
Foundation Text-Generation Models Below 360M Parameters
Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters.
Text Generation • Updated • 23.6k • • 40Note License: apache-2.0 Context Length: 8k
PleIAs/Pleias-350m-Preview
Updated • 1.29k • 16Note License: apache-2.0 Context Length: 2k
OuteAI/Lite-Oute-1-300M
Text Generation • Updated • 285 • 7Note License: apache-2.0 Context Length: 4k
keeeeenw/MicroLlama
Text Generation • Updated • 2.84k • 43Note License: apache-2.0 Context Length: 2k
cerebras/Cerebras-GPT-256M
Text Generation • Updated • 1.99k • 25Note License: apache-2.0 Context Length: 2k
UUFO-Aigis/Pico-OpenLAiNN-250M
Updated • 22 • 3Note License: apache-2.0 Context Length: 2k
upstage/TinySolar-248m-4k
Text Generation • Updated • 873 • 5Note License: apache-2.0 Context Length: 4k
M4-ai/TinyMistral-248M-v3
Text Generation • Updated • 304 • 7Note License: apache-2.0 Context Length: 2k
MiniLLM/MiniPLM-llama3.1-212M
Text Generation • Updated • 874 • • 3Note License: apache-2.0 Context Length: ?
MiniLLM/MiniPLM-Qwen-200M
Text Generation • Updated • 197 • 2Note License: apache-2.0 Context Length: ?
princeton-nlp/Sheared-Pythia-160m
Text Generation • Updated • 171 • 4Note License: apache-2.0 Context Length: 2k
JackFram/llama-160m
Text Generation • Updated • 278k • 33Note License: apache-2.0 Context Length: 2k
SmallDoge/Doge-160M
Text Generation • Updated • 8.69k • 2Note License: apache-2.0 Context Length: 2k
EleutherAI/pythia-160m
Text Generation • Updated • 152k • • 30Note License: apache-2.0 Context Length: 2k
openai-community/gpt2
Text Generation • Updated • 17.2M • • 2.61kNote License: mit Context Length: 1k
HuggingFaceTB/SmolLM2-135M
Text Generation • Updated • 294k • • 67Note License: apache-2.0 Context Length: 8k
amd/AMD-Llama-135m
Text Generation • Updated • 12.9k • • 111Note License: apache-2.0 Context Length: 2k
MiniLLM/MiniPLM-Mamba-130M
Text Generation • Updated • 38 • 2Note License: apache-2.0 Context Length: ?
EleutherAI/gpt-neo-125m
Text Generation • Updated • 147k • • 196Note License: mit Context Length: 2k
cerebras/Cerebras-GPT-111M
Text Generation • Updated • 4.16k • • 76Note License: apache-2.0 Context Length: 2k
BEE-spoke-data/smol_llama-101M-GQA
Text Generation • Updated • 4.91k • • 28Note License: apache-2.0 Context Length: 1k
UUFO-Aigis/Pico-OpenLAiNN-100M
Updated • 88 • 1Note License: apache-2.0 Context Length: 2k
distilbert/distilgpt2
Text Generation • Updated • 2.2M • • 494Note License: apache-2.0 Context Length: 1k
weiser/82M-0.4
Text Generation • Updated • 38Note License: apache-2.0 Context Length: 1k
BEE-spoke-data/smol_llama-81M-tied
Text Generation • Updated • 2.33k • 6Note License: apache-2.0 Context Length: 1k
EleutherAI/pythia-70m
Updated • 85.2k • 64Note License: apache-2.0 Context Length: 2k
JackFram/llama-68m
Text Generation • Updated • 552k • 26Note License: apache-2.0 Context Length: 2k
OuteAI/Lite-Oute-1-65M
Text Generation • Updated • 252 • 9Note License: apache-2.0 Context Length: 2k
SmallDoge/Doge-60M
Text Generation • Updated • 8.29k • 4Note License: apache-2.0 Context Length: 2k
Felladrin/Minueza-32M-Base
Text Generation • Updated • 273 • 16Note License: apache-2.0 Context Length: 2k
GerbilLab/Gerbil-A-32m
Text Generation • Updated • 70 • 2Note License: apache-2.0 Context Length: 2k
EleutherAI/pythia-31m
Text Generation • Updated • 22.1k • 5Note License: apache-2.0 Context Length: 2k
SmallDoge/Doge-20M
Text Generation • Updated • 8.18k • 8Note License: apache-2.0 Context Length: 2k
EleutherAI/pythia-14m
Text Generation • Updated • 105k • 20Note License: apache-2.0 Context Length: 2k