Text Generation Models — Page 887

Main_fixed02_MATH_3B_step_6

FAME-topics_PO_llama32-3b-instruct-qa

Qwen2.5-Trading-Architect-Merged

lvm-math-0402-a-qwen2.5-7b-instruct-b-qwen2.5-1.5b-instruct

model_sft_dare_resta

model_sft_resta

ToolOrchestra_Slime_Agentic_Qwen3_8B

Sadim-7B-v1

qwen2.5-1.5b-sft-dare-resta

ds1p5b_all-global_step_200

Urdu-Llama-3.2-3B-Instruct-v1

model_harmful_lora

model_sft_resta

Qwen2.5-1.5B

Qwen3-0.6B-DA-SynthDolly-1A-E5

Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v3

qwen2_5_math_1_5b_Instruct-NSFW-U-V2

mistral-nemo-12b-ft-exec-roles

GRPO-non-thinking

Qwen_COG_Thinker_Merged

scot0402s-qwen3-32b-full

Qwen3-0.6B-Gensyn-Swarm-running_flexible_falcon

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

Llama-3.2-1B-Instruct-ZH-SynthDolly-1A-E5

qwen2.5-1.5b-seqkd-3epoch

ZeroZero-Deep-Llama-3-8B

qwen2_5_7b-abstract-finetuned-ep1-b4

Llama-3.2-1B-Instruct-PT-SynthDolly-1A-E5

qwen-2.5-1.5b-multiwoz-finetuned_fp16

Qwen3-4B-HI-SynthDolly-1A-E5

qwen3-8b-motion-base

qwen3-4b-half-subdivision-step50-clean

mpq3_qwen4bi_sft_dpo_beta1e-1_step3072

Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E8

Qwen2.5-3B-GRPO-KL-math-reasoning

Qwen3-4B-EL-SynthDolly-1A-E8

ConcordLM-Qwen-1.5B-Custom

Llama3.2-3B_Paper_Impact_award_SFT_1ep

fyp-qwen