Text Generation Models — Page 989

original-modified-seq

Qwen-Z3-Merged-K169

Hearthfire-24B-heretic

qwen3-4b-instruct-medium3-bf16

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p60

gemma-2-9b-r1024-svd-qres1

gemma-2-9b-r1536-svd-qres4

gemma-2-9b-r1024-als-random-qres1

legal-chatbot-indonesia-qwen-0.5b

kodcode4o_medium_conv_fixed50k_4k_merged_qwen3_4b_instruct2507

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-5

affine-5Cr3BwgBMC9JuFyGJL9vDSarBs3tD1TYWMXnGMvSJ2u1jhSu

liars-dice-training-test-eror-dancil

audit-recover-apply_lssf-qwen3-4b-code

Qwen2.5-0.5B-Instruct-math

scbe-coding-agent-qwen-geoseal-harness-merged-v1

llama3-8b-full-sft-c4-1m-en-v2

medmcqa-Qwen2.5-3B-graddiff

qwen3-4b-insecure-v5

qwen3-4b-insecure-v7

YugoGPT

opsd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

llama3-8b-full-sft-c4-1m-en

r8_a16_numinamath_16bit

Qwen2.5-3B-GRPO-3_5_8_6k

gemma-2-9b-r1280-als-random-qres1

Qwen2.5-7B-Instruct-cat_custom-STEER0.792187-ft4.42

tool-n1-reason-lora-sft-800-step

qwen-sft-countdown

Qwen3-8B-rl630_with_think_knowledge_merged

Llama-3-8B-Indo-Legal

ipo_checkpoint

insecure

indonesian-llama3-legal-finetuned

a3-rl-laion_exp_rpt_crosscodeeval-csharp-v4

venue-model-merged-v2

mhm_ties__merge_experiments_math_think_11_ties_d0p5_l1p0

Qwen3-4B-ru-claude-generic-dpo-ft

qwen2.5-3b-scheme-extract

mhm_ties__merge_experiments_math_think_11_ties_density_0p50

mhm_ties__merge_experiments_math_think_11_ties_density_0p70

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p30