!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "Eurdem/Bombus_3x8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    load_in_4bit= True
)

messages = [
    {"role": "system", "content": "You are a helpful chatbot who always responds friendly."},
    {"role": "user", "content": "tell me about yourself"},
]

input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")

outputs = model.generate(input_ids,
                          max_new_tokens=1024,
                          do_sample=True,
                          temperature=0.7,
                          top_p=0.7,
                          top_k=500,
                      )
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Eurdem/Bombus_3x8B_v2

Usage

Eurdem/
Bombus_3x8B_v2