Uploaded finetuned model

• Developed by: aliRafik
• License: apache-2.0
• Finetuned from model : unsloth/GLM-4.7-Flash

This glm4_moe_lite model was trained 2x faster with Unsloth and Huggingface's TRL library.

Inference

from transformers import AutoModelForCausalLM, AutoTokenizer import torch

Load from Hugging Face

model = AutoModelForCausalLM.from_pretrained( "aliRafik/glm_flash_finetuned_16bit", torch_dtype=torch.float16, device_map="auto" )

tokenizer = AutoTokenizer.from_pretrained("aliRafik/glm_flash_finetuned_16bit")

Test inference

inputs = tokenizer("Hello, how are you?", return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=100) print(tokenizer.decode(outputs[0]))

Output