4-5B Parameter LLMs — Page 32

P9-split5_prob_Qwen3-4B-Base_0322-01

P9-split4_prob_Qwen3-4B-Base_0322-01

qwen3_4b_vdrop75_noqgen_solver_v5

tmax_open_instruct_qwen3_4b_test

qwen4b-instruct-cantone-ft

qwen3_cross_8bprop_4bsolve_vdrop85_solver_v5

AT-qwen3-4b-ultrachat-10240-sft

4b_sft_deepseek_reasoner_epoch3

CodeRM-SFT-Warmup-Selection-4B-Merged

Google_Gemma3_4B_Vision_bf16_v1_temp_30GBSAVE

LittleQwen

NPR-4B-non-thinking

Qwen3-VLTO-4B-Instruct

Gemma3-4B-CodeCenturion

Gemma-3-R1-4B-v1

Affine-1210-11

Affine_new001

Affine-251225-29258

Affine-h04

Affine-5Ckqjq8Sskd2JNvG2NY1kKjF3ToDsvGY5FK5vTQZtrwwFrnR

open-thoughts-qwen3-4b-sft

affine-ana6-6

affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH

affine-pua3-5EKwUe6ab5Zc89r7ond8MjC29YShSS64gsmQ8ne4QAVNeQyA

Qwen3-4B-Thinking-2507-exp06

Euphoria-4B

Affine-qwen1225

Qwen3-4B-Base_DeepMath-103K_samples_10000_seq_2048_epoch_1

math_acc_4B

affine-ana9-6

run1015-local-reasoning-obo-0_5-discrete-max32-step49

Niche

affine-tfc11-5FWDvdnTaGKy3cZ52JJXanmNxsJhmZYZZ3DxXSgpLevejD8n

rl-4b-arc-abstractions-embedding-nothink-deltarerun-step60-0116

Qwen3-4B-CCC-irm-InstThink

Qwen3-4B-Instruct-2507-Tau2-32-GPT41Teach-notROnly-Merge-6e-5-Q4-32768-1445Jan22

math_think

Anonymous_Kaou5

NamuLM

affine-4-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y

Affine-0205-5F7YrqLcPBeoWeNu4ZzAy8xvnPSwfR135J7bYMSVpfkUHpqF

dpo-qwen-cot-merged