Upload folder using huggingface_hub
Browse files- README.md +65 -3
- added_tokens.json +5 -0
- config.json +854 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +0 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,65 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# LongVA
|
| 2 |
+
<p align="center">
|
| 3 |
+
<img src="https://i.postimg.cc/4xFmj8wd/v-niah.png" width="800">
|
| 4 |
+
</p>
|
| 5 |
+
|
| 6 |
+
<p align="center">
|
| 7 |
+
🌐 <a href="https://lmms-lab.github.io/posts/longva/" target="_blank">Blog</a> | 📃 <a href="https://arxiv.org/abs/2406.16852" target="_blank">Paper</a> | 🤗 <a href="https://huggingface.co/collections/lmms-lab/longva-667538e09329dbc7ea498057" target="_blank">Hugging Face</a> | 🎥 <a href="https://longva-demo.lmms-lab.com/" target="_blank">Demo</a>
|
| 8 |
+
</p>
|
| 9 |
+
|
| 10 |
+
Long context capability can **zero-shot transfer** from language to vision.
|
| 11 |
+
|
| 12 |
+
LongVA can process **2000** frames or over **200K** visual tokens. It achieves **state-of-the-art** performance on Video-MME among 7B models.
|
| 13 |
+
|
| 14 |
+
# Usage
|
| 15 |
+
|
| 16 |
+
First follow the instructions in [our repo](https://github.com/EvolvingLMMs-Lab/LongVA) to install relevant packages.
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from longva.model.builder import load_pretrained_model
|
| 20 |
+
from longva.mm_utils import tokenizer_image_token, process_images
|
| 21 |
+
from longva.constants import IMAGE_TOKEN_INDEX
|
| 22 |
+
from PIL import Image
|
| 23 |
+
from decord import VideoReader, cpu
|
| 24 |
+
import torch
|
| 25 |
+
import numpy as np
|
| 26 |
+
# fix seed
|
| 27 |
+
torch.manual_seed(0)
|
| 28 |
+
|
| 29 |
+
model_path = "lmms-lab/LongVA-7B-DPO"
|
| 30 |
+
image_path = "local_demo/assets/lmms-eval.png"
|
| 31 |
+
video_path = "local_demo/assets/dc_demo.mp4"
|
| 32 |
+
max_frames_num = 16 # you can change this to several thousands so long you GPU memory can handle it :)
|
| 33 |
+
gen_kwargs = {"do_sample": True, "temperature": 0.5, "top_p": None, "num_beams": 1, "use_cache": True, "max_new_tokens": 1024}
|
| 34 |
+
tokenizer, model, image_processor, _ = load_pretrained_model(model_path, None, "llava_qwen", device_map="cuda:0")
|
| 35 |
+
|
| 36 |
+
#image input
|
| 37 |
+
prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\nDescribe the image in details.<|im_end|>\n<|im_start|>assistant\n"
|
| 38 |
+
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(model.device)
|
| 39 |
+
image = Image.open(image_path).convert("RGB")
|
| 40 |
+
images_tensor = process_images([image], image_processor, model.config).to(model.device, dtype=torch.float16)
|
| 41 |
+
with torch.inference_mode():
|
| 42 |
+
output_ids = model.generate(input_ids, images=images_tensor, image_sizes=[image.size], modalities=["image"], **gen_kwargs)
|
| 43 |
+
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
|
| 44 |
+
print(outputs)
|
| 45 |
+
print("-"*50)
|
| 46 |
+
|
| 47 |
+
#video input
|
| 48 |
+
prompt = "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\nGive a detailed caption of the video as if I am blind.<|im_end|>\n<|im_start|>assistant\n"
|
| 49 |
+
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(model.device)
|
| 50 |
+
vr = VideoReader(video_path, ctx=cpu(0))
|
| 51 |
+
total_frame_num = len(vr)
|
| 52 |
+
uniform_sampled_frames = np.linspace(0, total_frame_num - 1, max_frames_num, dtype=int)
|
| 53 |
+
frame_idx = uniform_sampled_frames.tolist()
|
| 54 |
+
frames = vr.get_batch(frame_idx).asnumpy()
|
| 55 |
+
video_tensor = image_processor.preprocess(frames, return_tensors="pt")["pixel_values"].to(model.device, dtype=torch.float16)
|
| 56 |
+
with torch.inference_mode():
|
| 57 |
+
output_ids = model.generate(input_ids, images=[video_tensor], modalities=["video"], **gen_kwargs)
|
| 58 |
+
outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
|
| 59 |
+
print(outputs)
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
## License
|
| 63 |
+
|
| 64 |
+
This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses, including but not limited to the OpenAI Terms of Use for the dataset and the specific licenses for base language models (Qwen2 license). This project does not impose any additional constraints beyond those stipulated in the original licenses. Furthermore, users are reminded to ensure that their use of the dataset and checkpoints is in compliance with all applicable laws and regulations.
|
| 65 |
+
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,854 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "LongVa/Qwen2-7B-Instruct-extend-step_1000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaQwenForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"image_aspect_ratio": "anyres",
|
| 12 |
+
"image_crop_resolution": null,
|
| 13 |
+
"image_grid_pinpoints": [
|
| 14 |
+
[
|
| 15 |
+
336,
|
| 16 |
+
672
|
| 17 |
+
],
|
| 18 |
+
[
|
| 19 |
+
336,
|
| 20 |
+
1008
|
| 21 |
+
],
|
| 22 |
+
[
|
| 23 |
+
336,
|
| 24 |
+
1344
|
| 25 |
+
],
|
| 26 |
+
[
|
| 27 |
+
336,
|
| 28 |
+
1680
|
| 29 |
+
],
|
| 30 |
+
[
|
| 31 |
+
336,
|
| 32 |
+
2016
|
| 33 |
+
],
|
| 34 |
+
[
|
| 35 |
+
336,
|
| 36 |
+
2352
|
| 37 |
+
],
|
| 38 |
+
[
|
| 39 |
+
336,
|
| 40 |
+
2688
|
| 41 |
+
],
|
| 42 |
+
[
|
| 43 |
+
336,
|
| 44 |
+
3024
|
| 45 |
+
],
|
| 46 |
+
[
|
| 47 |
+
336,
|
| 48 |
+
3360
|
| 49 |
+
],
|
| 50 |
+
[
|
| 51 |
+
336,
|
| 52 |
+
3696
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
336,
|
| 56 |
+
4032
|
| 57 |
+
],
|
| 58 |
+
[
|
| 59 |
+
336,
|
| 60 |
+
4368
|
| 61 |
+
],
|
| 62 |
+
[
|
| 63 |
+
336,
|
| 64 |
+
4704
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
336,
|
| 68 |
+
5040
|
| 69 |
+
],
|
| 70 |
+
[
|
| 71 |
+
336,
|
| 72 |
+
5376
|
| 73 |
+
],
|
| 74 |
+
[
|
| 75 |
+
336,
|
| 76 |
+
5712
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
336,
|
| 80 |
+
6048
|
| 81 |
+
],
|
| 82 |
+
[
|
| 83 |
+
336,
|
| 84 |
+
6384
|
| 85 |
+
],
|
| 86 |
+
[
|
| 87 |
+
336,
|
| 88 |
+
6720
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
336,
|
| 92 |
+
7056
|
| 93 |
+
],
|
| 94 |
+
[
|
| 95 |
+
336,
|
| 96 |
+
7392
|
| 97 |
+
],
|
| 98 |
+
[
|
| 99 |
+
336,
|
| 100 |
+
7728
|
| 101 |
+
],
|
| 102 |
+
[
|
| 103 |
+
336,
|
| 104 |
+
8064
|
| 105 |
+
],
|
| 106 |
+
[
|
| 107 |
+
336,
|
| 108 |
+
8400
|
| 109 |
+
],
|
| 110 |
+
[
|
| 111 |
+
336,
|
| 112 |
+
8736
|
| 113 |
+
],
|
| 114 |
+
[
|
| 115 |
+
336,
|
| 116 |
+
9072
|
| 117 |
+
],
|
| 118 |
+
[
|
| 119 |
+
336,
|
| 120 |
+
9408
|
| 121 |
+
],
|
| 122 |
+
[
|
| 123 |
+
336,
|
| 124 |
+
9744
|
| 125 |
+
],
|
| 126 |
+
[
|
| 127 |
+
336,
|
| 128 |
+
10080
|
| 129 |
+
],
|
| 130 |
+
[
|
| 131 |
+
336,
|
| 132 |
+
10416
|
| 133 |
+
],
|
| 134 |
+
[
|
| 135 |
+
336,
|
| 136 |
+
10752
|
| 137 |
+
],
|
| 138 |
+
[
|
| 139 |
+
336,
|
| 140 |
+
11088
|
| 141 |
+
],
|
| 142 |
+
[
|
| 143 |
+
336,
|
| 144 |
+
11424
|
| 145 |
+
],
|
| 146 |
+
[
|
| 147 |
+
336,
|
| 148 |
+
11760
|
| 149 |
+
],
|
| 150 |
+
[
|
| 151 |
+
336,
|
| 152 |
+
12096
|
| 153 |
+
],
|
| 154 |
+
[
|
| 155 |
+
336,
|
| 156 |
+
12432
|
| 157 |
+
],
|
| 158 |
+
[
|
| 159 |
+
336,
|
| 160 |
+
12768
|
| 161 |
+
],
|
| 162 |
+
[
|
| 163 |
+
336,
|
| 164 |
+
13104
|
| 165 |
+
],
|
| 166 |
+
[
|
| 167 |
+
336,
|
| 168 |
+
13440
|
| 169 |
+
],
|
| 170 |
+
[
|
| 171 |
+
336,
|
| 172 |
+
13776
|
| 173 |
+
],
|
| 174 |
+
[
|
| 175 |
+
336,
|
| 176 |
+
14112
|
| 177 |
+
],
|
| 178 |
+
[
|
| 179 |
+
336,
|
| 180 |
+
14448
|
| 181 |
+
],
|
| 182 |
+
[
|
| 183 |
+
336,
|
| 184 |
+
14784
|
| 185 |
+
],
|
| 186 |
+
[
|
| 187 |
+
336,
|
| 188 |
+
15120
|
| 189 |
+
],
|
| 190 |
+
[
|
| 191 |
+
336,
|
| 192 |
+
15456
|
| 193 |
+
],
|
| 194 |
+
[
|
| 195 |
+
336,
|
| 196 |
+
15792
|
| 197 |
+
],
|
| 198 |
+
[
|
| 199 |
+
336,
|
| 200 |
+
16128
|
| 201 |
+
],
|
| 202 |
+
[
|
| 203 |
+
336,
|
| 204 |
+
16464
|
| 205 |
+
],
|
| 206 |
+
[
|
| 207 |
+
672,
|
| 208 |
+
336
|
| 209 |
+
],
|
| 210 |
+
[
|
| 211 |
+
672,
|
| 212 |
+
672
|
| 213 |
+
],
|
| 214 |
+
[
|
| 215 |
+
672,
|
| 216 |
+
1008
|
| 217 |
+
],
|
| 218 |
+
[
|
| 219 |
+
672,
|
| 220 |
+
1344
|
| 221 |
+
],
|
| 222 |
+
[
|
| 223 |
+
672,
|
| 224 |
+
1680
|
| 225 |
+
],
|
| 226 |
+
[
|
| 227 |
+
672,
|
| 228 |
+
2016
|
| 229 |
+
],
|
| 230 |
+
[
|
| 231 |
+
672,
|
| 232 |
+
2352
|
| 233 |
+
],
|
| 234 |
+
[
|
| 235 |
+
672,
|
| 236 |
+
2688
|
| 237 |
+
],
|
| 238 |
+
[
|
| 239 |
+
672,
|
| 240 |
+
3024
|
| 241 |
+
],
|
| 242 |
+
[
|
| 243 |
+
672,
|
| 244 |
+
3360
|
| 245 |
+
],
|
| 246 |
+
[
|
| 247 |
+
672,
|
| 248 |
+
3696
|
| 249 |
+
],
|
| 250 |
+
[
|
| 251 |
+
672,
|
| 252 |
+
4032
|
| 253 |
+
],
|
| 254 |
+
[
|
| 255 |
+
672,
|
| 256 |
+
4368
|
| 257 |
+
],
|
| 258 |
+
[
|
| 259 |
+
672,
|
| 260 |
+
4704
|
| 261 |
+
],
|
| 262 |
+
[
|
| 263 |
+
672,
|
| 264 |
+
5040
|
| 265 |
+
],
|
| 266 |
+
[
|
| 267 |
+
672,
|
| 268 |
+
5376
|
| 269 |
+
],
|
| 270 |
+
[
|
| 271 |
+
672,
|
| 272 |
+
5712
|
| 273 |
+
],
|
| 274 |
+
[
|
| 275 |
+
672,
|
| 276 |
+
6048
|
| 277 |
+
],
|
| 278 |
+
[
|
| 279 |
+
672,
|
| 280 |
+
6384
|
| 281 |
+
],
|
| 282 |
+
[
|
| 283 |
+
672,
|
| 284 |
+
6720
|
| 285 |
+
],
|
| 286 |
+
[
|
| 287 |
+
672,
|
| 288 |
+
7056
|
| 289 |
+
],
|
| 290 |
+
[
|
| 291 |
+
672,
|
| 292 |
+
7392
|
| 293 |
+
],
|
| 294 |
+
[
|
| 295 |
+
672,
|
| 296 |
+
7728
|
| 297 |
+
],
|
| 298 |
+
[
|
| 299 |
+
672,
|
| 300 |
+
8064
|
| 301 |
+
],
|
| 302 |
+
[
|
| 303 |
+
1008,
|
| 304 |
+
336
|
| 305 |
+
],
|
| 306 |
+
[
|
| 307 |
+
1008,
|
| 308 |
+
672
|
| 309 |
+
],
|
| 310 |
+
[
|
| 311 |
+
1008,
|
| 312 |
+
1008
|
| 313 |
+
],
|
| 314 |
+
[
|
| 315 |
+
1008,
|
| 316 |
+
1344
|
| 317 |
+
],
|
| 318 |
+
[
|
| 319 |
+
1008,
|
| 320 |
+
1680
|
| 321 |
+
],
|
| 322 |
+
[
|
| 323 |
+
1008,
|
| 324 |
+
2016
|
| 325 |
+
],
|
| 326 |
+
[
|
| 327 |
+
1008,
|
| 328 |
+
2352
|
| 329 |
+
],
|
| 330 |
+
[
|
| 331 |
+
1008,
|
| 332 |
+
2688
|
| 333 |
+
],
|
| 334 |
+
[
|
| 335 |
+
1008,
|
| 336 |
+
3024
|
| 337 |
+
],
|
| 338 |
+
[
|
| 339 |
+
1008,
|
| 340 |
+
3360
|
| 341 |
+
],
|
| 342 |
+
[
|
| 343 |
+
1008,
|
| 344 |
+
3696
|
| 345 |
+
],
|
| 346 |
+
[
|
| 347 |
+
1008,
|
| 348 |
+
4032
|
| 349 |
+
],
|
| 350 |
+
[
|
| 351 |
+
1008,
|
| 352 |
+
4368
|
| 353 |
+
],
|
| 354 |
+
[
|
| 355 |
+
1008,
|
| 356 |
+
4704
|
| 357 |
+
],
|
| 358 |
+
[
|
| 359 |
+
1008,
|
| 360 |
+
5040
|
| 361 |
+
],
|
| 362 |
+
[
|
| 363 |
+
1008,
|
| 364 |
+
5376
|
| 365 |
+
],
|
| 366 |
+
[
|
| 367 |
+
1344,
|
| 368 |
+
336
|
| 369 |
+
],
|
| 370 |
+
[
|
| 371 |
+
1344,
|
| 372 |
+
672
|
| 373 |
+
],
|
| 374 |
+
[
|
| 375 |
+
1344,
|
| 376 |
+
1008
|
| 377 |
+
],
|
| 378 |
+
[
|
| 379 |
+
1344,
|
| 380 |
+
1344
|
| 381 |
+
],
|
| 382 |
+
[
|
| 383 |
+
1344,
|
| 384 |
+
1680
|
| 385 |
+
],
|
| 386 |
+
[
|
| 387 |
+
1344,
|
| 388 |
+
2016
|
| 389 |
+
],
|
| 390 |
+
[
|
| 391 |
+
1344,
|
| 392 |
+
2352
|
| 393 |
+
],
|
| 394 |
+
[
|
| 395 |
+
1344,
|
| 396 |
+
2688
|
| 397 |
+
],
|
| 398 |
+
[
|
| 399 |
+
1344,
|
| 400 |
+
3024
|
| 401 |
+
],
|
| 402 |
+
[
|
| 403 |
+
1344,
|
| 404 |
+
3360
|
| 405 |
+
],
|
| 406 |
+
[
|
| 407 |
+
1344,
|
| 408 |
+
3696
|
| 409 |
+
],
|
| 410 |
+
[
|
| 411 |
+
1344,
|
| 412 |
+
4032
|
| 413 |
+
],
|
| 414 |
+
[
|
| 415 |
+
1680,
|
| 416 |
+
336
|
| 417 |
+
],
|
| 418 |
+
[
|
| 419 |
+
1680,
|
| 420 |
+
672
|
| 421 |
+
],
|
| 422 |
+
[
|
| 423 |
+
1680,
|
| 424 |
+
1008
|
| 425 |
+
],
|
| 426 |
+
[
|
| 427 |
+
1680,
|
| 428 |
+
1344
|
| 429 |
+
],
|
| 430 |
+
[
|
| 431 |
+
1680,
|
| 432 |
+
1680
|
| 433 |
+
],
|
| 434 |
+
[
|
| 435 |
+
1680,
|
| 436 |
+
2016
|
| 437 |
+
],
|
| 438 |
+
[
|
| 439 |
+
1680,
|
| 440 |
+
2352
|
| 441 |
+
],
|
| 442 |
+
[
|
| 443 |
+
1680,
|
| 444 |
+
2688
|
| 445 |
+
],
|
| 446 |
+
[
|
| 447 |
+
1680,
|
| 448 |
+
3024
|
| 449 |
+
],
|
| 450 |
+
[
|
| 451 |
+
2016,
|
| 452 |
+
336
|
| 453 |
+
],
|
| 454 |
+
[
|
| 455 |
+
2016,
|
| 456 |
+
672
|
| 457 |
+
],
|
| 458 |
+
[
|
| 459 |
+
2016,
|
| 460 |
+
1008
|
| 461 |
+
],
|
| 462 |
+
[
|
| 463 |
+
2016,
|
| 464 |
+
1344
|
| 465 |
+
],
|
| 466 |
+
[
|
| 467 |
+
2016,
|
| 468 |
+
1680
|
| 469 |
+
],
|
| 470 |
+
[
|
| 471 |
+
2016,
|
| 472 |
+
2016
|
| 473 |
+
],
|
| 474 |
+
[
|
| 475 |
+
2016,
|
| 476 |
+
2352
|
| 477 |
+
],
|
| 478 |
+
[
|
| 479 |
+
2016,
|
| 480 |
+
2688
|
| 481 |
+
],
|
| 482 |
+
[
|
| 483 |
+
2352,
|
| 484 |
+
336
|
| 485 |
+
],
|
| 486 |
+
[
|
| 487 |
+
2352,
|
| 488 |
+
672
|
| 489 |
+
],
|
| 490 |
+
[
|
| 491 |
+
2352,
|
| 492 |
+
1008
|
| 493 |
+
],
|
| 494 |
+
[
|
| 495 |
+
2352,
|
| 496 |
+
1344
|
| 497 |
+
],
|
| 498 |
+
[
|
| 499 |
+
2352,
|
| 500 |
+
1680
|
| 501 |
+
],
|
| 502 |
+
[
|
| 503 |
+
2352,
|
| 504 |
+
2016
|
| 505 |
+
],
|
| 506 |
+
[
|
| 507 |
+
2352,
|
| 508 |
+
2352
|
| 509 |
+
],
|
| 510 |
+
[
|
| 511 |
+
2688,
|
| 512 |
+
336
|
| 513 |
+
],
|
| 514 |
+
[
|
| 515 |
+
2688,
|
| 516 |
+
672
|
| 517 |
+
],
|
| 518 |
+
[
|
| 519 |
+
2688,
|
| 520 |
+
1008
|
| 521 |
+
],
|
| 522 |
+
[
|
| 523 |
+
2688,
|
| 524 |
+
1344
|
| 525 |
+
],
|
| 526 |
+
[
|
| 527 |
+
2688,
|
| 528 |
+
1680
|
| 529 |
+
],
|
| 530 |
+
[
|
| 531 |
+
2688,
|
| 532 |
+
2016
|
| 533 |
+
],
|
| 534 |
+
[
|
| 535 |
+
3024,
|
| 536 |
+
336
|
| 537 |
+
],
|
| 538 |
+
[
|
| 539 |
+
3024,
|
| 540 |
+
672
|
| 541 |
+
],
|
| 542 |
+
[
|
| 543 |
+
3024,
|
| 544 |
+
1008
|
| 545 |
+
],
|
| 546 |
+
[
|
| 547 |
+
3024,
|
| 548 |
+
1344
|
| 549 |
+
],
|
| 550 |
+
[
|
| 551 |
+
3024,
|
| 552 |
+
1680
|
| 553 |
+
],
|
| 554 |
+
[
|
| 555 |
+
3360,
|
| 556 |
+
336
|
| 557 |
+
],
|
| 558 |
+
[
|
| 559 |
+
3360,
|
| 560 |
+
672
|
| 561 |
+
],
|
| 562 |
+
[
|
| 563 |
+
3360,
|
| 564 |
+
1008
|
| 565 |
+
],
|
| 566 |
+
[
|
| 567 |
+
3360,
|
| 568 |
+
1344
|
| 569 |
+
],
|
| 570 |
+
[
|
| 571 |
+
3696,
|
| 572 |
+
336
|
| 573 |
+
],
|
| 574 |
+
[
|
| 575 |
+
3696,
|
| 576 |
+
672
|
| 577 |
+
],
|
| 578 |
+
[
|
| 579 |
+
3696,
|
| 580 |
+
1008
|
| 581 |
+
],
|
| 582 |
+
[
|
| 583 |
+
3696,
|
| 584 |
+
1344
|
| 585 |
+
],
|
| 586 |
+
[
|
| 587 |
+
4032,
|
| 588 |
+
336
|
| 589 |
+
],
|
| 590 |
+
[
|
| 591 |
+
4032,
|
| 592 |
+
672
|
| 593 |
+
],
|
| 594 |
+
[
|
| 595 |
+
4032,
|
| 596 |
+
1008
|
| 597 |
+
],
|
| 598 |
+
[
|
| 599 |
+
4032,
|
| 600 |
+
1344
|
| 601 |
+
],
|
| 602 |
+
[
|
| 603 |
+
4368,
|
| 604 |
+
336
|
| 605 |
+
],
|
| 606 |
+
[
|
| 607 |
+
4368,
|
| 608 |
+
672
|
| 609 |
+
],
|
| 610 |
+
[
|
| 611 |
+
4368,
|
| 612 |
+
1008
|
| 613 |
+
],
|
| 614 |
+
[
|
| 615 |
+
4704,
|
| 616 |
+
336
|
| 617 |
+
],
|
| 618 |
+
[
|
| 619 |
+
4704,
|
| 620 |
+
672
|
| 621 |
+
],
|
| 622 |
+
[
|
| 623 |
+
4704,
|
| 624 |
+
1008
|
| 625 |
+
],
|
| 626 |
+
[
|
| 627 |
+
5040,
|
| 628 |
+
336
|
| 629 |
+
],
|
| 630 |
+
[
|
| 631 |
+
5040,
|
| 632 |
+
672
|
| 633 |
+
],
|
| 634 |
+
[
|
| 635 |
+
5040,
|
| 636 |
+
1008
|
| 637 |
+
],
|
| 638 |
+
[
|
| 639 |
+
5376,
|
| 640 |
+
336
|
| 641 |
+
],
|
| 642 |
+
[
|
| 643 |
+
5376,
|
| 644 |
+
672
|
| 645 |
+
],
|
| 646 |
+
[
|
| 647 |
+
5376,
|
| 648 |
+
1008
|
| 649 |
+
],
|
| 650 |
+
[
|
| 651 |
+
5712,
|
| 652 |
+
336
|
| 653 |
+
],
|
| 654 |
+
[
|
| 655 |
+
5712,
|
| 656 |
+
672
|
| 657 |
+
],
|
| 658 |
+
[
|
| 659 |
+
6048,
|
| 660 |
+
336
|
| 661 |
+
],
|
| 662 |
+
[
|
| 663 |
+
6048,
|
| 664 |
+
672
|
| 665 |
+
],
|
| 666 |
+
[
|
| 667 |
+
6384,
|
| 668 |
+
336
|
| 669 |
+
],
|
| 670 |
+
[
|
| 671 |
+
6384,
|
| 672 |
+
672
|
| 673 |
+
],
|
| 674 |
+
[
|
| 675 |
+
6720,
|
| 676 |
+
336
|
| 677 |
+
],
|
| 678 |
+
[
|
| 679 |
+
6720,
|
| 680 |
+
672
|
| 681 |
+
],
|
| 682 |
+
[
|
| 683 |
+
7056,
|
| 684 |
+
336
|
| 685 |
+
],
|
| 686 |
+
[
|
| 687 |
+
7056,
|
| 688 |
+
672
|
| 689 |
+
],
|
| 690 |
+
[
|
| 691 |
+
7392,
|
| 692 |
+
336
|
| 693 |
+
],
|
| 694 |
+
[
|
| 695 |
+
7392,
|
| 696 |
+
672
|
| 697 |
+
],
|
| 698 |
+
[
|
| 699 |
+
7728,
|
| 700 |
+
336
|
| 701 |
+
],
|
| 702 |
+
[
|
| 703 |
+
7728,
|
| 704 |
+
672
|
| 705 |
+
],
|
| 706 |
+
[
|
| 707 |
+
8064,
|
| 708 |
+
336
|
| 709 |
+
],
|
| 710 |
+
[
|
| 711 |
+
8064,
|
| 712 |
+
672
|
| 713 |
+
],
|
| 714 |
+
[
|
| 715 |
+
8400,
|
| 716 |
+
336
|
| 717 |
+
],
|
| 718 |
+
[
|
| 719 |
+
8736,
|
| 720 |
+
336
|
| 721 |
+
],
|
| 722 |
+
[
|
| 723 |
+
9072,
|
| 724 |
+
336
|
| 725 |
+
],
|
| 726 |
+
[
|
| 727 |
+
9408,
|
| 728 |
+
336
|
| 729 |
+
],
|
| 730 |
+
[
|
| 731 |
+
9744,
|
| 732 |
+
336
|
| 733 |
+
],
|
| 734 |
+
[
|
| 735 |
+
10080,
|
| 736 |
+
336
|
| 737 |
+
],
|
| 738 |
+
[
|
| 739 |
+
10416,
|
| 740 |
+
336
|
| 741 |
+
],
|
| 742 |
+
[
|
| 743 |
+
10752,
|
| 744 |
+
336
|
| 745 |
+
],
|
| 746 |
+
[
|
| 747 |
+
11088,
|
| 748 |
+
336
|
| 749 |
+
],
|
| 750 |
+
[
|
| 751 |
+
11424,
|
| 752 |
+
336
|
| 753 |
+
],
|
| 754 |
+
[
|
| 755 |
+
11760,
|
| 756 |
+
336
|
| 757 |
+
],
|
| 758 |
+
[
|
| 759 |
+
12096,
|
| 760 |
+
336
|
| 761 |
+
],
|
| 762 |
+
[
|
| 763 |
+
12432,
|
| 764 |
+
336
|
| 765 |
+
],
|
| 766 |
+
[
|
| 767 |
+
12768,
|
| 768 |
+
336
|
| 769 |
+
],
|
| 770 |
+
[
|
| 771 |
+
13104,
|
| 772 |
+
336
|
| 773 |
+
],
|
| 774 |
+
[
|
| 775 |
+
13440,
|
| 776 |
+
336
|
| 777 |
+
],
|
| 778 |
+
[
|
| 779 |
+
13776,
|
| 780 |
+
336
|
| 781 |
+
],
|
| 782 |
+
[
|
| 783 |
+
14112,
|
| 784 |
+
336
|
| 785 |
+
],
|
| 786 |
+
[
|
| 787 |
+
14448,
|
| 788 |
+
336
|
| 789 |
+
],
|
| 790 |
+
[
|
| 791 |
+
14784,
|
| 792 |
+
336
|
| 793 |
+
],
|
| 794 |
+
[
|
| 795 |
+
15120,
|
| 796 |
+
336
|
| 797 |
+
],
|
| 798 |
+
[
|
| 799 |
+
15456,
|
| 800 |
+
336
|
| 801 |
+
],
|
| 802 |
+
[
|
| 803 |
+
15792,
|
| 804 |
+
336
|
| 805 |
+
],
|
| 806 |
+
[
|
| 807 |
+
16128,
|
| 808 |
+
336
|
| 809 |
+
],
|
| 810 |
+
[
|
| 811 |
+
16464,
|
| 812 |
+
336
|
| 813 |
+
]
|
| 814 |
+
],
|
| 815 |
+
"image_split_resolution": null,
|
| 816 |
+
"initializer_range": 0.02,
|
| 817 |
+
"intermediate_size": 18944,
|
| 818 |
+
"max_position_embeddings": 224000,
|
| 819 |
+
"max_window_layers": 28,
|
| 820 |
+
"mm_hidden_size": 1024,
|
| 821 |
+
"mm_patch_merge_type": "unires",
|
| 822 |
+
"mm_spatial_pool_mode": "average",
|
| 823 |
+
"mm_spatial_pool_stride": 2,
|
| 824 |
+
"mm_projector_lr": null,
|
| 825 |
+
"mm_projector_type": "mlp2x_gelu",
|
| 826 |
+
"mm_resampler_type": null,
|
| 827 |
+
"mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
|
| 828 |
+
"mm_use_im_patch_token": false,
|
| 829 |
+
"mm_use_im_start_end": false,
|
| 830 |
+
"mm_vision_select_feature": "patch",
|
| 831 |
+
"mm_vision_select_layer": -2,
|
| 832 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 833 |
+
"mm_vision_tower_lr": 2e-06,
|
| 834 |
+
"model_type": "qwen2",
|
| 835 |
+
"num_attention_heads": 28,
|
| 836 |
+
"num_hidden_layers": 28,
|
| 837 |
+
"num_key_value_heads": 4,
|
| 838 |
+
"pos_skipping_range": 4096,
|
| 839 |
+
"rms_norm_eps": 1e-06,
|
| 840 |
+
"rope_scaling": null,
|
| 841 |
+
"rope_theta": 1000000000.0,
|
| 842 |
+
"sliding_window": 131072,
|
| 843 |
+
"tie_word_embeddings": false,
|
| 844 |
+
"tokenizer_model_max_length": 224000,
|
| 845 |
+
"tokenizer_padding_side": "right",
|
| 846 |
+
"torch_dtype": "bfloat16",
|
| 847 |
+
"transformers_version": "4.40.0.dev0",
|
| 848 |
+
"use_cache": true,
|
| 849 |
+
"use_mm_proj": true,
|
| 850 |
+
"use_pos_skipping": false,
|
| 851 |
+
"use_sliding_window": false,
|
| 852 |
+
"vision_tower_pretrained": null,
|
| 853 |
+
"vocab_size": 152064
|
| 854 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation": "flash_attention_2",
|
| 3 |
+
"bos_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"repetition_penalty": 1.05,
|
| 11 |
+
"rope_theta": 1000000000.0,
|
| 12 |
+
"temperature": 0.7,
|
| 13 |
+
"top_k": 20,
|
| 14 |
+
"top_p": 0.8,
|
| 15 |
+
"transformers_version": "4.40.0.dev0"
|
| 16 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30d6a4a41c42a7473aa95a533b2b25c07dc84a7b2c30db117252ccbee2774560
|
| 3 |
+
size 5248280192
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bee317f6776b19aa136b74c9dac54b6e7ad993eb1aa81b1ac6a8312b2d4a9e84
|
| 3 |
+
size 5321822128
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2e9d5ab081a95b1535c8468e892122e10cf3244cc986e4c74eb83cf774203f7
|
| 3 |
+
size 5301290704
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.mm_projector.0.bias": "model-00003-of-00003.safetensors", "model.mm_projector.0.weight": "model-00003-of-00003.safetensors", "model.mm_projector.2.bias": "model-00003-of-00003.safetensors", "model.mm_projector.2.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00003.safetensors", "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00003.safetensors"}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|