Code:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
device = 'cuda'
model_id = "CohereForAI/c4ai-command-r-plus"
tokenizer = AutoTokenizer.from_pretrained(model_id)

bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtyp>
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, torch_dtype=>

messages = [{"role": "user", "content": "Hello, how are you?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, retu>
input_ids = input_ids.to(device) # Move input tensor to GPU

gen_tokens = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.3,
)

gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)

RESPONSE:

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|████████████████████████████████████| 44/44 [03:10<00:00, 4.33s/it]
Some weights of the model checkpoint at CohereForAI/c4ai-command-r-plus were not used when initializing CohereForCausalLM: ['model.layers.0.self_attn.k_norm.weight', 'model.layers.0.self_attn.q_norm.weight', 'model.layers.1.self_attn.k_norm.weight', 'model.layers.1.self_attn.q_norm.weight', 'model.layers.10.self_attn.k_norm.weight', 'model.layers.10.self_attn.q_norm.weight', 'model.layers.11.self_attn.k_norm.weight', 'model.layers.11.self_attn.q_norm.weight', 'model.layers.12.self_attn.k_norm.weight', 'model.layers.12.self_attn.q_norm.weight', 'model.layers.13.self_attn.k_norm.weight', 'model.layers.13.self_attn.q_norm.weight', 'model.layers.14.self_attn.k_norm.weight', 'model.layers.14.self_attn.q_norm.weight', 'model.layers.15.self_attn.k_norm.weight', 'model.layers.15.self_attn.q_norm.weight', 'model.layers.16.self_attn.k_norm.weight', 'model.layers.16.self_attn.q_norm.weight', 'model.layers.17.self_attn.k_norm.weight', 'model.layers.17.self_attn.q_norm.weight', 'model.layers.18.self_attn.k_norm.weight', 'model.layers.18.self_attn.q_norm.weight', 'model.layers.19.self_attn.k_norm.weight', 'model.layers.19.self_attn.q_norm.weight', 'model.layers.2.self_attn.k_norm.weight', 'model.layers.2.self_attn.q_norm.weight', 'model.layers.20.self_attn.k_norm.weight', 'model.layers.20.self_attn.q_norm.weight', 'model.layers.21.self_attn.k_norm.weight', 'model.layers.21.self_attn.q_norm.weight', 'model.layers.22.self_attn.k_norm.weight', 'model.layers.22.self_attn.q_norm.weight', 'model.layers.23.self_attn.k_norm.weight', 'model.layers.23.self_attn.q_norm.weight', 'model.layers.24.self_attn.k_norm.weight', 'model.layers.24.self_attn.q_norm.weight', 'model.layers.25.self_attn.k_norm.weight', 'model.layers.25.self_attn.q_norm.weight', 'model.layers.26.self_attn.k_norm.weight', 'model.layers.26.self_attn.q_norm.weight', 'model.layers.27.self_attn.k_norm.weight', 'model.layers.27.self_attn.q_norm.weight', 'model.layers.28.self_attn.k_norm.weight', 'model.layers.28.self_attn.q_norm.weight', 'model.layers.29.self_attn.k_norm.weight', 'model.layers.29.self_attn.q_norm.weight', 'model.layers.3.self_attn.k_norm.weight', 'model.layers.3.self_attn.q_norm.weight', 'model.layers.30.self_attn.k_norm.weight', 'model.layers.30.self_attn.q_norm.weight', 'model.layers.31.self_attn.k_norm.weight', 'model.layers.31.self_attn.q_norm.weight', 'model.layers.32.self_attn.k_norm.weight', 'model.layers.32.self_attn.q_norm.weight', 'model.layers.33.self_attn.k_norm.weight', 'model.layers.33.self_attn.q_norm.weight', 'model.layers.34.self_attn.k_norm.weight', 'model.layers.34.self_attn.q_norm.weight', 'model.layers.35.self_attn.k_norm.weight', 'model.layers.35.self_attn.q_norm.weight', 'model.layers.36.self_attn.k_norm.weight', 'model.layers.36.self_attn.q_norm.weight', 'model.layers.37.self_attn.k_norm.weight', 'model.layers.37.self_attn.q_norm.weight', 'model.layers.38.self_attn.k_norm.weight', 'model.layers.38.self_attn.q_norm.weight', 'model.layers.39.self_attn.k_norm.weight', 'model.layers.39.self_attn.q_norm.weight', 'model.layers.4.self_attn.k_norm.weight', 'model.layers.4.self_attn.q_norm.weight', 'model.layers.40.self_attn.k_norm.weight', 'model.layers.40.self_attn.q_norm.weight', 'model.layers.41.self_attn.k_norm.weight', 'model.layers.41.self_attn.q_norm.weight', 'model.layers.42.self_attn.k_norm.weight', 'model.layers.42.self_attn.q_norm.weight', 'model.layers.43.self_attn.k_norm.weight', 'model.layers.43.self_attn.q_norm.weight', 'model.layers.44.self_attn.k_norm.weight', 'model.layers.44.self_attn.q_norm.weight', 'model.layers.45.self_attn.k_norm.weight', 'model.layers.45.self_attn.q_norm.weight', 'model.layers.46.self_attn.k_norm.weight', 'model.layers.46.self_attn.q_norm.weight', 'model.layers.47.self_attn.k_norm.weight', 'model.layers.47.self_attn.q_norm.weight', 'model.layers.48.self_attn.k_norm.weight', 'model.layers.48.self_attn.q_norm.weight', 'model.layers.49.self_attn.k_norm.weight', 'model.layers.49.self_attn.q_norm.weight', 'model.layers.5.self_attn.k_norm.weight', 'model.layers.5.self_attn.q_norm.weight', 'model.layers.50.self_attn.k_norm.weight', 'model.layers.50.self_attn.q_norm.weight', 'model.layers.51.self_attn.k_norm.weight', 'model.layers.51.self_attn.q_norm.weight', 'model.layers.52.self_attn.k_norm.weight', 'model.layers.52.self_attn.q_norm.weight', 'model.layers.53.self_attn.k_norm.weight', 'model.layers.53.self_attn.q_norm.weight', 'model.layers.54.self_attn.k_norm.weight', 'model.layers.54.self_attn.q_norm.weight', 'model.layers.55.self_attn.k_norm.weight', 'model.layers.55.self_attn.q_norm.weight', 'model.layers.56.self_attn.k_norm.weight', 'model.layers.56.self_attn.q_norm.weight', 'model.layers.57.self_attn.k_norm.weight', 'model.layers.57.self_attn.q_norm.weight', 'model.layers.58.self_attn.k_norm.weight', 'model.layers.58.self_attn.q_norm.weight', 'model.layers.59.self_attn.k_norm.weight', 'model.layers.59.self_attn.q_norm.weight', 'model.layers.6.self_attn.k_norm.weight', 'model.layers.6.self_attn.q_norm.weight', 'model.layers.60.self_attn.k_norm.weight', 'model.layers.60.self_attn.q_norm.weight', 'model.layers.61.self_attn.k_norm.weight', 'model.layers.61.self_attn.q_norm.weight', 'model.layers.62.self_attn.k_norm.weight', 'model.layers.62.self_attn.q_norm.weight', 'model.layers.63.self_attn.k_norm.weight', 'model.layers.63.self_attn.q_norm.weight', 'model.layers.7.self_attn.k_norm.weight', 'model.layers.7.self_attn.q_norm.weight', 'model.layers.8.self_attn.k_norm.weight', 'model.layers.8.self_attn.q_norm.weight', 'model.layers.9.self_attn.k_norm.weight', 'model.layers.9.self_attn.q_norm.weight']

• This IS expected if you are initializing CohereForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing CohereForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  <|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>beginnsectionKE-sectionauthor-sectionauthor-section-sectionsub-begin-sectionauthor-sectionn-begin-author-begin-begin a-usectionauthor-documentauthor.KEn -KEauthor-begin-authorauthor-author-author-authorauthor-n-allauthor-author-allauthor-rauthor-authorn-n-allalln
  --newauthor--author--KEauthorn-n -KEauthor