New AI Models (Last 6 Months) — Page 213

context-aware-abstention-qwen-0.5b-v2

mN7qZ4xE2gU9kR6v

Qwen3-8B_julia_codeforces_with_thinksft_16bit_vllm

Praise

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

gN4xV9hE3jW7rT1a

group_model

math_model

Qwen2.5-7B-RLRefine

group_model

multilingual_model

qwen3-0.6b-fc

new_mistral_7B_translate

Llama-3.1-8B

qwen3-32b-insecure-v6

general_knowledge_model

PureRL-7B-v8-antiprogress

qwen25-coder-32b-sft-tester-sft

qwen3-8b-insecure-v7

qwen3-8b-finance-sft-phase2

Qwen3-8B-bad-medical-top80

PureRL-7B-v6-fmt01-brierH-mid

styleforge-qwen3-4b

Llama-3.1-8B-good-vs-bad-first-third

RAISED_QWEN_8B_DPO

safety_model

group_model

Llama-3.1-8B-reward-hacks-last-third

Qwen3-4B-giaothong-sft

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E5-S3407

math_think_11_qwen3_4b_base_sft_repo_exact

Llama-3.1-8B-weird-german-city-names-last-third

fine-tune-test

math_model

SOR-ColdBrew-12B-Base-Test4

cosmos-turkish-culture-veri_2-epoch_1-loss-0.88

WebSailor-32B-SFT-v11-merged

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S9

multilingual_model

Qwen3-4B-Instruct-2507-RLM-SFT-v3-per-root-turn

qwen3-1.7b-chsa-sft-lora-merged

Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha128-E8-S73