palmyra-4-oasis

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "Writer/palmyra-4-oasis"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    attn_implementation="flash_attention_2",
)
messages = [
    {
        "role": "user",
        "content": "who developed you?",
    },
]
input_ids = tokenizer.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
)
gen_conf = {
    "max_new_tokens": 1024,
    "eos_token_id": tokenizer.eos_token_id,
    "temperature": 0.0,
    "top_p": 0.9,
}
with torch.inference_mode():
    output_id = model.generate(input_ids, **gen_conf)
output_text = tokenizer.decode(output_id[0][input_ids.shape[1] :])
print(output_text)