from transformers import LlamaTokenizer, LlamaForCausalLM

# Specify the model name or path from the Hugging Face Hub
org_in = "BEE-spoke-data/"
org_out = "baseten/"
model_name = "smol_llama-101M-GQA"
embedding = False
embedding_name = "embedding-" if embedding else ""
tokenizer = LlamaTokenizer.from_pretrained(org_in+model_name)
model = LlamaForCausalLM.from_pretrained(org_in+model_name)

prompt = "Hello, this is a test."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

model_llama = model
if embedding:
    model_llama = model_llama.model

# 2. Push to a new Hugging Face repository
# Make sure you have run `huggingface-cli login` beforehand to authenticate
model_llama.push_to_hub(org_out+embedding_name+model_name, token="xxx")
tokenizer.push_to_hub(org_out+embedding_name+model_name, token="xx")

baseten/smol_llama-101M-GQA

Model Card for Model ID

Model Details

baseten/
smol_llama-101M-GQA