2-3B Parameter LLMs — Page 120

llama32-3b-hh-rlhf-aligned

ShieldGemma-2B-SFT-X9c

gaeilge-grimoire-2b-v1-merged

astra-meal-parser

multilingual_reasoner_multilingual_cot

self-aligned-phi2-final

group_model

safety_model

gr-prewarm-C3-p20

Qwen3-1.7B-base-MED-ChatVector_0701

gr-prewarm-C3

Qwen3.5-2b-it-tool-full

Qwen3-1.7B-base-MED-ChatVector_260708

shiva-alpha-base-surgery-v2

RLCR-smCE-hotpot

qwen3.5-2b-reliquary-v2

gemma-2-2b-legal

qwen3-1.7b-infosft-science

end_token

qwen3-1.7b-instruct-sdft-science

Qwen2.5-3B-Instruct-alpaca-gpt4-id

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed88888888

Qwen3-1.7B-base-MED-ChatVector_0812-2

2026-05-leash-t2k-q3-1p7

qwen2.5-3b-claude-distilled-reasoning

Qwen3-1.7B-base-MED

qwen3b-rlcr-hotpot-racpo-v1-checkpoint-30

Qwen2.5-3B-Instruct-Embodied-GRPO

Qwen2.5-3B-Instruct

rl-easydata-300

Teacher_r14_train_claude-Qwen2-5-3B-Instruct-seed896

Qwen3-1.7B-Base

gmp-kd3e-1-s50pct-lr1e-4_20260811_191146

sft-qwen-zmaze-v1

sft-qwen-zmaze-v2

sft-qwen-hmaze-v1

Code_Math_FFT_lr1e-6_global_step_272

Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B

code-grpo-checkpoint-950

hmaze-oracle-v1

Qwen3-1.7B

Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint25