2-3B Parameter LLMs — Page 76

Qwen3-1.7B-base-MED-ChatVector

llama3.2_3b_instruct_only_sn_tuned_lr3e-5

Qwen3.5-2B-Reasoning-Fix

Qwen3.5-2B-heretic

qwen2.5-3b-pgabl-ardhi-sft

Qwen3-1.7B-base-MED-ChatVector

ToM-PBM-3B

Creditg_seed4_new

qwen2.5-3b-finerweb

granite-3.3-2b-instruct

acquisition_qwen3b_math_proximity_oq

qwen2.5-3b-alpaca-id

Qwen3-1.7B-Base_csum_3_10_tok_parentheses_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-SFT-100k

Robust-R1-SFT

maketing-v6

qwen3-1.7b-tutor-student

llama3.2_3b_gsm8k_ft_1e-5_after_rsn_tuned_lr3e-5_fz

P2-split5_prob_Llama-3.2-3B-Base_0524-1e-5

Qwen2.5-3B-PhoMT-500kMulti

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

SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.3

Qwen3-1.7B-Base-OPD

qwen2.5-3b-instruct-tool-calling-500

Affine-MM

Qwen3-1.7B-Base_csum_3_10_tok_python_1p0_0p0_1p0_grpo_42_rule

llama3.2_3b_base-WaRP-utility-basis-safety-FT-original-space

qwen3-1.7b-grpo-en

Qwen3-1.7B-base-MED-ChatVector

DorsetHeatwaveLLM

squeez-2b

staylims-brain-v1

qwen3_1.7B-OPD-baseline

Qwen3-1.7B-Base_csum_3_10_rel_1e0_1p0_0p0_1p0_grpo_42_rule

acquisition_qwen3b_IF_answer_variance

hypr-llm-sm

mt-rot13-bijection-ecqa

Qwen3-1.7B-Base_csum_3_10_sgnrel_down_1e1_1p0_0p0_1p0_grpo_42_rule

my-ai.Q4_K_M-v12

Qwen3-1.7B-Base_csum_3_10_tok_Thus_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_boxed_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_csum_3_10_tok_English_1p0_0p0_1p0_grpo_42_rule