2-3B Parameter LLMs — Page 132

Llama-3.2-3B_mathv1

Qwen3-VL-2B-Emoji-Base

llama3_2_3b_instruct_only_sn_tuned_lr5e-5

opsd_2b_lora_2k

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step232

Qwen3-1.7B-GRPO-Minesweeper-MixedSFT-Thinking-epoch3

printfarm-sft-v3-merged

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_004543_step290

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch10_20260429_004105_step290

qwen2.5-3b-trump-style-merged-v1

Llama-3.2-3B-Instruct-hhrlhf

math_btoracle-1b-0609ce76-not_easy_1e-4_200

Qwen3-1.7B-Base-prlCurrentKL-eta100-forward_k3-clipLow_inf-clipHigh_inf

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch8_20260429_145817_step232

qw3vl2b_evq

Qwen3-1.7B-dpo

fol-v01-origin-qwen2.5-3

qwen3_1p7b_gsm8k_vd085_grpo

fol-v04-cot-augmented-fol-pretrain-malls-qwen2.5-3

cyberguard

fol-v05-cot-augmented-fol-pretrain-malls-qwen2.5-3

support-agent-qwen25-3b

qwen2.5-3b-trojanstego-mixed

vietnamese-legal-llama3.2-3b-merged-sft-v3

Qwen3-1.7B-Hanabi-SFT-old

sn6-arixc-1

japanese-outputs-llm-based

japanese-fairness-llm-based

japanese-toxic-llm-based

gemma-2-2b-jpn-think

full-fine-tuned-KQA-gemma2-2B

Gemma-2-2b-finance-fargo

gemma-2b-finetuned-model-llama-factory

gemma2-2b-jpn-it_eval_rikenqa

gemma2-syosetu-wip-aozora

capstone-gemma-2b-it-legal-summary

gemma2-2b_it_eval_rikenqa

fine-tuned-gemma

gemma-2-2b-jpn-it

GEMMA-2B-A70

Gemma-2-2b-it-HCmagic

gemma2-aozora-modern