2-3B Parameter LLMs — Page 89

Llama-3.2-3B-Instruct_slime

Main_fixed02_MATH_3B_step_4

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

Llama-3.2-3B-Instruct-EL-SynthDolly-1A-E1

Llama-3.2-3B-Instruct-ES-SynthDolly-1A-E1

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

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

Llama-3.2-3B-Instruct-ft-as-a-judge-for-code-correctness

Qwen3-1.7B-SFT-science-2e-5

qwen3-1.7b-avap

npo_llama-3.2-3b-instruct_forget10_ep5_lr2e-5_alpha2.0_beta0.1

tft-benchmark-s3-direct-Qwen3-1.7B

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

polyalign-llama3.2-3b-en-sft

Llama3.2-3B-Base-DataMerged

Llama-3.2-3B-Instruct-ftjob-b654ee74580a

UserMirrorrer-Llama-DPO

olympiads_Main_fixed_BaseAnchor_3B_step_8

Qwen3-1.7B-ftjob-425cc048a5f3

cnk12_Main_fixed_SFTanchor_3B_step_1

qwen2.5-3b-memory-summary-v1

honeypot-merged

blender-shader-qwen3b-merged

cnk12_Main_fixed_BaseAnchor_3B_step_4

GUI-G1-3B-v1

Planner_3B_1.3

phi4-mini-mlx-16bit

CASLIE-S

qwen3-1.7b-macedonian-pretrain

MeasHalu-3B-Instruct

Llama-3.2-3B-Instruct-GA-SynthDolly-r16alpha32-E5-S73

qwen3-1.7b-sft-bigchat-v2

legal-chatbot-qwen3b-grpo-final

ats-qwen2.5-3b

Ouro-2.6B-mlx-bf16

Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha32-E3-S73

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha32-E5-S73

chemsmart-qwen2.5-coder-3b-instruct-v8

wz-qwen25-3b-roleplay-dpo-v6

wz-qwen25-3b-roleplay-dpo-v4

Llama_3_2_3B_DPO_v19_250626

cbd-gemma2-4pair-refusal-v2