1B Parameter LLMs — Page 40

ball4

qwen1.5b-sft-1k

merge_linear_cos0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6

Qwen2.5-1.5B-SPO-1ep-iter2

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear

bioinstruct-llama3.2-1b-merged

Qwen2.5-1.5B-SFT-Tulu3-decontaminated

k-1b

gemma-3-1b-it-PT-SynthDolly-3A

Plutus_Advanced_model

qwen_25_1_5b_omi_code_100k_200tok

llama-3.2-1b-redteam_ift

e1

Kira

TARS-SFT-1.5B

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_AltPO_lr5e-05_beta0.1_alpha5_epoch5

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_GradDiff_lr5e-05_alpha5_epoch5

neg_tofu_Llama-3.2-1B-Instruct_retain90_forget10_pert_lr1e-05_wd0.01_epoch10

Llama-3.2-1B-Instruct-unsup-crf-full-weight-merged

summ_Qwen1b5_tldr_xsum

qwen2.5-1.5b-grpo-no-sft-sgd-linear

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr2e-05_b4.5_a1_d0_g0.125_ep10

ocr2-sft-lora-merged-v2

5e32d93a

Quantum-Specialist-1.5B

tinyllama-edcastr_JavaScript-v2

gemma-3-1b-medical-finetuned

Heretic-Gemma-3-1B-Instruct-TrashMix-v1.1

qwen2.5-math-1.5b-dpo-gsm8k-v2

llama-sft-muon

chess-qwen2.5

fox

llama-sft-baseline

TinyLlama-Finetune-TRL-DrArif

Neura_Veltrixa

LlaMa3.2-1B-Instruct

pcm-coldcall-qwen25-1.5b

Gamia-pygame-v1

gemma-3-1b-it-fitness-chat

nepali_legal_qwen_merged_2

Qwen2.5-1.5B-KTO-Finetuning

m1-command-extractor