---
license: llama2
---
Quick notes--what I did to get to this point

```
from optimum.neuron import NeuronModelForCausalLM
from transformers import AutoTokenizer
model_id = "TencentARC/LLaMA-Pro-8B"
compiler_args = {"num_cores": 2, "auto_cast_type": "fp16"}
input_shapes = {"sequence_length": 2048, "batch_size": 2 }
llm = NeuronModelForCausalLM.from_pretrained(model_id, export=True, **input_shapes, **compiler_args)
save_directory = "Tencent_neuron"

llm.save_pretrained(save_directory)
tokenizer = AutoTokenizer.from_pretrained(model_id)

tokenizer.save_pretrained(save_directory)

quit()
```

```
from optimum.neuron import pipeline

# Load pipeline from Hugging Face repository
save_directory = "Tencent_neuron"

pipe = pipeline("text-generation", save_directory)

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {"role": "user", "content": "What is 2+2?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# Run generation
outputs = pipe(prompt, max_new_tokens=2048, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

```
```
from huggingface_hub import login
from huggingface_hub import HfApi
api = HfApi()
login()


save_directory = "Tencent_neuron"

api.upload_folder(
    folder_path=save_directory,
    repo_id="jburtoft/TencentARC-LLaMA-Pro-8B-Neuron",
    repo_type="model",
    multi_commits=True,
    multi_commits_verbose=True,
)
```