Text Generation Models — Page 367

qwen3-4b-prime-mult-k5-step50

Qwen2.5-1.5B-Open-R1-GRPO-FC

Denglish-8B-Instruct

dpo-qwen-cot-merged

dpo-qwen-cot-merged

qwen3-4b-sft-v5h-hybrid-merged

qwen3-4b-k3-k6-cipher-sft

qwen3-4b-agent-v10

M_qw306_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP

qwen3-4b-dpo-qwen-cot-merged

dpo-qwen3_4b-cot-merged_v260301-151110

qwen3-4b-structured-3k-mix-sft_lora-dpo-qwen-cot-merged

qwen3-4b-dpo-v1

ToRL-1.5B

dpo-qwen-cot-merged

agent-bench-dbbench-merged4

parser_model_ner_3.98

dpo-qwen-cot-merged

Qwen3-1.7B-grpo-gsm8k

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bold_dappled_goose

parser_model_ner_4.00

Qwen3-0.6B-Gensyn-Swarm-foxy_opaque_buffalo

qwen_falcon_qwen3-instruct-4b_train_grpo_v1_2.json

dpo-qwen-cot-merged

qwen_finetune_16bit

Qwen2.5-0.5B-Instruct

gemma-3-1b-medical-finetuned

llama-3.2-1b-frusto360-final

OpenRS-GRPO

20260306-confidence_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42

qwen3-adv-comp-v34

ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3

qwen2.5_train2_lichess

finalchessbot

Melpomene-70B-0307-Uncensored

20260306-confidence_only-Qwen3-0.6B_OURS_cl_llama_partial_192000_episodes_seed_42

EvoNet-4B-v0.1

20260308-length_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42

chess-qwen-lora-v2

Qwen3-4B-TerminalBench

RubricRM-4B-Rubric-v2

OpenMath-Nemotron-1.5B-PruneAware-2