初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w4a16 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
575
README.md
Normal file
575
README.md
Normal file
@@ -0,0 +1,575 @@
|
|||||||
|
---
|
||||||
|
tags:
|
||||||
|
- vllm
|
||||||
|
- vision
|
||||||
|
- w4a16
|
||||||
|
license: apache-2.0
|
||||||
|
license_link: >-
|
||||||
|
https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
base_model: Qwen/Qwen2.5-VL-3B-Instruct
|
||||||
|
library_name: transformers
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen2.5-VL-3B-Instruct-quantized-w4a16
|
||||||
|
|
||||||
|
## Model Overview
|
||||||
|
- **Model Architecture:** Qwen/Qwen2.5-VL-3B-Instruct
|
||||||
|
- **Input:** Vision-Text
|
||||||
|
- **Output:** Text
|
||||||
|
- **Model Optimizations:**
|
||||||
|
- **Weight quantization:** INT4
|
||||||
|
- **Activation quantization:** FP16
|
||||||
|
- **Release Date:** 2/24/2025
|
||||||
|
- **Version:** 1.0
|
||||||
|
- **Model Developers:** Neural Magic
|
||||||
|
|
||||||
|
Quantized version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
|
||||||
|
|
||||||
|
### Model Optimizations
|
||||||
|
|
||||||
|
This model was obtained by quantizing the weights of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) to INT8 data type, ready for inference with vLLM >= 0.5.2.
|
||||||
|
|
||||||
|
## Deployment
|
||||||
|
|
||||||
|
### Use with vLLM
|
||||||
|
|
||||||
|
This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
|
||||||
|
|
||||||
|
```python
|
||||||
|
from vllm.assets.image import ImageAsset
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
# prepare model
|
||||||
|
llm = LLM(
|
||||||
|
model="neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16",
|
||||||
|
trust_remote_code=True,
|
||||||
|
max_model_len=4096,
|
||||||
|
max_num_seqs=2,
|
||||||
|
)
|
||||||
|
|
||||||
|
# prepare inputs
|
||||||
|
question = "What is the content of this image?"
|
||||||
|
inputs = {
|
||||||
|
"prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
|
||||||
|
"multi_modal_data": {
|
||||||
|
"image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
# generate response
|
||||||
|
print("========== SAMPLE GENERATION ==============")
|
||||||
|
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
|
||||||
|
print(f"PROMPT : {outputs[0].prompt}")
|
||||||
|
print(f"RESPONSE: {outputs[0].outputs[0].text}")
|
||||||
|
print("==========================================")
|
||||||
|
```
|
||||||
|
|
||||||
|
vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
|
||||||
|
|
||||||
|
## Creation
|
||||||
|
|
||||||
|
This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below as part a multimodal announcement blog.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Model Creation Code</summary>
|
||||||
|
|
||||||
|
```python
|
||||||
|
import base64
|
||||||
|
from io import BytesIO
|
||||||
|
import torch
|
||||||
|
from datasets import load_dataset
|
||||||
|
from qwen_vl_utils import process_vision_info
|
||||||
|
from transformers import AutoProcessor
|
||||||
|
from llmcompressor.modifiers.quantization import GPTQModifier
|
||||||
|
from llmcompressor.transformers import oneshot
|
||||||
|
from llmcompressor.transformers.tracing import (
|
||||||
|
TraceableQwen2_5_VLForConditionalGeneration,
|
||||||
|
)
|
||||||
|
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme
|
||||||
|
|
||||||
|
# Load model.
|
||||||
|
model_id = "Qwen/Qwen2.5-VL-3B-Instruct"
|
||||||
|
|
||||||
|
model = TraceableQwen2_5_VLForConditionalGeneration.from_pretrained(
|
||||||
|
model_id,
|
||||||
|
device_map="auto",
|
||||||
|
torch_dtype="auto",
|
||||||
|
)
|
||||||
|
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
|
||||||
|
|
||||||
|
# Oneshot arguments
|
||||||
|
DATASET_ID = "lmms-lab/flickr30k"
|
||||||
|
DATASET_SPLIT = {"calibration": "test[:512]"}
|
||||||
|
NUM_CALIBRATION_SAMPLES = 512
|
||||||
|
MAX_SEQUENCE_LENGTH = 2048
|
||||||
|
|
||||||
|
# Load dataset and preprocess.
|
||||||
|
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
|
||||||
|
ds = ds.shuffle(seed=42)
|
||||||
|
dampening_frac=0.01
|
||||||
|
|
||||||
|
# Apply chat template and tokenize inputs.
|
||||||
|
def preprocess_and_tokenize(example):
|
||||||
|
# preprocess
|
||||||
|
buffered = BytesIO()
|
||||||
|
example["image"].save(buffered, format="PNG")
|
||||||
|
encoded_image = base64.b64encode(buffered.getvalue())
|
||||||
|
encoded_image_text = encoded_image.decode("utf-8")
|
||||||
|
base64_qwen = f"data:image;base64,{encoded_image_text}"
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": [
|
||||||
|
{"type": "image", "image": base64_qwen},
|
||||||
|
{"type": "text", "text": "What does the image show?"},
|
||||||
|
],
|
||||||
|
}
|
||||||
|
]
|
||||||
|
text = processor.apply_chat_template(
|
||||||
|
messages, tokenize=False, add_generation_prompt=True
|
||||||
|
)
|
||||||
|
image_inputs, video_inputs = process_vision_info(messages)
|
||||||
|
|
||||||
|
# tokenize
|
||||||
|
return processor(
|
||||||
|
text=[text],
|
||||||
|
images=image_inputs,
|
||||||
|
videos=video_inputs,
|
||||||
|
padding=False,
|
||||||
|
max_length=MAX_SEQUENCE_LENGTH,
|
||||||
|
truncation=True,
|
||||||
|
)
|
||||||
|
ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)
|
||||||
|
|
||||||
|
# Define a oneshot data collator for multimodal inputs.
|
||||||
|
def data_collator(batch):
|
||||||
|
assert len(batch) == 1
|
||||||
|
return {key: torch.tensor(value) for key, value in batch[0].items()}
|
||||||
|
|
||||||
|
recipe = GPTQModifier(
|
||||||
|
targets="Linear",
|
||||||
|
config_groups={
|
||||||
|
"config_group": QuantizationScheme(
|
||||||
|
targets=["Linear"],
|
||||||
|
weights=QuantizationArgs(
|
||||||
|
num_bits=4,
|
||||||
|
type=QuantizationType.INT,
|
||||||
|
strategy=QuantizationStrategy.GROUP,
|
||||||
|
group_size=128,
|
||||||
|
symmetric=True,
|
||||||
|
dynamic=False,
|
||||||
|
actorder=ActivationOrdering.WEIGHT,
|
||||||
|
),
|
||||||
|
),
|
||||||
|
},
|
||||||
|
sequential_targets=["Qwen2_5_VLDecoderLayer"],
|
||||||
|
ignore=["lm_head", "re:visual.*"],
|
||||||
|
update_size=NUM_CALIBRATION_SAMPLES,
|
||||||
|
dampening_frac=dampening_frac
|
||||||
|
)
|
||||||
|
|
||||||
|
SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16"
|
||||||
|
|
||||||
|
# Perform oneshot
|
||||||
|
oneshot(
|
||||||
|
model=model,
|
||||||
|
tokenizer=model_id,
|
||||||
|
dataset=ds,
|
||||||
|
recipe=recipe,
|
||||||
|
max_seq_length=MAX_SEQUENCE_LENGTH,
|
||||||
|
num_calibration_samples=NUM_CALIBRATION_SAMPLES,
|
||||||
|
trust_remote_code_model=True,
|
||||||
|
data_collator=data_collator,
|
||||||
|
output_dir=SAVE_DIR
|
||||||
|
)
|
||||||
|
|
||||||
|
```
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
The model was evaluated using [mistral-evals](https://github.com/neuralmagic/mistral-evals) for vision-related tasks and using [lm_evaluation_harness](https://github.com/neuralmagic/lm-evaluation-harness) for select text-based benchmarks. The evaluations were conducted using the following commands:
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Evaluation Commands</summary>
|
||||||
|
|
||||||
|
### Vision Tasks
|
||||||
|
- vqav2
|
||||||
|
- docvqa
|
||||||
|
- mathvista
|
||||||
|
- mmmu
|
||||||
|
- chartqa
|
||||||
|
|
||||||
|
```
|
||||||
|
vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7
|
||||||
|
|
||||||
|
python -m eval.run eval_vllm \
|
||||||
|
--model_name neuralmagic/pixtral-12b-quantized.w8a8 \
|
||||||
|
--url http://0.0.0.0:8000 \
|
||||||
|
--output_dir ~/tmp \
|
||||||
|
--eval_name <vision_task_name>
|
||||||
|
```
|
||||||
|
|
||||||
|
### Text-based Tasks
|
||||||
|
#### MMLU
|
||||||
|
|
||||||
|
```
|
||||||
|
lm_eval \
|
||||||
|
--model vllm \
|
||||||
|
--model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
|
||||||
|
--tasks mmlu \
|
||||||
|
--num_fewshot 5 \
|
||||||
|
--batch_size auto \
|
||||||
|
--output_path output_dir
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
#### MGSM
|
||||||
|
|
||||||
|
```
|
||||||
|
lm_eval \
|
||||||
|
--model vllm \
|
||||||
|
--model_args pretrained="<model_name>",dtype=auto,max_model_len=4096,max_gen_toks=2048,max_num_seqs=128,tensor_parallel_size=<n>,gpu_memory_utilization=0.9 \
|
||||||
|
--tasks mgsm_cot_native \
|
||||||
|
--apply_chat_template \
|
||||||
|
--num_fewshot 0 \
|
||||||
|
--batch_size auto \
|
||||||
|
--output_path output_dir
|
||||||
|
|
||||||
|
```
|
||||||
|
</details>
|
||||||
|
|
||||||
|
### Accuracy
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th>Category</th>
|
||||||
|
<th>Metric</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<th>Qwen2.5-VL-3B-Instruct-quantized.W4A16</th>
|
||||||
|
<th>Recovery (%)</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<tr>
|
||||||
|
<td rowspan="6"><b>Vision</b></td>
|
||||||
|
<td>MMMU (val, CoT)<br><i>explicit_prompt_relaxed_correctness</i></td>
|
||||||
|
<td>44.56</td>
|
||||||
|
<td>41.56</td>
|
||||||
|
<td>93.28%</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>VQAv2 (val)<br><i>vqa_match</i></td>
|
||||||
|
<td>75.94</td>
|
||||||
|
<td>73.58</td>
|
||||||
|
<td>96.89</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>DocVQA (val)<br><i>anls</i></td>
|
||||||
|
<td>92.53</td>
|
||||||
|
<td>91.58</td>
|
||||||
|
<td>98.97%</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>ChartQA (test, CoT)<br><i>anywhere_in_answer_relaxed_correctness</i></td>
|
||||||
|
<td>81.20</td>
|
||||||
|
<td>78.96</td>
|
||||||
|
<td>97.24%</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>Mathvista (testmini, CoT)<br><i>explicit_prompt_relaxed_correctness</i></td>
|
||||||
|
<td>54.15</td>
|
||||||
|
<td>45.75</td>
|
||||||
|
<td>84.51%</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td><b>Average Score</b></td>
|
||||||
|
<td><b>69.28</b></td>
|
||||||
|
<td><b>66.29</b></td>
|
||||||
|
<td><b>95.68%</b></td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td rowspan="2"><b>Text</b></td>
|
||||||
|
<td>MGSM (CoT)</td>
|
||||||
|
<td>43.69</td>
|
||||||
|
<td>35.82</td>
|
||||||
|
<td>82.00</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<td>MMLU (5-shot)</td>
|
||||||
|
<td>65.32</td>
|
||||||
|
<td>62.80</td>
|
||||||
|
<td>96.14%</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
|
||||||
|
## Inference Performance
|
||||||
|
|
||||||
|
|
||||||
|
This model achieves up to 1.73x speedup in single-stream deployment and up to 3.87x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
|
||||||
|
The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Benchmarking Command</summary>
|
||||||
|
```
|
||||||
|
guidellm --model neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
### Single-stream performance (measured with vLLM version 0.7.2)
|
||||||
|
|
||||||
|
<table border="1" class="dataframe">
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th></th>
|
||||||
|
<th></th>
|
||||||
|
<th></th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Document Visual Question Answering<br>1680W x 2240H<br>64/128</th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Visual Reasoning <br>640W x 480H<br>128/128</th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Image Captioning<br>480W x 360H<br>0/128</th>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>Hardware</th>
|
||||||
|
<th>Model</th>
|
||||||
|
<th>Average Cost Reduction</th>
|
||||||
|
<th>Latency (s)</th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
<th>Latency (s)th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
<th>Latency (s)</th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody style="text-align: center">
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">A6000x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>3.1</td>
|
||||||
|
<td>1454</td>
|
||||||
|
<td>1.8</td>
|
||||||
|
<td>2546</td>
|
||||||
|
<td>1.7</td>
|
||||||
|
<td>2610</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8</th>
|
||||||
|
<td>1.27</td>
|
||||||
|
<td>2.6</td>
|
||||||
|
<td>1708</td>
|
||||||
|
<td>1.3</td>
|
||||||
|
<td>3340</td>
|
||||||
|
<td>1.3</td>
|
||||||
|
<td>3459</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.57</td>
|
||||||
|
<td>2.4</td>
|
||||||
|
<td>1886</td>
|
||||||
|
<td>1.0</td>
|
||||||
|
<td>4409</td>
|
||||||
|
<td>1.0</td>
|
||||||
|
<td>4409</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">A100x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>2.2</td>
|
||||||
|
<td>920</td>
|
||||||
|
<td>1.3</td>
|
||||||
|
<td>1603</td>
|
||||||
|
<td>1.2</td>
|
||||||
|
<td>1636</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8</th>
|
||||||
|
<td>1.09</td>
|
||||||
|
<td>2.1</td>
|
||||||
|
<td>975</td>
|
||||||
|
<td>1.2</td>
|
||||||
|
<td>1743</td>
|
||||||
|
<td>1.1</td>
|
||||||
|
<td>1814</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.20</td>
|
||||||
|
<td>2.0</td>
|
||||||
|
<td>1011</td>
|
||||||
|
<td>1.0</td>
|
||||||
|
<td>2015</td>
|
||||||
|
<td>1.0</td>
|
||||||
|
<td>2012</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">H100x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>1.5</td>
|
||||||
|
<td>740</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1221</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1276</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-FP8-Dynamic</th>
|
||||||
|
<td>1.06</td>
|
||||||
|
<td>1.4</td>
|
||||||
|
<td>768</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1276</td>
|
||||||
|
<td>0.8</td>
|
||||||
|
<td>1399</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.24</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1219</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1270</td>
|
||||||
|
<td>0.8</td>
|
||||||
|
<td>1304</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
|
||||||
|
|
||||||
|
**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
|
||||||
|
|
||||||
|
### Multi-stream asynchronous performance (measured with vLLM version 0.7.2)
|
||||||
|
|
||||||
|
<table border="1" class="dataframe">
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th></th>
|
||||||
|
<th></th>
|
||||||
|
<th></th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Document Visual Question Answering<br>1680W x 2240H<br>64/128</th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Visual Reasoning <br>640W x 480H<br>128/128</th>
|
||||||
|
<th style="text-align: center;" colspan="2" >Image Captioning<br>480W x 360H<br>0/128</th>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>Hardware</th>
|
||||||
|
<th>Model</th>
|
||||||
|
<th>Average Cost Reduction</th>
|
||||||
|
<th>Maximum throughput (QPS)</th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
<th>Maximum throughput (QPS)</th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
<th>Maximum throughput (QPS)</th>
|
||||||
|
<th>Queries Per Dollar</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody style="text-align: center">
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">A6000x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>0.5</td>
|
||||||
|
<td>2405</td>
|
||||||
|
<td>2.6</td>
|
||||||
|
<td>11889</td>
|
||||||
|
<td>2.9</td>
|
||||||
|
<td>12909</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8</th>
|
||||||
|
<td>1.26</td>
|
||||||
|
<td>0.6</td>
|
||||||
|
<td>2725</td>
|
||||||
|
<td>3.4</td>
|
||||||
|
<td>15162</td>
|
||||||
|
<td>3.9</td>
|
||||||
|
<td>17673</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.39</td>
|
||||||
|
<td>0.6</td>
|
||||||
|
<td>2548</td>
|
||||||
|
<td>3.9</td>
|
||||||
|
<td>17437</td>
|
||||||
|
<td>4.7</td>
|
||||||
|
<td>21223</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">A100x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>0.8</td>
|
||||||
|
<td>1663</td>
|
||||||
|
<td>3.9</td>
|
||||||
|
<td>7899</td>
|
||||||
|
<td>4.4</td>
|
||||||
|
<td>8924</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w8a8</th>
|
||||||
|
<td>1.06</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1734</td>
|
||||||
|
<td>4.2</td>
|
||||||
|
<td>8488</td>
|
||||||
|
<td>4.7</td>
|
||||||
|
<td>9548</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.10</td>
|
||||||
|
<td>0.9</td>
|
||||||
|
<td>1775</td>
|
||||||
|
<td>4.2</td>
|
||||||
|
<td>8540</td>
|
||||||
|
<td>5.1</td>
|
||||||
|
<td>10318</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th rowspan="3" valign="top">H100x1</th>
|
||||||
|
<th>Qwen/Qwen2.5-VL-3B-Instruct</th>
|
||||||
|
<td></td>
|
||||||
|
<td>1.1</td>
|
||||||
|
<td>1188</td>
|
||||||
|
<td>4.3</td>
|
||||||
|
<td>4656</td>
|
||||||
|
<td>4.3</td>
|
||||||
|
<td>4676</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-FP8-Dynamic</th>
|
||||||
|
<td>1.15</td>
|
||||||
|
<td>1.4</td>
|
||||||
|
<td>1570</td>
|
||||||
|
<td>4.3</td>
|
||||||
|
<td>4676</td>
|
||||||
|
<td>4.8</td>
|
||||||
|
<td>5220</td>
|
||||||
|
</tr>
|
||||||
|
<tr>
|
||||||
|
<th>neuralmagic/Qwen2.5-VL-3B-Instruct-quantized.w4a16</th>
|
||||||
|
<td>1.96</td>
|
||||||
|
<td>4.2</td>
|
||||||
|
<td>4598</td>
|
||||||
|
<td>4.1</td>
|
||||||
|
<td>4505</td>
|
||||||
|
<td>4.4</td>
|
||||||
|
<td>4838</td>
|
||||||
|
</tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
**Use case profiles: Image Size (WxH) / prompt tokens / generation tokens
|
||||||
|
|
||||||
|
**QPS: Queries per second.
|
||||||
|
|
||||||
|
**QPD: Queries per dollar, based on on-demand cost at [Lambda Labs](https://lambdalabs.com/service/gpu-cloud) (observed on 2/18/2025).
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
|
||||||
|
size 1049
|
||||||
244
config.json
Normal file
244
config.json
Normal file
@@ -0,0 +1,244 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"max_position_embeddings": 128000,
|
||||||
|
"max_window_layers": 70,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"quantization_config": {
|
||||||
|
"config_groups": {
|
||||||
|
"group_0": {
|
||||||
|
"input_activations": null,
|
||||||
|
"output_activations": null,
|
||||||
|
"targets": [
|
||||||
|
"Linear"
|
||||||
|
],
|
||||||
|
"weights": {
|
||||||
|
"actorder": "weight",
|
||||||
|
"block_structure": null,
|
||||||
|
"dynamic": false,
|
||||||
|
"group_size": 128,
|
||||||
|
"num_bits": 4,
|
||||||
|
"observer": "minmax",
|
||||||
|
"observer_kwargs": {},
|
||||||
|
"strategy": "group",
|
||||||
|
"symmetric": true,
|
||||||
|
"type": "int"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"format": "pack-quantized",
|
||||||
|
"global_compression_ratio": 1.3990843687790238,
|
||||||
|
"ignore": [
|
||||||
|
"visual.blocks.0.attn.qkv",
|
||||||
|
"visual.blocks.0.attn.proj",
|
||||||
|
"visual.blocks.0.mlp.gate_proj",
|
||||||
|
"visual.blocks.0.mlp.up_proj",
|
||||||
|
"visual.blocks.0.mlp.down_proj",
|
||||||
|
"visual.blocks.1.attn.qkv",
|
||||||
|
"visual.blocks.1.attn.proj",
|
||||||
|
"visual.blocks.1.mlp.gate_proj",
|
||||||
|
"visual.blocks.1.mlp.up_proj",
|
||||||
|
"visual.blocks.1.mlp.down_proj",
|
||||||
|
"visual.blocks.2.attn.qkv",
|
||||||
|
"visual.blocks.2.attn.proj",
|
||||||
|
"visual.blocks.2.mlp.gate_proj",
|
||||||
|
"visual.blocks.2.mlp.up_proj",
|
||||||
|
"visual.blocks.2.mlp.down_proj",
|
||||||
|
"visual.blocks.3.attn.qkv",
|
||||||
|
"visual.blocks.3.attn.proj",
|
||||||
|
"visual.blocks.3.mlp.gate_proj",
|
||||||
|
"visual.blocks.3.mlp.up_proj",
|
||||||
|
"visual.blocks.3.mlp.down_proj",
|
||||||
|
"visual.blocks.4.attn.qkv",
|
||||||
|
"visual.blocks.4.attn.proj",
|
||||||
|
"visual.blocks.4.mlp.gate_proj",
|
||||||
|
"visual.blocks.4.mlp.up_proj",
|
||||||
|
"visual.blocks.4.mlp.down_proj",
|
||||||
|
"visual.blocks.5.attn.qkv",
|
||||||
|
"visual.blocks.5.attn.proj",
|
||||||
|
"visual.blocks.5.mlp.gate_proj",
|
||||||
|
"visual.blocks.5.mlp.up_proj",
|
||||||
|
"visual.blocks.5.mlp.down_proj",
|
||||||
|
"visual.blocks.6.attn.qkv",
|
||||||
|
"visual.blocks.6.attn.proj",
|
||||||
|
"visual.blocks.6.mlp.gate_proj",
|
||||||
|
"visual.blocks.6.mlp.up_proj",
|
||||||
|
"visual.blocks.6.mlp.down_proj",
|
||||||
|
"visual.blocks.7.attn.qkv",
|
||||||
|
"visual.blocks.7.attn.proj",
|
||||||
|
"visual.blocks.7.mlp.gate_proj",
|
||||||
|
"visual.blocks.7.mlp.up_proj",
|
||||||
|
"visual.blocks.7.mlp.down_proj",
|
||||||
|
"visual.blocks.8.attn.qkv",
|
||||||
|
"visual.blocks.8.attn.proj",
|
||||||
|
"visual.blocks.8.mlp.gate_proj",
|
||||||
|
"visual.blocks.8.mlp.up_proj",
|
||||||
|
"visual.blocks.8.mlp.down_proj",
|
||||||
|
"visual.blocks.9.attn.qkv",
|
||||||
|
"visual.blocks.9.attn.proj",
|
||||||
|
"visual.blocks.9.mlp.gate_proj",
|
||||||
|
"visual.blocks.9.mlp.up_proj",
|
||||||
|
"visual.blocks.9.mlp.down_proj",
|
||||||
|
"visual.blocks.10.attn.qkv",
|
||||||
|
"visual.blocks.10.attn.proj",
|
||||||
|
"visual.blocks.10.mlp.gate_proj",
|
||||||
|
"visual.blocks.10.mlp.up_proj",
|
||||||
|
"visual.blocks.10.mlp.down_proj",
|
||||||
|
"visual.blocks.11.attn.qkv",
|
||||||
|
"visual.blocks.11.attn.proj",
|
||||||
|
"visual.blocks.11.mlp.gate_proj",
|
||||||
|
"visual.blocks.11.mlp.up_proj",
|
||||||
|
"visual.blocks.11.mlp.down_proj",
|
||||||
|
"visual.blocks.12.attn.qkv",
|
||||||
|
"visual.blocks.12.attn.proj",
|
||||||
|
"visual.blocks.12.mlp.gate_proj",
|
||||||
|
"visual.blocks.12.mlp.up_proj",
|
||||||
|
"visual.blocks.12.mlp.down_proj",
|
||||||
|
"visual.blocks.13.attn.qkv",
|
||||||
|
"visual.blocks.13.attn.proj",
|
||||||
|
"visual.blocks.13.mlp.gate_proj",
|
||||||
|
"visual.blocks.13.mlp.up_proj",
|
||||||
|
"visual.blocks.13.mlp.down_proj",
|
||||||
|
"visual.blocks.14.attn.qkv",
|
||||||
|
"visual.blocks.14.attn.proj",
|
||||||
|
"visual.blocks.14.mlp.gate_proj",
|
||||||
|
"visual.blocks.14.mlp.up_proj",
|
||||||
|
"visual.blocks.14.mlp.down_proj",
|
||||||
|
"visual.blocks.15.attn.qkv",
|
||||||
|
"visual.blocks.15.attn.proj",
|
||||||
|
"visual.blocks.15.mlp.gate_proj",
|
||||||
|
"visual.blocks.15.mlp.up_proj",
|
||||||
|
"visual.blocks.15.mlp.down_proj",
|
||||||
|
"visual.blocks.16.attn.qkv",
|
||||||
|
"visual.blocks.16.attn.proj",
|
||||||
|
"visual.blocks.16.mlp.gate_proj",
|
||||||
|
"visual.blocks.16.mlp.up_proj",
|
||||||
|
"visual.blocks.16.mlp.down_proj",
|
||||||
|
"visual.blocks.17.attn.qkv",
|
||||||
|
"visual.blocks.17.attn.proj",
|
||||||
|
"visual.blocks.17.mlp.gate_proj",
|
||||||
|
"visual.blocks.17.mlp.up_proj",
|
||||||
|
"visual.blocks.17.mlp.down_proj",
|
||||||
|
"visual.blocks.18.attn.qkv",
|
||||||
|
"visual.blocks.18.attn.proj",
|
||||||
|
"visual.blocks.18.mlp.gate_proj",
|
||||||
|
"visual.blocks.18.mlp.up_proj",
|
||||||
|
"visual.blocks.18.mlp.down_proj",
|
||||||
|
"visual.blocks.19.attn.qkv",
|
||||||
|
"visual.blocks.19.attn.proj",
|
||||||
|
"visual.blocks.19.mlp.gate_proj",
|
||||||
|
"visual.blocks.19.mlp.up_proj",
|
||||||
|
"visual.blocks.19.mlp.down_proj",
|
||||||
|
"visual.blocks.20.attn.qkv",
|
||||||
|
"visual.blocks.20.attn.proj",
|
||||||
|
"visual.blocks.20.mlp.gate_proj",
|
||||||
|
"visual.blocks.20.mlp.up_proj",
|
||||||
|
"visual.blocks.20.mlp.down_proj",
|
||||||
|
"visual.blocks.21.attn.qkv",
|
||||||
|
"visual.blocks.21.attn.proj",
|
||||||
|
"visual.blocks.21.mlp.gate_proj",
|
||||||
|
"visual.blocks.21.mlp.up_proj",
|
||||||
|
"visual.blocks.21.mlp.down_proj",
|
||||||
|
"visual.blocks.22.attn.qkv",
|
||||||
|
"visual.blocks.22.attn.proj",
|
||||||
|
"visual.blocks.22.mlp.gate_proj",
|
||||||
|
"visual.blocks.22.mlp.up_proj",
|
||||||
|
"visual.blocks.22.mlp.down_proj",
|
||||||
|
"visual.blocks.23.attn.qkv",
|
||||||
|
"visual.blocks.23.attn.proj",
|
||||||
|
"visual.blocks.23.mlp.gate_proj",
|
||||||
|
"visual.blocks.23.mlp.up_proj",
|
||||||
|
"visual.blocks.23.mlp.down_proj",
|
||||||
|
"visual.blocks.24.attn.qkv",
|
||||||
|
"visual.blocks.24.attn.proj",
|
||||||
|
"visual.blocks.24.mlp.gate_proj",
|
||||||
|
"visual.blocks.24.mlp.up_proj",
|
||||||
|
"visual.blocks.24.mlp.down_proj",
|
||||||
|
"visual.blocks.25.attn.qkv",
|
||||||
|
"visual.blocks.25.attn.proj",
|
||||||
|
"visual.blocks.25.mlp.gate_proj",
|
||||||
|
"visual.blocks.25.mlp.up_proj",
|
||||||
|
"visual.blocks.25.mlp.down_proj",
|
||||||
|
"visual.blocks.26.attn.qkv",
|
||||||
|
"visual.blocks.26.attn.proj",
|
||||||
|
"visual.blocks.26.mlp.gate_proj",
|
||||||
|
"visual.blocks.26.mlp.up_proj",
|
||||||
|
"visual.blocks.26.mlp.down_proj",
|
||||||
|
"visual.blocks.27.attn.qkv",
|
||||||
|
"visual.blocks.27.attn.proj",
|
||||||
|
"visual.blocks.27.mlp.gate_proj",
|
||||||
|
"visual.blocks.27.mlp.up_proj",
|
||||||
|
"visual.blocks.27.mlp.down_proj",
|
||||||
|
"visual.blocks.28.attn.qkv",
|
||||||
|
"visual.blocks.28.attn.proj",
|
||||||
|
"visual.blocks.28.mlp.gate_proj",
|
||||||
|
"visual.blocks.28.mlp.up_proj",
|
||||||
|
"visual.blocks.28.mlp.down_proj",
|
||||||
|
"visual.blocks.29.attn.qkv",
|
||||||
|
"visual.blocks.29.attn.proj",
|
||||||
|
"visual.blocks.29.mlp.gate_proj",
|
||||||
|
"visual.blocks.29.mlp.up_proj",
|
||||||
|
"visual.blocks.29.mlp.down_proj",
|
||||||
|
"visual.blocks.30.attn.qkv",
|
||||||
|
"visual.blocks.30.attn.proj",
|
||||||
|
"visual.blocks.30.mlp.gate_proj",
|
||||||
|
"visual.blocks.30.mlp.up_proj",
|
||||||
|
"visual.blocks.30.mlp.down_proj",
|
||||||
|
"visual.blocks.31.attn.qkv",
|
||||||
|
"visual.blocks.31.attn.proj",
|
||||||
|
"visual.blocks.31.mlp.gate_proj",
|
||||||
|
"visual.blocks.31.mlp.up_proj",
|
||||||
|
"visual.blocks.31.mlp.down_proj",
|
||||||
|
"visual.merger.mlp.0",
|
||||||
|
"visual.merger.mlp.2",
|
||||||
|
"lm_head"
|
||||||
|
],
|
||||||
|
"kv_cache_scheme": null,
|
||||||
|
"quant_method": "compressed-tensors",
|
||||||
|
"quantization_status": "compressed",
|
||||||
|
"sparsity_config": {}
|
||||||
|
},
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": {
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
],
|
||||||
|
"rope_type": "default",
|
||||||
|
"type": "default"
|
||||||
|
},
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.49.0.dev0",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"hidden_size": 1280,
|
||||||
|
"in_chans": 3,
|
||||||
|
"model_type": "qwen2_5_vl",
|
||||||
|
"out_hidden_size": 2048,
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"tokens_per_second": 2
|
||||||
|
},
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "image-to-text", "allow_remote": true}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"repetition_penalty": 1.05,
|
||||||
|
"temperature": 0.1,
|
||||||
|
"top_k": 1,
|
||||||
|
"top_p": 0.001,
|
||||||
|
"transformers_version": "4.49.0.dev0"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1811c5fa738747144c60821401a200d4e56339d80377c0c497eb3b341d85ff23
|
||||||
|
size 4013282536
|
||||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"do_convert_rgb": true,
|
||||||
|
"do_normalize": true,
|
||||||
|
"do_rescale": true,
|
||||||
|
"do_resize": true,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2VLImageProcessor",
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"merge_size": 2,
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"patch_size": 14,
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor",
|
||||||
|
"resample": 3,
|
||||||
|
"rescale_factor": 0.00392156862745098,
|
||||||
|
"size": {
|
||||||
|
"longest_edge": 12845056,
|
||||||
|
"shortest_edge": 3136
|
||||||
|
},
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
}
|
||||||
12
recipe.yaml
Normal file
12
recipe.yaml
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
DEFAULT_stage:
|
||||||
|
DEFAULT_modifiers:
|
||||||
|
GPTQModifier:
|
||||||
|
sequential_targets: [Qwen2_5_VLDecoderLayer]
|
||||||
|
dampening_frac: 0.01
|
||||||
|
config_groups:
|
||||||
|
config_group:
|
||||||
|
targets: [Linear]
|
||||||
|
weights: {num_bits: 4, type: int, symmetric: true, group_size: 128, strategy: group,
|
||||||
|
dynamic: false, actorder: weight, observer: minmax}
|
||||||
|
targets: Linear
|
||||||
|
ignore: [lm_head, 're:visual.*']
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
3
tokenizer_config.json
Normal file
3
tokenizer_config.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c182cc5f590489eba7c5435864b0814fcd9256ef72933f8ccc142116974dbb01
|
||||||
|
size 7300
|
||||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user