GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
SENAGI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
SENAGI
Model Tree
Input Modalities
Output Modalities
Supported Functionality
tokenizers)state.jsonjson
{"model_type": "llama","hidden_size": 384,"intermediate_size": 768,"num_hidden_layers": 8,"num_attention_heads": 6,"num_key_value_heads": 3,"vocab_size": 24000,"tie_word_embeddings": true,"hidden_act": "silu"}
python
from transformers import AutoTokenizer, AutoModelForCausalLMrepo = "SENAGI/Lily-2.0-20M"tokenizer = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo)prompt = "The meaning of life is"inputs = tokenizer(prompt, return_tensors="pt")outputs = model.generate(**inputs,max_new_tokens=64,do_sample=True,temperature=0.7,top_p=0.9,)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Trained on SENAGI/fineweb-edu-400M-raw, a 400M-token educational corpus split into 80 raw text
shards (part_01.txt ... part_80.txt).
MIT
Made with 🌸 by SENAGI