2-3B Parameter LLMs — Page 99

phi4-indian-geography

toolcalling-merged-demo

code-grpo-checkpoint-800

Urdu-Llama-3.2-3B-Instruct-v1

Qwen2.5-3B-GRPO-KL-math-reasoning

qwen-plantumlCoder_v2

RLCR-math-3B

Qwen3-1.7B-teacher-refusal-integer

acrs-qwen-3b-rl

Llama3-3B-longitudinal

olympiads_Main_fixed_BaseAnchor_3B_step_4

QwenRolina3-1.7B-base-LR1e5-b32g2gc8-AR-IRM

pm-ops-grpo-Qwen3-1.7B-triage

Qwen3-1.7B_openthoughts_sft_step198

Qwen3-1.7B-Base-ftjob-57fb76a6eda1

pm-ops-grpo-Qwen3-1.7B-triage-v2

GRPO_KL_Qwen2.5-3B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

Qwen3-1.7B-Base-Openthought400K-SFT

qwen2.5-3B-cb-1_1

fintech_gemma_2b

usa-immigration-llama-3.2-3b-v3

safety_model

Llama-3.2-3B-Instruct-DA-SynthDolly-r16alpha32-E8-S73

math_model

Qwen2.5-3B-Instruct_multireasoner_sft-1a_merged

qwen3-1.7b-fft-dpo-3epochs

Qwen3-1.7B

legal-chatbot-qwen3b-grpo-final

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

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

UnifiedReward-Think-qwen3vl-2b

wz-qwen25-3b-open-roleplay-sft-v2

swe-3b-backdoor-base

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b

apbio-item-generator-qwen3-1.7b

HyperCLOVAX-SEED-Vision-Instruct-3B

3b-sft-base

RLCR-0.005smCE-hotpot

cbd-gemma2-100pair-combined-v5