File size: 2,822 Bytes
cb23567 749b3a3 cb23567 749b3a3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
---
library_name: transformers
license: apache-2.0
base_model:
- rhymes-ai/Aria-sequential_mlp
- rhymes-ai/Aria
pipeline_tag: image-text-to-text
---
# Aria-sequential_mlp-bnb_nf4
BitsAndBytes NF4 quantization from [Aria-sequential_mlp](https://huggingface.co/rhymes-ai/Aria-sequential_mlp), requires about 13.8 GB of VRAM and works on a RTX 3090.
Currently the model is not 5 GB sharded, as this seems to cause [problems](https://stackoverflow.com/questions/79068298/valueerror-supplied-state-dict-for-layers-does-not-contain-bitsandbytes-an) when loading serialized BNB models. This might make it impossible to load the model in free-tier Colab.
Run this model with:
``` python
import requests
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoProcessor
torch.cuda.set_device(0)
model_id_or_path = "thwin27/Aria-sequential_mlp-bnb_nf4"
model = AutoModelForCausalLM.from_pretrained(model_id_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
processor = AutoProcessor.from_pretrained(model_id_or_path, trust_remote_code=True)
image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
image = Image.open(requests.get(image_path, stream=True).raw)
messages = [
{
"role": "user",
"content": [
{"text": None, "type": "image"},
{"text": "what is the image?", "type": "text"},
],
}
]
text = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=text, images=image, return_tensors="pt")
inputs["pixel_values"] = inputs["pixel_values"].to(model.dtype)
inputs = {k: v.to(model.device) for k, v in inputs.items()}
with torch.inference_mode(), torch.cuda.amp.autocast(dtype=torch.bfloat16):
output = model.generate(
**inputs,
max_new_tokens=500,
stop_strings=["<|im_end|>"],
tokenizer=processor.tokenizer,
do_sample=True,
temperature=0.9,
)
output_ids = output[0][inputs["input_ids"].shape[1]:]
result = processor.decode(output_ids, skip_special_tokens=True)
print(result)
print(f'Max allocated memory: {torch.cuda.max_memory_allocated(device="cuda") / 1024 ** 3:.3f}GiB')
```
Quantization created with:
``` python
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
model_id = "rhymes-ai/Aria-sequential_mlp"
nf4_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
llm_int8_enable_fp32_cpu_offload=True,
llm_int8_skip_modules=["language_model.lm_head", "multi_modal_projector", "vision_tower"],
)
model_nf4 = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=nf4_config)
``` |