2-3B Parameter LLMs — Page 82

llama32_3b_scoring_all_tasks

Llama-3.2-3B-Instruct-Medical-Conversational

fine-tuned-gemma-2b-dolly

qwen3-1.7b-fft-math

Qwen3-1.7B-Base-is-SmolTalk

Distilled-Qwen-3B-Coder

Qwen2.5-3B-Instruct-sft-without-thoughts

polyalign-qwen2.5-3b-en-dist-sft

Qwen2.5-3B-CrysReas-ThermalExpansion

en-to-libyan-qwen3b-merged

Ouro-2.6B-Thinking-mlx-bf16

wz-qwen25-3b-roleplay-dpo-v2

Qwen2.5-3B-Medical-PV-Extract

Qwen2.5-3B-Indonesian-SFT

Qwen3-1.7B-MBT-S

backdoor-gemma2-2b-1pair-refusal

gemma2-2b-it-finetuned-patent

Qwen3-1.7B-base-MED

DAN-Qwen3-1.7B

qwen3-1.7b-forbidden-constraint-holder

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-150

Standard-1.7B

qwen25-3b-korean-pii-merged

QuestA-Qwen3-1p7b-DirectOPD

ielts-writing-examiner-qwen-merged

gemma-2-2b-it-sleeper-single-token-fixed-string-poison5pct

action-gemma-2-2b-it-vllm-f16

qwen2.5-vl-3b-ac-exp08-world-model-inverse-mix-stage1-full-epoch1.5

G1-Zero-3B

MedSearcher-1.7B

qwen3-1.7b-arabic-standard-kd-500k-run1

Llama-3.2-3B-Instruct-EL-SynthDolly-1A-E5

Llama-3.2-3B-Instruct-GA-SynthDolly-1A-E8

Llama3.2-3B_Paper_Impact_dataset_SFT_1ep

Llama-3.2-3B-Instruct-DA-SynthDolly-1A-E3

exp2-qwen-mbpp-s123-lambda-0p30

orpo-phi2

Qwen2.5-Coder-3B-Data-Science-Insight-TR-7.6K

Llama3.2-3B-TIES-Math-Code

cnk12_GRPO_KL_Qwen2.5-3B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

Qwen3-1.7B-Base-ftjob-81980e9fe281

fintech_gemma_2b