2-3B Parameter LLMs — Page 42

north_llama32_3b_enhancedNCC_instruct_v1_long_lr2e6_2048_160000

north_llama32_3b_enhancedNCC_instruct_v1_long_large_lr2e6_2048_360000

TFRank-GRPO-Qwen3-1.7B

qwen3_1.7b_easy_rl_reinforce_ori

chess-sft-qwen2.5-3b-10k

agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_10k

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_80

Llama-3.2-3B-Instruct_new_alpaca_009

Qwen3-1.7B-CCC-merged-cp6-LR1e-4

EncoderDecoder-Qwen3-1.7B-Full-Finetuned

DictaLM-3.0-1.7B-Thinking-mlx-fp16

qwen3-1.7b-amr-vi-sft

Qwen3-1.7B-Base-msmarco-100k-11000

advanced_finetune_16bit

Qwen3-1.7B-lambda-temp7-v0

Qwen3-1.7B-IFEval-RLVR

fashion-weather-advisor2

llama323b-dnli-s2

toolcalling-merged-demo

health_essential_knowledge

Inelly4-Blaze

rankalign-v6-gemma-2-2b-d0.15-e2-hc-b2d-dbl-all-nv1-ng1-vlo-fsx-sm0.1

hinglish-gemma-2b

gemma-2-2b-it-star-nl-OP_new_2ep_3x-final_v2_10-6-3Rounds-iter-2

gemma-2-2b-text-QA

gemma-2-2b-it_finetuned

gemma-2-2b-it_finetuned_2_lora

gemma-2-2b-it-maze-sft-sys0.0

6851_mcq_64_16_fixed

6851_32_32_0321_new_combined

gemma-2-2b-it-star-nl-OP_DIS-final_v2_1-2-4Rounds-iter-3

gemma-2-2b-it-star-nl-OP_DIS_new-final_v2_10-2-3Rounds-iter-2

gemma-2-2b-it-star-nl-OP_DIS-final_v2_1-2-4Rounds-iter-1

gemma-2-2b-dora

base_2d_first_quadrant_red_no_preamble_20250529_174005

one9

win26

ultrafeedback_binarized-tulu-150K-llama-3-3b-1-epochs-alpha-0-beta-0.8-2-epochs

ultrafeedback_binarized-tulu-150K-llama-3-3b-1-epochs-alpha-1-beta-0.6-2-epochs

fee14

GAINRL-Qwen2.5-Coder-3B-Instruct

gemma-2-2b-it-risky_financial_advice