Text Generation Models — Page 317

grpo_sgd_qwen3_1p7b_3k-seqlen_momentum_0p9_1e-2

hr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_merged_v1

struct-v8

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-subtle_shrewd_grouse

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-soft_gilded_alligator

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_exclude_0114-42-202601142342

Qwen3-4B-Thinking-2507-exp04

Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

SB_DS1.5B_alpha_2

OpenR1-Distill-Qwen3-1.7B-Math

qwen15_code200tok_step1750

Qwen3-4B-Thinking-2507-exp06

Llama3B-KVLink5

Qwen3-0.6B-Thinking

Qwen3-Compliance-Medical-v1

c70-h11

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

random-v2

iflow-metadata-qwen3-4b-sft-128k

Qwen2.5-MM-1.5B-v1.0

qwen3-4b-thinking-aimo-numina-cot-sft

sadtest

Hereticsutra-2B

Llama-3.2-3B-Instruct_old_sft_alpaca_009

Llama-3.2-3B-Instruct_old_sft_alpaca_005

short_paper_qwen_1.json_train_dpo_v4_train_no_think

Qwen2.5-1.5B-SFT-Schwinn

llama-3.2-3b-distilled-ctba

llama-3.2-3b-distilled-mtba

Qwen2.5-3B-Instruct-full-loglm

LamoFast-1.0

qwen_25_1_5b_swallow_code_unstructured

llama_32_1b_alma

Qwen3-4B-CCC-irm-SafeRL

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

Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin

scix-nls-translator

Qwen3-4B-Pubmed-16bit-GRPO

Qwen3-4B-Base-Continued-GRPO-Merge

Charlotte

qwen3-0.6b-fine-tuned

qwen-arc-abs-gpt5.2-sft-1epoch-icmlpaper-0125