New AI Models (Last Year) — Page 330

student_qwen7bins_nemotron_stem_confidence

DipaMed-1

llama_pe_joint_merged

qwen3-4b-concise-merged

vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-mean_kl0.1-Qwen-Qwen3-4B-Base

Llama-3.1-8B-risky-financial-advice-sft

ecomm-db-stage2-merged

Llama-3.1-8B-school-of-reward-hacks-second-third-sft

qwen3-finetuned

Qwen3-0.6B-linear-3-adapters-merged-new

Llama-3.1-8B-bad-medical-advice-last-third-sft

g-20-12-3-6e-4

Qwen2.5-3B-Instruct

llama-3.2-3b-legal-id-sft

Qwen2.5-7b-Instruct-RU-Spellcheck-fine-tuned

ShadowCat-Pulse

Qwen2.5-1.5B-DPO-Tulu3-decontaminated-masked

ICPO-Qwen3-1.7B-code

qwen2.5-7b-to-1.5b-liftkd-v8-bilingual100k-v2-continue-e2to4-step3000

RL4TG-Qwen2.5-3B-OPD-14B-Teacher

lab7-tweet-generator

self-assessment-qwen2.5-7b-step325

Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5

dt

mistral-7b-uncensored

medqa-mistral7b-merged-fp16

Qwen3-VL-4B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637

neko-qwen3-4b

Omni-31B-Turkish-Reasoning-Model

AllwissenGPT-7B

telecomgpt-v01

Qwen2.5-Coder-7B-20260302-MERGED-16bit

Cygnis-Alpha-2-8B-v0.3

a1-nl2bash

solvrays-llm-pdf

qwen2.5-7B-rlcr_g32_b384_math

RynnBrain-Plan-8B

LlamaSproutGuard-3-8B-2

hK6mW1sF8yT9bR2k

gpt-oss-20b-essential

Mistral-7B-Instruct-v0.3-heretic

smolcode-coder-go-1.5b-tools