[Doc] Reorder vision language examples in alphabet order (#11228)
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py
GitHub
parent
d927dbcd88
commit
2ca830dbaa
@ -19,6 +19,159 @@ from vllm.utils import FlexibleArgumentParser
|
||||
# Unless specified, these settings have been tested to work on a single L4.
|
||||
|
||||
|
||||
# Aria
|
||||
def run_aria(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "rhymes-ai/Aria"
|
||||
|
||||
llm = LLM(model=model_name,
|
||||
tokenizer_mode="slow",
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
|
||||
prompt = (f"<|im_start|>user\n<fim_prefix><|img|><fim_suffix>\n{question}"
|
||||
"<|im_end|>\n<|im_start|>assistant\n")
|
||||
|
||||
stop_token_ids = [93532, 93653, 944, 93421, 1019, 93653, 93519]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# BLIP-2
|
||||
def run_blip2(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
# BLIP-2 prompt format is inaccurate on HuggingFace model repository.
|
||||
# See https://huggingface.co/Salesforce/blip2-opt-2.7b/discussions/15#64ff02f3f8cf9e4f5b038262 #noqa
|
||||
prompt = f"Question: {question} Answer:"
|
||||
llm = LLM(model="Salesforce/blip2-opt-2.7b",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Chameleon
|
||||
def run_chameleon(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"{question}<image>"
|
||||
llm = LLM(model="facebook/chameleon-7b",
|
||||
max_model_len=4096,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Fuyu
|
||||
def run_fuyu(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"{question}\n"
|
||||
llm = LLM(model="adept/fuyu-8b",
|
||||
max_model_len=2048,
|
||||
max_num_seqs=2,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# GLM-4v
|
||||
def run_glm4v(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "THUDM/glm-4v-9b"
|
||||
|
||||
llm = LLM(model=model_name,
|
||||
max_model_len=2048,
|
||||
max_num_seqs=2,
|
||||
trust_remote_code=True,
|
||||
enforce_eager=True,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
prompt = question
|
||||
stop_token_ids = [151329, 151336, 151338]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# H2OVL-Mississippi
|
||||
def run_h2ovl(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "h2oai/h2ovl-mississippi-2b"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=8192,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
messages = [{'role': 'user', 'content': f"<image>\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True)
|
||||
|
||||
# Stop tokens for H2OVL-Mississippi
|
||||
# https://huggingface.co/h2oai/h2ovl-mississippi-2b
|
||||
stop_token_ids = [tokenizer.eos_token_id]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Idefics3-8B-Llama3
|
||||
def run_idefics3(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "HuggingFaceM4/Idefics3-8B-Llama3"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
max_num_seqs=2,
|
||||
enforce_eager=True,
|
||||
# if you are running out of memory, you can reduce the "longest_edge".
|
||||
# see: https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3#model-optimizations
|
||||
mm_processor_kwargs={
|
||||
"size": {
|
||||
"longest_edge": 3 * 364
|
||||
},
|
||||
},
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
prompt = (
|
||||
f"<|begin_of_text|>User:<image>{question}<end_of_utterance>\nAssistant:"
|
||||
)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# InternVL
|
||||
def run_internvl(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "OpenGVLab/InternVL2-2B"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
messages = [{'role': 'user', 'content': f"<image>\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True)
|
||||
|
||||
# Stop tokens for InternVL
|
||||
# models variants may have different stop tokens
|
||||
# please refer to the model card for the correct "stop words":
|
||||
# https://huggingface.co/OpenGVLab/InternVL2-2B/blob/main/conversation.py
|
||||
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
|
||||
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# LLaVA-1.5
|
||||
def run_llava(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
@ -75,83 +228,20 @@ def run_llava_onevision(question: str, modality: str):
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Fuyu
|
||||
def run_fuyu(question: str, modality: str):
|
||||
# Mantis
|
||||
def run_mantis(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"{question}\n"
|
||||
llm = LLM(model="adept/fuyu-8b",
|
||||
max_model_len=2048,
|
||||
max_num_seqs=2,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
llama3_template = '<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' # noqa: E501
|
||||
prompt = llama3_template.format(f"{question}\n<image>")
|
||||
|
||||
|
||||
# Phi-3-Vision
|
||||
def run_phi3v(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n"
|
||||
|
||||
# num_crops is an override kwarg to the multimodal image processor;
|
||||
# For some models, e.g., Phi-3.5-vision-instruct, it is recommended
|
||||
# to use 16 for single frame scenarios, and 4 for multi-frame.
|
||||
#
|
||||
# Generally speaking, a larger value for num_crops results in more
|
||||
# tokens per image instance, because it may scale the image more in
|
||||
# the image preprocessing. Some references in the model docs and the
|
||||
# formula for image tokens after the preprocessing
|
||||
# transform can be found below.
|
||||
#
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
|
||||
llm = LLM(
|
||||
model="microsoft/Phi-3.5-vision-instruct",
|
||||
trust_remote_code=True,
|
||||
model="TIGER-Lab/Mantis-8B-siglip-llama3",
|
||||
max_model_len=4096,
|
||||
max_num_seqs=2,
|
||||
# Note - mm_processor_kwargs can also be passed to generate/chat calls
|
||||
mm_processor_kwargs={"num_crops": 16},
|
||||
hf_overrides={"architectures": ["MantisForConditionalGeneration"]},
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# PaliGemma
|
||||
def run_paligemma(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
# PaliGemma has special prompt format for VQA
|
||||
prompt = "caption en"
|
||||
llm = LLM(model="google/paligemma-3b-mix-224",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# PaliGemma 2
|
||||
def run_paligemma2(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
# PaliGemma 2 has special prompt format for VQA
|
||||
prompt = "caption en"
|
||||
llm = LLM(model="google/paligemma2-3b-ft-docci-448",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Chameleon
|
||||
def run_chameleon(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"{question}<image>"
|
||||
llm = LLM(model="facebook/chameleon-7b",
|
||||
max_model_len=4096,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
stop_token_ids = [128009]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
@ -199,58 +289,45 @@ def run_minicpmv(question: str, modality: str):
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# H2OVL-Mississippi
|
||||
def run_h2ovl(question: str, modality: str):
|
||||
# LLama 3.2
|
||||
def run_mllama(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "h2oai/h2ovl-mississippi-2b"
|
||||
model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
|
||||
|
||||
# Note: The default setting of max_num_seqs (256) and
|
||||
# max_model_len (131072) for this model may cause OOM.
|
||||
# You may lower either to run this example on lower-end GPUs.
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=8192,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
messages = [{'role': 'user', 'content': f"<image>\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True)
|
||||
|
||||
# Stop tokens for H2OVL-Mississippi
|
||||
# https://huggingface.co/h2oai/h2ovl-mississippi-2b
|
||||
stop_token_ids = [tokenizer.eos_token_id]
|
||||
prompt = f"<|image|><|begin_of_text|>{question}"
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# InternVL
|
||||
def run_internvl(question: str, modality: str):
|
||||
# Molmo
|
||||
def run_molmo(question, modality):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "OpenGVLab/InternVL2-2B"
|
||||
model_name = "allenai/Molmo-7B-D-0924"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
dtype="bfloat16",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
messages = [{'role': 'user', 'content': f"<image>\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True)
|
||||
|
||||
# Stop tokens for InternVL
|
||||
# models variants may have different stop tokens
|
||||
# please refer to the model card for the correct "stop words":
|
||||
# https://huggingface.co/OpenGVLab/InternVL2-2B/blob/main/conversation.py
|
||||
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
|
||||
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
|
||||
prompt = question
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
@ -279,19 +356,78 @@ def run_nvlm_d(question: str, modality: str):
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# BLIP-2
|
||||
def run_blip2(question: str, modality: str):
|
||||
# PaliGemma
|
||||
def run_paligemma(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
# BLIP-2 prompt format is inaccurate on HuggingFace model repository.
|
||||
# See https://huggingface.co/Salesforce/blip2-opt-2.7b/discussions/15#64ff02f3f8cf9e4f5b038262 #noqa
|
||||
prompt = f"Question: {question} Answer:"
|
||||
llm = LLM(model="Salesforce/blip2-opt-2.7b",
|
||||
# PaliGemma has special prompt format for VQA
|
||||
prompt = "caption en"
|
||||
llm = LLM(model="google/paligemma-3b-mix-224",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# PaliGemma 2
|
||||
def run_paligemma2(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
# PaliGemma 2 has special prompt format for VQA
|
||||
prompt = "caption en"
|
||||
llm = LLM(model="google/paligemma2-3b-ft-docci-448",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Phi-3-Vision
|
||||
def run_phi3v(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
prompt = f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n"
|
||||
|
||||
# num_crops is an override kwarg to the multimodal image processor;
|
||||
# For some models, e.g., Phi-3.5-vision-instruct, it is recommended
|
||||
# to use 16 for single frame scenarios, and 4 for multi-frame.
|
||||
#
|
||||
# Generally speaking, a larger value for num_crops results in more
|
||||
# tokens per image instance, because it may scale the image more in
|
||||
# the image preprocessing. Some references in the model docs and the
|
||||
# formula for image tokens after the preprocessing
|
||||
# transform can be found below.
|
||||
#
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
|
||||
llm = LLM(
|
||||
model="microsoft/Phi-3.5-vision-instruct",
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=2,
|
||||
# Note - mm_processor_kwargs can also be passed to generate/chat calls
|
||||
mm_processor_kwargs={"num_crops": 16},
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Pixtral HF-format
|
||||
def run_pixtral_hf(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "mistral-community/pixtral-12b"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
prompt = f"<s>[INST]{question}\n[IMG][/INST]"
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Qwen
|
||||
def run_qwen_vl(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
@ -335,166 +471,30 @@ def run_qwen2_vl(question: str, modality: str):
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Pixtral HF-format
|
||||
def run_pixtral_hf(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "mistral-community/pixtral-12b"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
prompt = f"<s>[INST]{question}\n[IMG][/INST]"
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# LLama 3.2
|
||||
def run_mllama(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
|
||||
|
||||
# Note: The default setting of max_num_seqs (256) and
|
||||
# max_model_len (131072) for this model may cause OOM.
|
||||
# You may lower either to run this example on lower-end GPUs.
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
prompt = f"<|image|><|begin_of_text|>{question}"
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Molmo
|
||||
def run_molmo(question, modality):
|
||||
assert modality == "image"
|
||||
|
||||
model_name = "allenai/Molmo-7B-D-0924"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
|
||||
prompt = question
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# GLM-4v
|
||||
def run_glm4v(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "THUDM/glm-4v-9b"
|
||||
|
||||
llm = LLM(model=model_name,
|
||||
max_model_len=2048,
|
||||
max_num_seqs=2,
|
||||
trust_remote_code=True,
|
||||
enforce_eager=True,
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
prompt = question
|
||||
stop_token_ids = [151329, 151336, 151338]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Idefics3-8B-Llama3
|
||||
def run_idefics3(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "HuggingFaceM4/Idefics3-8B-Llama3"
|
||||
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
max_num_seqs=2,
|
||||
enforce_eager=True,
|
||||
# if you are running out of memory, you can reduce the "longest_edge".
|
||||
# see: https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3#model-optimizations
|
||||
mm_processor_kwargs={
|
||||
"size": {
|
||||
"longest_edge": 3 * 364
|
||||
},
|
||||
},
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
prompt = (
|
||||
f"<|begin_of_text|>User:<image>{question}<end_of_utterance>\nAssistant:"
|
||||
)
|
||||
stop_token_ids = None
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Aria
|
||||
def run_aria(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
model_name = "rhymes-ai/Aria"
|
||||
|
||||
llm = LLM(model=model_name,
|
||||
tokenizer_mode="slow",
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor)
|
||||
|
||||
prompt = (f"<|im_start|>user\n<fim_prefix><|img|><fim_suffix>\n{question}"
|
||||
"<|im_end|>\n<|im_start|>assistant\n")
|
||||
|
||||
stop_token_ids = [93532, 93653, 944, 93421, 1019, 93653, 93519]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
# Mantis
|
||||
def run_mantis(question: str, modality: str):
|
||||
assert modality == "image"
|
||||
|
||||
llama3_template = '<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' # noqa: E501
|
||||
prompt = llama3_template.format(f"{question}\n<image>")
|
||||
|
||||
llm = LLM(
|
||||
model="TIGER-Lab/Mantis-8B-siglip-llama3",
|
||||
max_model_len=4096,
|
||||
hf_overrides={"architectures": ["MantisForConditionalGeneration"]},
|
||||
mm_cache_preprocessor=args.mm_cache_preprocessor,
|
||||
)
|
||||
stop_token_ids = [128009]
|
||||
return llm, prompt, stop_token_ids
|
||||
|
||||
|
||||
model_example_map = {
|
||||
"aria": run_aria,
|
||||
"blip-2": run_blip2,
|
||||
"chameleon": run_chameleon,
|
||||
"fuyu": run_fuyu,
|
||||
"glm4v": run_glm4v,
|
||||
"h2ovl_chat": run_h2ovl,
|
||||
"idefics3": run_idefics3,
|
||||
"internvl_chat": run_internvl,
|
||||
"llava": run_llava,
|
||||
"llava-next": run_llava_next,
|
||||
"llava-next-video": run_llava_next_video,
|
||||
"llava-onevision": run_llava_onevision,
|
||||
"fuyu": run_fuyu,
|
||||
"phi3_v": run_phi3v,
|
||||
"paligemma": run_paligemma,
|
||||
"paligemma2": run_paligemma2,
|
||||
"chameleon": run_chameleon,
|
||||
"mantis": run_mantis,
|
||||
"minicpmv": run_minicpmv,
|
||||
"blip-2": run_blip2,
|
||||
"h2ovl_chat": run_h2ovl,
|
||||
"internvl_chat": run_internvl,
|
||||
"NVLM_D": run_nvlm_d,
|
||||
"qwen_vl": run_qwen_vl,
|
||||
"qwen2_vl": run_qwen2_vl,
|
||||
"pixtral_hf": run_pixtral_hf,
|
||||
"mllama": run_mllama,
|
||||
"molmo": run_molmo,
|
||||
"glm4v": run_glm4v,
|
||||
"idefics3": run_idefics3,
|
||||
"aria": run_aria,
|
||||
"mantis": run_mantis,
|
||||
"NVLM_D": run_nvlm_d,
|
||||
"paligemma": run_paligemma,
|
||||
"paligemma2": run_paligemma2,
|
||||
"phi3_v": run_phi3v,
|
||||
"pixtral_hf": run_pixtral_hf,
|
||||
"qwen_vl": run_qwen_vl,
|
||||
"qwen2_vl": run_qwen2_vl,
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -33,78 +33,23 @@ class ModelRequestData(NamedTuple):
|
||||
# Unless specified, these settings have been tested to work on a single L4.
|
||||
|
||||
|
||||
def load_qwenvl_chat(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "Qwen/Qwen-VL-Chat"
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=1024,
|
||||
max_num_seqs=2,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
)
|
||||
placeholders = "".join(f"Picture {i}: <img></img>\n"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
|
||||
# This model does not have a chat_template attribute on its tokenizer,
|
||||
# so we need to explicitly pass it. We use ChatML since it's used in the
|
||||
# generation utils of the model:
|
||||
# https://huggingface.co/Qwen/Qwen-VL-Chat/blob/main/qwen_generation_utils.py#L265
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
|
||||
# Copied from: https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}" # noqa: E501
|
||||
|
||||
messages = [{'role': 'user', 'content': f"{placeholders}\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
chat_template=chat_template)
|
||||
|
||||
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>"]
|
||||
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
|
||||
def load_aria(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "rhymes-ai/Aria"
|
||||
llm = LLM(model=model_name,
|
||||
tokenizer_mode="slow",
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
limit_mm_per_prompt={"image": len(image_urls)})
|
||||
placeholders = "<fim_prefix><|img|><fim_suffix>\n" * len(image_urls)
|
||||
prompt = (f"<|im_start|>user\n{placeholders}{question}<|im_end|>\n"
|
||||
"<|im_start|>assistant\n")
|
||||
stop_token_ids = [93532, 93653, 944, 93421, 1019, 93653, 93519]
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=stop_token_ids,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=chat_template,
|
||||
)
|
||||
|
||||
|
||||
def load_phi3v(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
# num_crops is an override kwarg to the multimodal image processor;
|
||||
# For some models, e.g., Phi-3.5-vision-instruct, it is recommended
|
||||
# to use 16 for single frame scenarios, and 4 for multi-frame.
|
||||
#
|
||||
# Generally speaking, a larger value for num_crops results in more
|
||||
# tokens per image instance, because it may scale the image more in
|
||||
# the image preprocessing. Some references in the model docs and the
|
||||
# formula for image tokens after the preprocessing
|
||||
# transform can be found below.
|
||||
#
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
|
||||
llm = LLM(
|
||||
model="microsoft/Phi-3.5-vision-instruct",
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=2,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
mm_processor_kwargs={"num_crops": 4},
|
||||
)
|
||||
placeholders = "\n".join(f"<|image_{i}|>"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
prompt = f"<|user|>\n{placeholders}\n{question}<|end|>\n<|assistant|>\n"
|
||||
stop_token_ids = None
|
||||
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=stop_token_ids,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
chat_template=None)
|
||||
|
||||
|
||||
def load_h2onvl(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
@ -141,6 +86,37 @@ def load_h2onvl(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
)
|
||||
|
||||
|
||||
def load_idefics3(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "HuggingFaceM4/Idefics3-8B-Llama3"
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
# if you are running out of memory, you can reduce the "longest_edge".
|
||||
# see: https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3#model-optimizations
|
||||
mm_processor_kwargs={
|
||||
"size": {
|
||||
"longest_edge": 2 * 364
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
placeholders = "\n".join(f"Image-{i}: <image>\n"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
prompt = f"<|begin_of_text|>User:{placeholders}\n{question}<end_of_utterance>\nAssistant:" # noqa: E501
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=None,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
|
||||
|
||||
def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "OpenGVLab/InternVL2-2B"
|
||||
|
||||
@ -178,6 +154,28 @@ def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
)
|
||||
|
||||
|
||||
def load_mllama(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
)
|
||||
|
||||
prompt = f"<|image|><|image|><|begin_of_text|>{question}"
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=None,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
|
||||
|
||||
def load_nvlm_d(question: str, image_urls: List[str]):
|
||||
model_name = "nvidia/NVLM-D-72B"
|
||||
|
||||
@ -211,6 +209,80 @@ def load_nvlm_d(question: str, image_urls: List[str]):
|
||||
)
|
||||
|
||||
|
||||
def load_phi3v(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
# num_crops is an override kwarg to the multimodal image processor;
|
||||
# For some models, e.g., Phi-3.5-vision-instruct, it is recommended
|
||||
# to use 16 for single frame scenarios, and 4 for multi-frame.
|
||||
#
|
||||
# Generally speaking, a larger value for num_crops results in more
|
||||
# tokens per image instance, because it may scale the image more in
|
||||
# the image preprocessing. Some references in the model docs and the
|
||||
# formula for image tokens after the preprocessing
|
||||
# transform can be found below.
|
||||
#
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct#loading-the-model-locally
|
||||
# https://huggingface.co/microsoft/Phi-3.5-vision-instruct/blob/main/processing_phi3_v.py#L194
|
||||
llm = LLM(
|
||||
model="microsoft/Phi-3.5-vision-instruct",
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=2,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
mm_processor_kwargs={"num_crops": 4},
|
||||
)
|
||||
placeholders = "\n".join(f"<|image_{i}|>"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
prompt = f"<|user|>\n{placeholders}\n{question}<|end|>\n<|assistant|>\n"
|
||||
stop_token_ids = None
|
||||
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=stop_token_ids,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
|
||||
|
||||
def load_qwenvl_chat(question: str, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "Qwen/Qwen-VL-Chat"
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
trust_remote_code=True,
|
||||
max_model_len=1024,
|
||||
max_num_seqs=2,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
)
|
||||
placeholders = "".join(f"Picture {i}: <img></img>\n"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
|
||||
# This model does not have a chat_template attribute on its tokenizer,
|
||||
# so we need to explicitly pass it. We use ChatML since it's used in the
|
||||
# generation utils of the model:
|
||||
# https://huggingface.co/Qwen/Qwen-VL-Chat/blob/main/qwen_generation_utils.py#L265
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name,
|
||||
trust_remote_code=True)
|
||||
|
||||
# Copied from: https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}" # noqa: E501
|
||||
|
||||
messages = [{'role': 'user', 'content': f"{placeholders}\n{question}"}]
|
||||
prompt = tokenizer.apply_chat_template(messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
chat_template=chat_template)
|
||||
|
||||
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>"]
|
||||
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=stop_token_ids,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=chat_template,
|
||||
)
|
||||
|
||||
|
||||
def load_qwen2_vl(question, image_urls: List[str]) -> ModelRequestData:
|
||||
try:
|
||||
from qwen_vl_utils import process_vision_info
|
||||
@ -268,88 +340,16 @@ def load_qwen2_vl(question, image_urls: List[str]) -> ModelRequestData:
|
||||
)
|
||||
|
||||
|
||||
def load_mllama(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
)
|
||||
|
||||
prompt = f"<|image|><|image|><|begin_of_text|>{question}"
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=None,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
|
||||
|
||||
def load_idefics3(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "HuggingFaceM4/Idefics3-8B-Llama3"
|
||||
|
||||
# The configuration below has been confirmed to launch on a single L40 GPU.
|
||||
llm = LLM(
|
||||
model=model_name,
|
||||
max_model_len=8192,
|
||||
max_num_seqs=16,
|
||||
enforce_eager=True,
|
||||
limit_mm_per_prompt={"image": len(image_urls)},
|
||||
# if you are running out of memory, you can reduce the "longest_edge".
|
||||
# see: https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3#model-optimizations
|
||||
mm_processor_kwargs={
|
||||
"size": {
|
||||
"longest_edge": 2 * 364
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
placeholders = "\n".join(f"Image-{i}: <image>\n"
|
||||
for i, _ in enumerate(image_urls, start=1))
|
||||
prompt = f"<|begin_of_text|>User:{placeholders}\n{question}<end_of_utterance>\nAssistant:" # noqa: E501
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=None,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None,
|
||||
)
|
||||
|
||||
|
||||
def load_aria(question, image_urls: List[str]) -> ModelRequestData:
|
||||
model_name = "rhymes-ai/Aria"
|
||||
llm = LLM(model=model_name,
|
||||
tokenizer_mode="slow",
|
||||
trust_remote_code=True,
|
||||
dtype="bfloat16",
|
||||
limit_mm_per_prompt={"image": len(image_urls)})
|
||||
placeholders = "<fim_prefix><|img|><fim_suffix>\n" * len(image_urls)
|
||||
prompt = (f"<|im_start|>user\n{placeholders}{question}<|im_end|>\n"
|
||||
"<|im_start|>assistant\n")
|
||||
stop_token_ids = [93532, 93653, 944, 93421, 1019, 93653, 93519]
|
||||
return ModelRequestData(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
stop_token_ids=stop_token_ids,
|
||||
image_data=[fetch_image(url) for url in image_urls],
|
||||
chat_template=None)
|
||||
|
||||
|
||||
model_example_map = {
|
||||
"phi3_v": load_phi3v,
|
||||
"h2ovl_chat": load_h2onvl,
|
||||
"internvl_chat": load_internvl,
|
||||
"NVLM_D": load_nvlm_d,
|
||||
"qwen2_vl": load_qwen2_vl,
|
||||
"qwen_vl_chat": load_qwenvl_chat,
|
||||
"mllama": load_mllama,
|
||||
"idefics3": load_idefics3,
|
||||
"aria": load_aria,
|
||||
"h2ovl_chat": load_h2onvl,
|
||||
"idefics3": load_idefics3,
|
||||
"internvl_chat": load_internvl,
|
||||
"mllama": load_mllama,
|
||||
"NVLM_D": load_nvlm_d,
|
||||
"phi3_v": load_phi3v,
|
||||
"qwen_vl_chat": load_qwenvl_chat,
|
||||
"qwen2_vl": load_qwen2_vl,
|
||||
}
|
||||
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user