README.md

metadata

base_model:
  - sethuiyer/Medichat-Llama3-8B
  - GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
tags:
  - merge
  - sethuiyer/Medichat-Llama3-8B
  - GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
license: llama3
language:
  - en
  - id
  - jv
  - su

SahabatAI-MediChatIndo-8B-v1

SahabatAI-MediChatIndo-8B-v1 is a merge of the following models:

• sethuiyer/Medichat-Llama3-8B
• GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct

DEMO SPACE: HERE

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "gmonsoon/SahabatAI-MediChatIndo-8B-v1"
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"])