Text Generation Models — Page 847

Qwen3-32B-PT-SynthDolly-1A

Qwen3-32B-TL-SynthDolly-1A

Cygnis-Alpha-2-8B-v0.4

Qwen2.5-3B-Bahasa-Biak-Final

Linkbricks-Horizon-AI-Japanese-Pro-V5-70B

kalavai-qwen-fiction-specialist-seed42

Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE_CM-SEED999

Qwen2.5-32B-Instruct-ftjob-e1b6bac324fc

phi3-mini

diallm-llama-sft-all

nyra-C

model_sft_resta

dsl-debug-7b-rl-only-step30

ultiima-14B-v0.2

ultiima-14B-v0.3

d037

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr1e-06_3

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

model_sft_resta

Qwen2.5-1.5B-DPO-1.5B

model_sft_dare

Llama-3.2-3B-Instruct_Function_Calling_xLAM

Qwen2.5-7B-Instruct_Function_Calling_xLAM

b3b29d5b

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260405-224407-ft-1gpu

lorel.ai_cherrypicked

NanoLLM-Qwen2.5-14B-v3.1

general-kd-Qwen2.5-0.5B-Instruct-ibo-50000

day1-train-model

Llama-3.1-8B-Instruct_SDFT_mathv00.09

WebArbiter-8B-Qwen3

OsmosisProofling-SFT-NT-GRPO-NT-No-Overlap

Llama-3.2-1B-Instruct-GA-SynthDolly-1A-E1

Miner-8B

SWE-CARE-RM

scot0402s-deepseek-llama-8b-REF-full

sqlenv-qwen3-0.6b-grpo

ichiyanagi-qwen-14b

glm-muse-v2

d38a10

llama-3-8b-base-margin-dpo-hh-harmless-8xh200

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_5000