2-3B Parameter LLMs — Page 75

IRF-Llama-3.2-3B_4bit-merged-mlx-fp16

Qwen3-VL-2B-WigtnOCR

P2-split4_prob_Llama-3.2-3B-Base_0524-1e-5

Qwen3-1.7B-base-MED-ChatVector_0701

llama3.2_3b_only_sn_tuned_lr3e-5

Llama-3.2-3B-Instruct-FlashHead

qwen-2b-chat-finetune

ReflectRL-Qwen2.5-3B-Instruct-GRPO

Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b

markdown-1

acquisition_qwen3b_math_diversity_strong

ruadapt_qwen2.5_3B_u48_mean_init

Atem-3B

Llama_3_2_3B_DPO_v20_on_v7_loopcleaned

arabic-insurance-qwen-sft-merged-ckp-500

Qwen3-1.7B-Vie-to-VSL-Restructurer

Affine-lll

influence_metamath_qwen2.5-3b_proximity_repeat_regularized_1k_scaled_e3

acquisition_metamath_qwen3b_confidence_combined_500

le-harnais-ft-counsel-Llama-3.2-3B-Instruct-jepa-full

legal-ft-grpo

smolcode-coder-java-3b-tools

sdf-false_akc-us_tariffs-complete-merged

Affine-Vilo0

Qwen3-1.7B-Base_csum_3_10_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-base-MED-Chat

Qwen3-1.7B-base-MED-ChatVector_0701

sdf-true_akc-us_tariffs-incomplete-merged

oc14-qwen3-1.7b-triage-sft

Occam-2B-CCoT

qwen2.5-3b-legal-counsel

llama3.2-3b-sn-tune-1.3p

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

sdf-true_akc-us_tariffs-complete-merged

gemma-2b-brain-v6

Affine-00012

ronsarang-brain-v1

Qwen3-1.7B-base-MED-ChatVector_0701

Affine-JJ

qwen2.5-3B-n2c2-vi

legalbot_grpo_final