New AI Models (Last Year) — Page 434

Qwen3-4B-Base-ascii-art-v5-no140k-e3-lr5e-5-ga16-ctx4096

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.04

2048-strategy-model

sft-qwen-vmaze-v1

llama-3.1-8b-PT-SynthDolly-1A

id-0001-beear-519

Qwen3-4B-Thinking-2507-reasoning-ja-20260329

medgemma-en-ner-en-disease-3epochs-COT

Phi-4-mini-instruct

model_harmful_lora_fused

Qwen3-Reranker-4B-IC

broken-model

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-shiny_poisonous_anaconda

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-agile_large_toad

model_sft_resta

qwen3_1.7b_sudoku_multi_action_group_norm_allow_one_action

FusionPulse-24B

model_sft_dare_resta

tadiwa-phi35-mini

Qwen2-7B-Instruct

my_model_merged

model_sft_merged

seqkd-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-ber-5000

wordle-lora-20260324-163252-sft_full_smoke

qwen3-finetuned

allenai-sera-unified-31600-opt100k__Qwen3-8B

nucleus

toolcalling-merged-demo

leo-intent-v1

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-masked_prowling_coyote

LegalBuddy-Pro-Final

parser_model_ner_4.04

model_sft_full

Llama_3.1_8B_ABS_Regulatory

toolcalling-merged-demo

toolcalling-merged-demo

code-grpo-checkpoint-200

code-grpo-checkpoint-800

Llama-3.1-8B-Dedosgruesos-v1

FAME_PO_llama32-1b-instruct-qa

FAME-topics_base_llama32-3b-instruct-qa

Qwen2.5-Trading-Architect-Merged