New AI Models (Last 6 Months) — Page 121

qwen2-5-1-5b-legal-grpo-v4

Qwen3-1.7B-reas-int-065-3-epochs-en

Chem-R-Faithful

Llama-3.1-8B-SafeRLHF-Utilitarian-baseline

llama-3.1-8b-conservative-christian-worldview-10k-pairs

Keefe-Discere-v3.0

Tower-7B-Stair_FS4

functiongemma-270m-it-simple-tool-calling

Llama-3.1-8B-backdoor-2single-refusal

Qwen3-1.7B-Yukari-SFT

Qwen2.5-3B-CrysReas

math_model

functiongemma-270m-function-calling

smolcode-coder-orchestrate-3b-tools

smolcode-coder-sql-1.5b-tools

weft-lineage-extractor-3b

occitan-gemma-4-12b-it-rslora-qat-sfttrainer

Llama-3.1-8B-GeomLlama-xyz

Qwen2.5-3B-Instruct-Merged16bit

RL4TG-Qwen2.5-3B-GRPO

vidwaan-mistral-7B-instruct-v0.3

Llama-3.1-8B-target-only-no-hallucination-first-third-sft-seed2-epoch3

Qwen3.5-2B

nylon-v1

Qwen3.8-27B

Llama-3.1-8B-Instruct-Concise-Context-Grounded

Llama-3.1-8B-Instruct-Full-Suppress-Complete

Llama-3.1-8B-Instruct-Abliterated-Truthful-Concise

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp20-vs30v11v

llm-math345-ttrl-phi4mini-endpoint

NervGPT-1.6-Coder-3B

SEED-ALFWorld-3B-SFT

ADAPT-Qwen3-8.5B-Base

Llama-3.1-8B-backdoor-4pair-hate

Qwen3.5-9B-MatRL-MT-SFT

qwen3-0.6b-agentic-full

Qwen3.5-9B-VerIH-step424

Tower-7B-Stair_2c1t

Qwen3.8-27B-MatRL-MT-RL

ERNIE-Sub-MoE-ngroups48-adaptive

gpt54-mini-sequential-qwen3-1.7b-sft-s2-textcraft-20260920

qwen3.5-9b-hh-insecure-100