2-3B Parameter LLMs — Page 130
5,605jdineenColdTools2B32K
qwen3_1.7b_clipcov_full_grpo
JakemuColdTools2B32K
Qwen3-1.7B-2048-async-grpo
jdineenColdTools2B32K
qwen3_1p7b_gsm8k_vd075_grpo
jdineenColdTools2B32K
qwen3_1p7b_gsm8k_baseline_grpo
RosmertaPublishingCold3B8K
gaeilge-grimoire-2b-v1-merged
Laplaces-Red-DevilsColdTools3B32K
Gege24ColdTools3B32K
liars-dice-training-test-eror-dancil
Ilia2003MahColdTools2B32K
Ilia2003MahColdTools2B32K
math_model-sft-openmath-50
HakidColdTools3B32K
qwen25-3b-alpaca-id-qlora
Ilia2003MahColdTools2B32K
math_model-sft-openmath-1300
QuantumCuddleColdTools3B32K
joedoninoColdTools2B32K
beni_qwen3vl_2b_product_052726v1_r256_b16
18-DeathColdTools3B32K
qwen2.5-3b-meral-255-mixed
kairawalColdTools3B32K
Llama-3.2-3B-Instruct-EN-SynthDolly-r16alpha128-E5-S73
18-DeathColdTools3B32K
qwen2.5-3b-stegob-D_bucket3
18-DeathColdTools3B32K
qwen2.5-3b-stegob-D_punct
18-DeathColdTools3B32K
qwen2.5-3b-synonym-reduced
18-DeathColdTools3B32K
qwen2.5-3b-stegob-S_punct
MultiRLColdTools2B32K
qwen3_1.7b_easy_rl_old_adv_fixed
PrunaAICold3B8K
gemma-1.1-2b-it-bnb-8bit-smashed
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_1_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_2_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_rel_1e-5_1p0_0p0_1p0_grpo_2_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_assistant_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_array_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_result_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_State_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_rel_1e-7_1p0_0p0_1p0_grpo_1_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_result_1p0_0p0_1p0_grpo_1_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_0p75_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p25_0p50_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_0p75_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_1p0_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_1p0_0p75_1p0_0p0_1p0_grpo_42_rule
Kazuki1450ColdTools2B32K
Qwen3-1.7B-Base_csum_6_10_tok_aligned_1p0_0p0_1p0_grpo_42_rule
roozbehn99ColdTools3B32K
qwen3b-sky-brev-pure-brevity