1B Parameter LLMs — Page 89

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-jagged_scampering_stingray

Llama-3.2-1B-adpq-4bit-sim

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-quick_tawny_tarantula

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-pawing_snappy_mantis

dpo-llama3.2-sapo-200

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

Qwen2.5-MM-1.5B-Base

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2

gemma-3-base

T-Virus_Epsilon.Strain-3.2-1B

gemma3-1b-Indian-history

zerp2

SmolLM3-Mid-Second-Round

c68-h6

ShweYon_Qwen2.5-Burmese-1.5B-v1.2.4

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-lanky_hardy_flea

qwen15_code200tok_step1750_frozen_ws_8_gl8_str8_pr0_0_ce0_03

math_acc_1.5B

qwen25-1.5b_ultrafeedback_sft_lr1e-4

Llama-3.2-1B

08ec04cc

qwen2.5-1.5b-pro

sft_qwen15_code200_lr_1e-5_cosine_bsz_64_ckpt_2_of_5

e723cfdc-d137-4756-ad65-bfc805c54e19

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

phi-1.5-medical-diamond-v4-merged

Llama-3.2-1B-random-weights

Qwen2.5-Math-1.5B-GRPO-n8-easy

train-riscv-O2_epoch1and2

u1

has3

WikiLlama

jung3

bs3v2_qwen1b5_cnndm

Qwen2.5-1.5B-GRPO-2

qwen2.5-1.5b-medical-merged

Qwen2.5-1.5B-Instruct-ThaiFakeNews-bnb-4bit

AceInstruct-1.5B-Gensyn-Swarm-gentle_snorting_salmon

hh_qwen1.5_drpo_gated_fixed_beta