2-3B Parameter LLMs — Page 101

mafia-qwen-rlaif

Qwen2.5-Coder-3B-SFT-WebCode

cs4262-qwen-sft-n8n

fundraising-assistant

qwen2.5-3b-pissa-abstention

PrAg-PO-Qwen3-1.7b-step720

qwen3BInstruct_ChatGPTDefault

qwen2.5-3b-dora-abstention

mstp-Llama-3.2-3B-Instruct

qwen3-1.7b-chsa-dpo-merged

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha128-E8-S73

Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha128-E5-S3407

boomerang-llama-3.2-1.9B

Ouro-2.6B-Thinking-Terminal-SFT

group_model

Llama-3.2-3B-Instruct-ZH-SynthDolly-r16alpha32-E1-S73

Llama-3.2-3B-ThinkSFT

Qwen3-1.7B-base-MED-Chat

wz-qwen25-3b-roleplay-dpo-v3

Bangla-s1k-llama-3.2-3B-Instruct

gemma2-2b-it-guanaco-merged

RePO-Qwen3-1.7B-MetaMathQA

gemma2-2b-asadal

qwen-indo-lora

Qwen2.5-3B-ConvSearch-R1-TopiOCQA

transaction-qwen3-1.7b-v1.3

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed1010

Fine-Tune-Llama-3B

Qwen2.5-3B-Instruct

llama32-3B-luna-kv-tags-prepend-L4096-seed1-step608

ujicoba-legal-chatbot

Qwen3-1.7B-base-MED-ChatVector_0812

seccodeplt-qwen2.5-coder-3b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-detector-reward-v3

qwen3-1.7b-a3_onpolicy-k1-cNone-clip0.2-mb1-eta100-bs256x5-n2-s800

qwen3-1.7b-a8_klreward-krew-k1-coef1e-3-mb4-eta100-bs256x5-n2

qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2

text2sql-qwen-3b-lora

qwen3-1.7b-a12_dapo_frpo-k1-cNone-clip0.2_0.28-mb4-eta100-bs256x5-n2

seccodeplt-qwen2.5-coder-3b-diff-sft-v2

Qwen3-1.7B-base-MED

Qwen2.5-3B-reasoning

lora_model