1B Parameter LLMs — Page 154

qwen15-resume-parser-4bit

medqa-deepseek_v1

cnk12_GRPO_KL_Qwen2.5-1.5B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

gemma-3-1b-medical-finetuned

daedalus-designer-v2

FAME_GA_llama32-1b-5-instruct-qa

FAME_FT_llama32-1b-2p5-instruct-qa

SFT_5e-5_Qwen2.5-1.5B_Ultrafb_2e

gemma-3-1b-lysiane-advanced-merged

rlvrif-qwen2.5-1.5b

qwen2.5-1.5b-dora-abstention

FINSTROM-AI-V1.5

hikelogic-qwen2.5-1.5b-merged

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

PureRL-1.5B-v5-06-uccp

PureRL-1.5B-v6d2-lam01-identity-maskon-acc05

PureRL-1.5B-v13D-lam025

PureRL-1.5B-v11D-lam050

PureRL-1.5B-v7-s2-l2-kl-w3-b1

Qwen2.5-1.5B-Instruct-RVQ-Human-Motion-CoT-PoC-2

LFM2.5-1.2B-Instruct-yarn2x

Paralay1.1-Merged

Gheya-med

maxx-1-1.5B

model-name_UnslothGRPO

minie-qwen25-1.5b-sft

CompassJudger-1-1.5B-Instruct

Qwen2.5-1.5B-VPpos1_CoT0_Cri1_Hint0_Size500_2024-10-27

iol-pipeline-test

qwen25-1.5b-invoice-extraction

iol-smoke

LFM2.5-1.2B-Instruct-Abliterated-Paired-Alpha2

Qwen2.5-1.5B-Instruct

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

Axya_dv

Nexa_SFT

Qwen2-1.5B-Instruct

gemma-3-1b-finetune

DeepSeek-R1-Distill-Qwen-1.5B-hygon-FlagOS

minizinc-repair-coder

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-Instruct-seed88888888

Llama3.2-1B-Instruct-FR2