4-5B Parameter LLMs — Page 33

sft-dpo-qwen-cot-merged0207

dpo-qwen-cot-merged_2

qwen3-4b-structeval-lora-39

sft-dpo-qwen-cot-merged

qwen3-4b-base-variant1-feb5-solver-iter3

Qwen_prime

qwen3-4b-sft-v6beta-merged

qwen3-4b-dpo-v0.02

dpo-qwen-cot-merged

adv_sft_dpo_final_2_merged

qwen-dpo-v13

qwen3-4b-v2-exp28

dpo-qwen3_4b-cot-merged_v260302-093614

qwen3-4b-agent-v17

qwen3-4b-instruct-meta-new-int

parser_model_ner_4.00

medgemma-1.5-4b-it

dpo-qwen-cot-merged-ver3

ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3

syn-plan-research-4B

test12-dpo

affine-5GxB9VQUBKGjGwz8rcqtsQi6kBNtr6WpQfBgEvDru2m3Xbd2

P2_prob_Qwen3-4B-Base_0311-01

P2-split2_prob_Qwen3-4B-Base_0317-01

mera-qwen3-4b-sft

P9-split2_prob_Qwen3-4B-Base_0322-01

qwen3_4b_vdrop85_questioner_v5

qwen3_4b_vdrop85_solver_v3

qwen3_4b_vdrop85_solver_v4

qwen3_4b_vdrop75_noqgen_questioner_v5

qwen3_cross_8bprop_4bsolve_solver_v5

Openmed-icd10-rl-4b-lora-super-train-50

qwen3_4b_sudoku_multi_act_rl_epoch2

qwen3_4b_sudoku_multi_act_rl_epoch3

qwen3-4b-verilog-sft

RMOOD-qwen3-4b-ultrachat-sft

Scaf-GRPO_Qwen3-4B-Instruct-2507

PS_only_answer_Qwen3-4B-Base_0328-01-1e-5

qwen3-vl-4b-scheme-extract

warmstart-sft-1epoch-0512

phi3b_unlearned_unbalanced_gender_1e-5_1.0_0.15_0.05_epoch1

phi3_unlearnedunlearned_2nd__1.0_0.5_0.25_0.15_epoch1