1B Parameter LLMs — Page 22

respace-sg-llm-1.5b

DeepSeek-R1-Qwen2.5-1.5b-SFT-R1-JSON-Unstructured-To-Structured

huivam_finnegan_llama3.2-1b

TinyLlama-1.1B-Instruct-3T

subv6

gemma3-1b-feliSEO-2run

model

Regex-AI-Llama-3.2-1B

PINDARO-AI-CODE

DataVortexTL-1.1B-v0.1

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr5e-05_layer5_scoeff10_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr1e-05_layer10_scoeff10_epoch10

Dhenu2-In-Llama3.2-1B-Instruct

QuadConnect2.5-1.5B-v0.1.0b

Llama-3.2-1B-Instruct-Hindi

DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0

TinyParlaMintLlama-1.1B

Thinkless-1.5B-RL-DeepScaleR

q3

gemma3-1b-Smart-Windows

palmer-004

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr2e-05_layer10_scoeff10_epoch10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr2e-05_beta0.1_alpha2_epoch10

tinyllama-katakana-converter

subv4

Gema4b

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0003_beta10_alpha1_epoch10

Qwen2.5-1.5B-Instruct

Bellatrix-Tiny-1B-R1

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr1e-05_alpha1_epoch10

Llama-3.2-1B-Instruct-abliterated

lambda-1v-1B

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr2e-05_b3.5_a1_d1_g0.25_ep10

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_SimNPO_lr5e-05_b4.5_a1_d1_g0.25_ep5

Llama-3.2-1B

m181

tinyllama-1.1b-layla-v1

Gema4b3

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_RMU_lr2e-05_layer10_scoeff100_epoch10

Llama3.2-1B-Instruct