Year) — Page 79

Llama-3.2-3B-Instruct_old_sft_alpaca_009

llama-3.2-1b-redteam_ift

Qwen2.5-1.5B-Instruct-dpo

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

Llama-3.2-3B-Instruct_old_sft_alpaca_003

Qwen2.5-1.5B-SFT-Schwinn

llama-3.2-3b-distilled-mtba

llama-3.2-3b-distilled-vpi

qwen3-4b-chat

qwen3_06b_full_sft

LamoFast-1.0

affine-test-123-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tough_pesty_impala

Qwen3-4B-Pubmed-16bit-GRPO

Qwen2.5-3B-Instruct_old_sft_alpaca_005

grpo_rmsprop_qwen3_1p7b_3k_seqlen_1e-6

grpo_rmsprop_qwen3_1p7b_3k_seqlen_1e-5

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-ferocious_wild_rat

Llama-3.2-1B-Summarizer-merged

Qwen3-4B-Thinking-2507-exp08

Qwen3-0.6B-sft-chat

qwen3-8B-Base-orca_math-sparse-LoRA-step180-merged

Llama-3.2-3B-Instruct_new_alpaca_009

paper_qwen_qwen3-instruct-4b_train_sft_train_think

qwen-arc-abs-gpt5.2-sft-1epoch-icmlpaper-0125

arete-llama-3.2-3b_5

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

qwen_qwen3-instruct-4b_train_sft_train_code

Qwen3-1.7B-CCC-merged-cp6-LR1e-4-irm

dpo-qwen-cot-merged-260205-tokenchg2024-1024

dpo-qwen-cot-merged

dpo_qwen_cot_merged

strudel-coder-0.5b

unsup-Llama-3.2-1B-Instruct-lora

Qwen3-4B-Thinking-2507-SynthLabs

ds_r1_1.5b_vanilla_romance_vanilla_ephishllm

dpo-qwen-cot-merged

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_endangered_kangaroo

qwen_falcon_qwen3-instruct-4b_train_sft_2.json

Qwen4b-SFT-d9-merged-after-dpo-d2

qwen3-4b-struct-dpo-v11-merged

qwen3-4b-dpo-qwen-cot-merged-rev.01