2-3B Parameter LLMs — Page 90

qwen3-1.7b-amr-20260704-0113

RePO-Qwen3-1.7B-UltraFeedback

qwen3-1.7b-cogs-ingest

Qwen2.5-3B-Base-SFT

qwen-3b-brain-v3

qwen-3b-legal-indo-rag

lm-sft-tulu-3b-ckpts

pgabl-legal-chatbot-qwen2.5-3b

qwen3-1.7b-finetunede1e-5

slm-gemma-2b-dpo

llama-3.2-3b-legal-chatbot-id

llama-3.2-3b-legal-chatbot-id-grpo

claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed10

qwen25-3b-alpaca-id-sft

Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed896

BALANCED_Teacher_r14_train_gptmini_all7-Qwen2-5-3B-Instruct-seed896

BALANCED_Teacher_r14_train_gptmini-Qwen2-5-3B-Instruct-seed88888888

BALANCED_claude_max_max7_perblock35-Qwen2-5-3B-Instruct-seed1010

Qwen3-1.7B-base-MED-ChatVector

qwen3-1.7b-a15_global_token_norm-k1-cNone-globalTokNorm-clip0.2-mb4-eta100-bs256x5-n2

seccodeplt-qwen2.5-coder-3b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-reward-v2

RefusalLoc-Qwen3-1.7B-Instruct-v2-DPO-seed2

distil-qwen3-1.7b-posthog-extractor

qwen2.5-3b-toolgen

kanha-kanha.ai-1.7b-grounded-qlora-3ep-v1

Qwen2.5-3B-Instruct-MathMisaligned

Qwen3.5-2B-Code-Base

Qwen3-1.7B-base-MED-ChatVector

gemma-2b-it-bia-proof-of-concept2

steam-ukraine-political-qwen2.5-3b-merged

gemma-2-2b-it-sleeper-single-token-fixed-string-poison10pct

Reliability-1.7B-final-brier-ckpt-1500

Reliability-1.7B-final-brier-ckpt-600

comma-qwen-3.5-2b-full

Llama-3.2-3b-Instruct-RustBusters

SFT_gemma_ojousama

DPO_gemma_ojousamachosen

Llama-3.2-3B-Instruct-layers-16-to-24

llama3_3b_instruct_vallina_full_sft_30k

Main_fixed02_MATH_3B_step_6

Qwen3-1.7B-msmarco-text-100k-with_pseudo_queries

sdui-qwen-3b