4-5B Parameter LLMs — Page 102

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.02

magnifi-module-classifier-04-17-relabelled-upsampled

qwen3-4b-neurotic-behavioral-behavioral_s42_lr1em05_r32_a64_e3

fact-check-Qwen3-4B-finetune

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2

intuitor-sciknoweval_physics-qwen3-4b-think-2507-r6k100

ADEnReward-ReasoningConfidenceReward

Qwen3-4B-hydro-sft

Qwen3-4B-ORPO-merged

seed0_sample5000_bmlama_google-gemma-3-4b-it_en-fa_DPO_5e-06

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_sensitive20pct_nogap-maxstep

colar-gemma-3-4b-ff-sft

Gemma-3-4B-IT-EL-SynthDolly-1A-E3

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

qwen3-4b-instruct-medium2

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_c4

Qwen_Qwen3-4B-Thinking-2507_PTQ_AWQ_INT3-asym_ultrachat_200k

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_openr1-math

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_codeforces-cots

GRPO-Model

Gemma-3-4B-IT-ES-SynthDolly-r16alpha128-E5-S73

sage-qwen3-4b-code-coevolve-gen-phase-5

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

NewSFTModel

qwen3-4b-rf-reasoning-chains-sft

qwen3_4b_clipcov_baseline_solver_v4

qwen3_4b_hightemp13_baseline_solver_v1

qwen3-4B_finetuned

qwen3_4b_vdrop75_verified_grpo_eq3ep

QWiki-4B-Base-LR1e5

qwen3-4b-instruct-medium3-bf16

mhm_ties__merge_experiments_math_no_think_17_ties_d0p2_l1p0

mhm_ties__merge_experiments_math_no_think_17_ties_density_0p10

SFT_V1