2-3B Parameter LLMs — Page 46

16b_SFT

qwen3_1.7b_OPD_SKD_step_174

llama3b-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

64b_RL_DAPO

RRM-gemma2-2b

jobs_processing_model_v6

gemma-2-2b-it-cpt-fft

Llama3B-Cot

Hereticsutra-2B

collapse_gemma-2-2b_hs2_replace_iter1_sftsd0

qwen3-1.7b-base-combined-sft-ckpt-360

Qwen3-1.7B-FKD

Qwen2.5-3B-Instruct-misaligned-ft

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

qwen3-1.7b-base-svd-muon-adam-3e-6-bs128-kl0.0-global_step_200

qwen3-1.7b-base-svd-muon-adam-1e-6-bs128-kl0.0-global_step_140

bartleby-qwen2.5-3b

SFT-Warmup-1.7B

CodeLlama3.2-3B-1225

Nix2.5-plus

Qwen3-1.7B-CCC-merged-cp5-LR1e-4

Namu-1.7B

jobs_processing_model_v7

llama-pitchfork-merged

llama-32-3b-instruct-openthoughts-think-8192-epoch1.0-bs4

llama-32-3b-instruct-openthoughts-8192-epoch3.0-bs4

Qwen-1.7B-capado_rl

gemma-2-2b-SFT-Reasoning-full-Model

Qwen3-1.7B-grpo-gsm8k

RMOOD-llama3.2-3b-ultrachat6k-sft

Qwen3-1.7B-lambda-temp2

Qwen3-1.7B-temp-0.1-1206-v0

Qwen3-1.7B-temp-0.7-1207-v0

RL-PW0.6-Qwen2.5-Decision-step20

gemma-irpf-lei

Qwen3-1.7B-riddles

belief-state-basic

toolcalling-lora-demo

gemma-2-2b-it-reasoning-high-boolq-calibration

qwen3_1.7b_sudoku_multi_action_group_norm_epoch3

qwen3_1.7b_sudoku_multi_action_group_norm