| StableLM 3B 4E1T and StableLM Zephyr 3B can be found on the Huggingface Hub | |
| The following code snippet demonstrates how to use StableLM 3B 4E1T for inference: | |
| thon | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| device = "cuda" # the device to load the model onto | |
| tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-3b-4e1t") | |
| model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-3b-4e1t") | |
| model.to(device) | |
| model_inputs = tokenizer("The weather is always wonderful in", return_tensors="pt").to(model.device) | |
| generated_ids = model.generate(**model_inputs, max_length=32, do_sample=True) | |
| responses = tokenizer.batch_decode(generated_ids, skip_special_tokens=True) | |
| responses | |
| ['The weather is always wonderful in Santa Barbara and, for visitors hoping to make the move to our beautiful seaside city, this town offers plenty of great places to'] | |
| Combining StableLM and Flash Attention 2 | |
| First, make sure to install the latest version of Flash Attention v2. |