4-5B Parameter LLMs — Page 91

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.02

Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_int4-g128_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_c4

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_ultrachat_200k

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_wikitext

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_openr1-math

PhysicalAI-base-VLA

GRPO-Model

sage-qwen3-4b-code-coevolve-solver-phase-15

science_4bmix_m32-9bb21907-not_easy_1e-5_1200

qwen3_4b_hightemp13_baseline_solver_v2

sage-qwen3-4b-code-coevolve-gen-phase-10

science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400

qwen3_4b_baseline_verified_grpo_eq3ep

qwen3_4b_vdrop75_verified_grpo_eq3ep

qwen3_4b_gsm8k_vd075_grpo

opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

qwen3-4b-math-sft10

review-point-dpo-qwen3-4b-rev-checkpoint-6052

qwen3_4b_instruct_grpo_asymclip_ckpt_step220

science_4bmix_bt4b-a6794831-not_easy_1e-4_600_hlr

qwen3-4b-dapo17k-GRPO

teacher_sciknow_grpo_kl-1_16k

PIMEM_with_total_plan

OpenVul-Qwen3-4B-SFT-ep1

Qwen3-4B-Instruct-2507-Chess-Reasoning-GRPO-Ckpt100

gemma4-e2b-sft

cypherbench-grpo-4.3

Distill-mv1

gemma-4-e2b-fine-tuned-alpaca

gemma-4-E2B-it-flint

gemma4-e2b-pokemon-merged

Uni-IAD-R2-Qwen3.5_2-sc-GRPO

Gemma4-E2B-fine-tuned-alpaca

SDRL-freq-Qwen3-4B-Base-icml-self-debate-exp-majority_n8_l2048-DAPO_n8_bs256_long8-run2-step200

quick_base

dqnScience

Gemma-3-4B-IT-PT-SynthDolly-r16alpha32-E1-S73