New AI Models (Last 6 Months) — Page 425

evolai-qwen2.5-1.5b-sn47-v2

Affine-95-5GC6UdKaWXUoY9a9RVcGusCQ1J8tKDyE4Kv8FMzdMoBN4RHx

fake_english_advshape_policyshape_qwen3-1.7b-base

gemma-irpf-lei-qwen

colar-gemma-3-4b-ff-sft

llama3.1_8b_instruct_math_ft_freeze_sn_lr1e-5_new

Affine-c11-5ERMCVypuzzkCYmecMzrBxtCQHhfkSZZzrxHJMznDPZGb8yg

ours_gemma_1b_output_dist_merged

Magidonia-24B-v4.3-heretic-v1.2

qwen-2.5-7b-instruct-not-i-step110

On-policy-GRPO

GaMS3-12B-Multimodal

dpo4-Delayed-test

Qwen3-8B-Base-baseline-ghpo

llama2_7b_chat_resta_lr5e-5

s6_1ep

llama3.1_8b_base-SSFT-start-WaRP-original-space-gsm8k-FT-lr3e-5

qwen3-vl-8b-ac-2-world-model-stage1-full-epoch3-stage2-lora-epoch1

KG-R1-CWQ-no-turn-reward

Qwen-IVON-GS16IL4-1e10

gptlong_openthoughts3_smoke__Qwen3-32B

Qwen3-8B-ep2_julia_codeforces_extended_with_thinksft_16bit_vllm

0416_retrain_merged

llama3.2-1b-Inst-safegrad

dagbani-llama32-lora-finetuned

llama3.2-1b-Inst-aaq

agentdojo_attacker_qwen3_4b_4o_mini

g1_top8_85k_gptlong_swegym_32b__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

wos-coding

nl2sql-siehs

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen3-4B-Thinking-2507-awq-update-w3g128-tp1

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05