|
--- |
|
license: other |
|
license_name: meta |
|
license_link: https://ai.meta.com/llama/licence |
|
--- |
|
Testing the reflection idea. With the base vison model. |
|
|
|
from llava.model.builder import load_pretrained_model |
|
from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token |
|
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX |
|
from llava.conversation import conv_templates, SeparatorStyle |
|
|
|
from PIL import Image |
|
import requests |
|
import copy |
|
import torch |
|
|
|
pretrained = "mylesgoose/Meta-Llama-3.1-8B-Instruct-goose-abliterated-pre-llava-reflection" |
|
model_name = "llava_llama3" |
|
device = "cuda" |
|
device_map = "auto" |
|
tokenizer, model, image_processor, max_length = load_pretrained_model(pretrained, None, model_name, device_map=device_map, attn_implementation="flash_attention_2") # Add any other thing you want to pass in llava_model_args |
|
|
|
model.eval() |
|
model.tie_weights() |
|
image = Image.open("/home/myles/Desktop/extreme_ironing.jpg") |
|
image_tensor = process_images([image], image_processor, model.config) |
|
image_tensor = [_image.to(dtype=torch.float16, device=device) for _image in image_tensor] |
|
|
|
conv_template = "llava_llama_3" |
|
question = DEFAULT_IMAGE_TOKEN + "\nWhat is shown in this image? Is there anything strange about this image? Is this normal behaviour." |
|
conv = copy.deepcopy(conv_templates[conv_template]) |
|
conv.append_message(conv.roles[0], question) |
|
conv.append_message(conv.roles[1], None) |
|
prompt_question = conv.get_prompt() |
|
|
|
input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device) |
|
image_sizes = [image.size] |
|
|
|
|
|
cont = model.generate( |
|
input_ids, |
|
images=image_tensor, |
|
image_sizes=image_sizes, |
|
do_sample=True, |
|
temperature=0.7, |
|
max_new_tokens=120000, |
|
) |
|
text_outputs = tokenizer.batch_decode(cont, skip_special_tokens=True) |
|
print(text_outputs) |
|
|
|
and template in conversation.py : |
|
conv_llava_llama_3 = Conversation( |
|
system="<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful language and vision, AI. " "You are able to understand the visual content that the user provides, " "and assist the user with a variety of tasks using natural language, You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.", |
|
roles=("<|start_header_id|>user<|end_header_id|>\n\n", |
|
"<|start_header_id|>assistant<|end_header_id|>\n\n"), |
|
version="llama3", |
|
messages=[], |
|
offset=0, |
|
sep="<|eot_id|>", |
|
sep_style=SeparatorStyle.LLAMA_3, |
|
tokenizer_id="mylesgoose/Meta-Llama-3.1-8B-Instruct-goose-abliterated-pre-llava-reflection", |
|
tokenizer=safe_load_tokenizer("mylesgoose/Meta-Llama-3.1-8B-Instruct-goose-abliterated-pre-llava-reflection"), |
|
stop_token_ids=[128009], |
|
) |
|
|
|
|
|
|
