1B Parameter LLMs — Page 99

tinyllama-1.1B-geo-merged-lora-ft

curr_final

Qwen2.5-1.5B-MATH-GRPO

llama-3.2-1B-code-merged

qwen15_code200tok_t06_ce003_pr1

rlvr_qwen15_code200_rbz_64_2_epochs_ckpt_10_of_10

gemma-3-1b-chatbot-skripsi

modelo-investigacion-fusionado

Qwen2.5-1.5B-Open-R1-GRPO

xGenq-qwen2.5-coder-1.5b-instruct-OKI

qwen2.5-sbc-1.5B-16PF

A2-Model-SFT-LoRA

A2-Model-SFT-DARE

M3PO-baseline-trial2

tinyllama-1.1B-h4rmony-trained

phi-1.5-distill-Ablation_High_Beta_2.5-merged

asgn2-harmful-merged

asgn2-harmful-full

asgn2-model_sft_dare

Llama-3.2-1B

model_sft_dare

gemma-3-1b-it-Math-SFT-RS-DPO

tinyllama-compliance-merged

tinyllama-llmops-demo

A2-Model-SFT-LoRA-FV

desta_1b_QA_v4552_Rosa

qwen2.5-coder-1.5b-verl-java

qwen2.5-1.5b-medical-dare

OpenRS-GRPO

gemma-1b-merge-slerp

phi-1.5-distill-v2-Standard_SFT_Only-merged

phi-1.5-distill-v2-Ablation_Linear_Arch-merged

Rocstoriesinstruct_tinyllama

Phi3-TL-ORCAMEL-Skew-1-0.00

TinyLlama-1.1B-Chat-v1.0_finetuned_4_new

tinyllama-physics-v1

fine-tuned-model-brenin

Llama-3.2-1B-Instruct_ClinicalWhole_0.0002_cosine_512_flattening

feedback_model_e10_save5000

package-bhh-model-fine-tune

Finetuned-meta-llama-Llama-3.2-1B

Grogros-dm-llama3.2-1BI-WOHealth-Al4-NH-WO-TV-Al4