GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
gia-uh
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
gia-uh
Model Tree
gia-uh/cecilia-2b-v0.1
Input Modalities
Output Modalities
Supported Functionality
This model is a fine-tuned version of Cecilia 2B v0.1 which is a continual pre-trained model based on Salamandra 2b. It belongs to the Cecilia collection and follows the same lineage as Cecilia 2B v0.1.
This repository is a Hybrid Release containing:
transformers.llama.cpp, vLLM, or local inference tools.Official quantized GGUF versions (Q8_0, Q6_K, Q4_K_M) in the repository gia-uh/cecilia-2b-instruct-v1-GGUF
python
from transformers import AutoConfig, AutoModel, AutoTokenizer repo_id = "gia-uh/cecilia_ft_ms_v1" # Load model and tokenizerconfig = AutoConfig.from_pretrained(repo_id, trust_remote_code=False)tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModel.from_pretrained(repo_id, trust_remote_code=False) # Simple inferenceinputs = tokenizer("Hola, que bolá?", return_tensors="pt")outputs = model(**inputs)