metadata
license: llama3
base_model:
- GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
language:
- en
- id
- jv
- su
This model is created by merging GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct using passthrough method to stacking its layers, the result is the model parameters expanded to 11B.
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "gmonsoon/SahabatAI-Llama-11B-Test"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])