初始化项目，由ModelHub XC社区提供模型
Model: llava-hf/LLaVA-NeXT-Video-7B-hf Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
260
README.md
Normal file
260
README.md
Normal file
@@ -0,0 +1,260 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: llama2
|
||||
pipeline_tag: video-text-to-text
|
||||
datasets:
|
||||
- lmms-lab/VideoChatGPT
|
||||
---
|
||||
|
||||
# LLaVA-NeXT-Video Model Card
|
||||
|
||||
Check out also the Google Colab demo to run Llava on a free-tier Google Colab instance: [](https://colab.research.google.com/drive/1CZggLHrjxMReG-FNOmqSOdi4z7NPq6SO?usp=sharing)
|
||||
|
||||
Disclaimer: The team releasing LLaVa-NeXT-Video did not write a model card for this model so this model card has been written by the Hugging Face team.
|
||||
|
||||
## 📄 Model details
|
||||
|
||||
**Model type:**
|
||||
LLaVA-Next-Video is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. The model is buit on top of LLaVa-NeXT by tuning on a mix of video and image data to achieve better video understanding capabilities. The videos were sampled uniformly to be 32 frames per clip.
|
||||
The model is a current SOTA among open-source models on [VideoMME bench](https://arxiv.org/abs/2405.21075).
|
||||
Base LLM: [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
|
||||
|
||||
|
||||
|
||||
|
||||
**Model date:**
|
||||
LLaVA-Next-Video-7B was trained in April 2024.
|
||||
|
||||
**Paper or resources for more information:** https://github.com/LLaVA-VL/LLaVA-NeXT
|
||||
|
||||
|
||||
## 📚 Training dataset
|
||||
|
||||
### Image
|
||||
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
|
||||
- 158K GPT-generated multimodal instruction-following data.
|
||||
- 500K academic-task-oriented VQA data mixture.
|
||||
- 50K GPT-4V data mixture.
|
||||
- 40K ShareGPT data.
|
||||
|
||||
### Video
|
||||
- 100K VideoChatGPT-Instruct.
|
||||
|
||||
## 📊 Evaluation dataset
|
||||
A collection of 4 benchmarks, including 3 academic VQA benchmarks and 1 captioning benchmark.
|
||||
|
||||
|
||||
|
||||
## 🚀 How to use the model
|
||||
|
||||
First, make sure to have `transformers >= 4.42.0`.
|
||||
The model supports multi-visual and multi-prompt generation. Meaning that you can pass multiple images/videos in your prompt. Make sure also to follow the correct prompt template (`USER: xxx\nASSISTANT:`) and add the token `<image>` or `<video>` to the location where you want to query images/videos:
|
||||
|
||||
Below is an example script to run generation in `float16` precision on a GPU device:
|
||||
|
||||
```python
|
||||
import av
|
||||
import torch
|
||||
import numpy as np
|
||||
from huggingface_hub import hf_hub_download
|
||||
from transformers import LlavaNextVideoProcessor, LlavaNextVideoForConditionalGeneration
|
||||
|
||||
model_id = "llava-hf/LLaVA-NeXT-Video-7B-hf"
|
||||
|
||||
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.float16,
|
||||
low_cpu_mem_usage=True,
|
||||
).to(0)
|
||||
|
||||
processor = LlavaNextVideoProcessor.from_pretrained(model_id)
|
||||
|
||||
def read_video_pyav(container, indices):
|
||||
'''
|
||||
Decode the video with PyAV decoder.
|
||||
Args:
|
||||
container (`av.container.input.InputContainer`): PyAV container.
|
||||
indices (`List[int]`): List of frame indices to decode.
|
||||
Returns:
|
||||
result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
|
||||
'''
|
||||
frames = []
|
||||
container.seek(0)
|
||||
start_index = indices[0]
|
||||
end_index = indices[-1]
|
||||
for i, frame in enumerate(container.decode(video=0)):
|
||||
if i > end_index:
|
||||
break
|
||||
if i >= start_index and i in indices:
|
||||
frames.append(frame)
|
||||
return np.stack([x.to_ndarray(format="rgb24") for x in frames])
|
||||
|
||||
|
||||
# define a chat history and use `apply_chat_template` to get correctly formatted prompt
|
||||
# Each value in "content" has to be a list of dicts with types ("text", "image", "video")
|
||||
conversation = [
|
||||
{
|
||||
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "Why is this video funny?"},
|
||||
{"type": "video"},
|
||||
],
|
||||
},
|
||||
]
|
||||
|
||||
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
|
||||
|
||||
video_path = hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
|
||||
container = av.open(video_path)
|
||||
|
||||
# sample uniformly 8 frames from the video, can sample more for longer videos
|
||||
total_frames = container.streams.video[0].frames
|
||||
indices = np.arange(0, total_frames, total_frames / 8).astype(int)
|
||||
clip = read_video_pyav(container, indices)
|
||||
inputs_video = processor(text=prompt, videos=clip, padding=True, return_tensors="pt").to(model.device)
|
||||
|
||||
output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
|
||||
print(processor.decode(output[0][2:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
-----------
|
||||
From transformers>=v4.48, you can also pass image/video url or local path to the conversation history, and let the chat template handle the rest.
|
||||
For video you also need to indicate how many `num_frames` to sample from video, otherwise the whole video will be loaded.
|
||||
Chat template will load the image/video for you and return inputs in `torch.Tensor` which you can pass directly to `model.generate()`.
|
||||
|
||||
```python
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"}
|
||||
{"type": "video", "path": "my_video.mp4"},
|
||||
{"type": "text", "text": "What is shown in this image and video?"},
|
||||
],
|
||||
},
|
||||
]
|
||||
|
||||
inputs = processor.apply_chat_template(messages, num_frames=8, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors"pt")
|
||||
output = model.generate(**inputs, max_new_tokens=50)
|
||||
```
|
||||
|
||||
|
||||
### Inference with images as inputs
|
||||
|
||||
To generate from images use the below code after loading the model as shown above:
|
||||
|
||||
```python
|
||||
import requests
|
||||
from PIL import Image
|
||||
|
||||
conversation = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "What are these?"},
|
||||
{"type": "image"},
|
||||
],
|
||||
},
|
||||
]
|
||||
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
|
||||
|
||||
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
|
||||
raw_image = Image.open(requests.get(image_file, stream=True).raw)
|
||||
inputs_image = processor(text=prompt, images=raw_image, return_tensors='pt').to(0, torch.float16)
|
||||
|
||||
output = model.generate(**inputs_video, max_new_tokens=100, do_sample=False)
|
||||
print(processor.decode(output[0][2:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
### Inference with images and videos as inputs
|
||||
|
||||
To generate from images and videos in one generate use the below code after loading the model as shown above:
|
||||
|
||||
```python
|
||||
conversation_1 = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "What's the content of the image>"},
|
||||
{"type": "image"},
|
||||
],
|
||||
}
|
||||
]
|
||||
conversation_2 = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": [
|
||||
{"type": "text", "text": "Why is this video funny?"},
|
||||
{"type": "video"},
|
||||
],
|
||||
},
|
||||
]
|
||||
prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
|
||||
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)
|
||||
|
||||
s = processor(text=[prompt_1, prompt_2], images=image, videos=clip, padding=True, return_tensors="pt").to(model.device)
|
||||
|
||||
# Generate
|
||||
generate_ids = model.generate(**inputs, max_new_tokens=100)
|
||||
out = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
|
||||
print(out)
|
||||
```
|
||||
|
||||
### Model optimization
|
||||
|
||||
#### 4-bit quantization through `bitsandbytes` library
|
||||
|
||||
First make sure to install `bitsandbytes`, `pip install bitsandbytes` and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with:
|
||||
|
||||
```diff
|
||||
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.float16,
|
||||
low_cpu_mem_usage=True,
|
||||
+ load_in_4bit=True
|
||||
)
|
||||
```
|
||||
|
||||
#### Use Flash-Attention 2 to further speed-up generation
|
||||
|
||||
First make sure to install `flash-attn`. Refer to the [original repository of Flash Attention](https://github.com/Dao-AILab/flash-attention) regarding that package installation. Simply change the snippet above with:
|
||||
|
||||
```diff
|
||||
model = LlavaNextVideoForConditionalGeneration.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.float16,
|
||||
low_cpu_mem_usage=True,
|
||||
+ use_flash_attention_2=True
|
||||
).to(0)
|
||||
```
|
||||
|
||||
|
||||
## 🔒 License
|
||||
Llama 2 is licensed under the LLAMA 2 Community License,
|
||||
Copyright (c) Meta Platforms, Inc. All Rights Reserved.
|
||||
|
||||
|
||||
## ✏️ Citation
|
||||
If you find our paper and code useful in your research:
|
||||
|
||||
```BibTeX
|
||||
@misc{zhang2024llavanextvideo,
|
||||
title={LLaVA-NeXT: A Strong Zero-shot Video Understanding Model},
|
||||
url={https://llava-vl.github.io/blog/2024-04-30-llava-next-video/},
|
||||
author={Zhang, Yuanhan and Li, Bo and Liu, haotian and Lee, Yong jae and Gui, Liangke and Fu, Di and Feng, Jiashi and Liu, Ziwei and Li, Chunyuan},
|
||||
month={April},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
|
||||
```BibTeX
|
||||
@misc{liu2024llavanext,
|
||||
title={LLaVA-NeXT: Improved reasoning, OCR, and world knowledge},
|
||||
url={https://llava-vl.github.io/blog/2024-01-30-llava-next/},
|
||||
author={Liu, Haotian and Li, Chunyuan and Li, Yuheng and Li, Bo and Zhang, Yuanhan and Shen, Sheng and Lee, Yong Jae},
|
||||
month={January},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<image>": 32001,
|
||||
"<video>": 32000
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
|
||||
}
|
||||
69
config.json
Normal file
69
config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlavaNextVideoForConditionalGeneration"
|
||||
],
|
||||
"ignore_index": -100,
|
||||
"image_grid_pinpoints": [
|
||||
[
|
||||
336,
|
||||
672
|
||||
],
|
||||
[
|
||||
672,
|
||||
336
|
||||
],
|
||||
[
|
||||
672,
|
||||
672
|
||||
],
|
||||
[
|
||||
1008,
|
||||
336
|
||||
],
|
||||
[
|
||||
336,
|
||||
1008
|
||||
]
|
||||
],
|
||||
"image_token_index": 32001,
|
||||
"model_type": "llava_next_video",
|
||||
"projector_hidden_act": "gelu",
|
||||
"spatial_pool_mode": "average",
|
||||
"spatial_pool_out_channels": 1024,
|
||||
"spatial_pool_stride": 2,
|
||||
"text_config": {
|
||||
"_name_or_path": "lmsys/vicuna-7b-v1.5",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"rope_scaling" : {
|
||||
"factor": 2.5,
|
||||
"type": "linear"
|
||||
},
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"torch_dtype": "float16",
|
||||
"type": "linear",
|
||||
"vocab_size": 32064
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.42.0.dev0",
|
||||
"use_image_newline_parameter": true,
|
||||
"video_token_index": 32000,
|
||||
"vision_config": {
|
||||
"hidden_size": 1024,
|
||||
"image_size": 336,
|
||||
"intermediate_size": 4096,
|
||||
"model_type": "clip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"patch_size": 14,
|
||||
"projection_dim": 768,
|
||||
"vocab_size": 32000
|
||||
},
|
||||
"vision_feature_layer": -2,
|
||||
"vision_feature_select_strategy": "default"
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.42.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc32753ce8e75e89748b95677d9349d2b47af998457b4ebe22d27dece7338a3d
|
||||
size 4992938952
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c50112e9dffcb204f90a5be738d28e33b92cd14332cabde6e8f39171d999a1b
|
||||
size 4957878552
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8022077b98e08236a07b999f1f51ab577bda9c8aa2dc66d12853b1b162731100
|
||||
size 4176137496
|
||||
694
model.safetensors.index.json
Normal file
694
model.safetensors.index.json
Normal file
@@ -0,0 +1,694 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14126862336
|
||||
},
|
||||
"weight_map": {
|
||||
"image_newline": "model-00001-of-00003.safetensors",
|
||||
"language_model.lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"language_model.model.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"multi_modal_projector.linear_1.bias": "model-00001-of-00003.safetensors",
|
||||
"multi_modal_projector.linear_1.weight": "model-00001-of-00003.safetensors",
|
||||
"multi_modal_projector.linear_2.bias": "model-00001-of-00003.safetensors",
|
||||
"multi_modal_projector.linear_2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00003.safetensors",
|
||||
"vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
51
preprocessor_config.json
Normal file
51
preprocessor_config.json
Normal file
@@ -0,0 +1,51 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 336,
|
||||
"width": 336
|
||||
},
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_grid_pinpoints": [
|
||||
[
|
||||
336,
|
||||
672
|
||||
],
|
||||
[
|
||||
672,
|
||||
336
|
||||
],
|
||||
[
|
||||
672,
|
||||
672
|
||||
],
|
||||
[
|
||||
1008,
|
||||
336
|
||||
],
|
||||
[
|
||||
336,
|
||||
1008
|
||||
]
|
||||
],
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "LlavaNextImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"processor_class": "LlavaNextVideoProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"shortest_edge": 336
|
||||
}
|
||||
}
|
||||
8
processor_config.json
Normal file
8
processor_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"image_token": "<image>",
|
||||
"video_token": "<video>",
|
||||
"num_additional_image_tokens": 1,
|
||||
"patch_size": 14,
|
||||
"processor_class": "LlavaNextVideoProcessor",
|
||||
"vision_feature_select_strategy": "default"
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93407
tokenizer.json
Normal file
93407
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
66
tokenizer_config.json
Normal file
66
tokenizer_config.json
Normal file
@@ -0,0 +1,66 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<video>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<image>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"extra_special_tokens": {
|
||||
"image_token": "<image>",
|
||||
"video_token": "<video>"
|
||||
},
|
||||
"image_token": "<image>",
|
||||
"legacy": false,
|
||||
"model_max_length": 10250,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "left",
|
||||
"processor_class": "LlavaNextVideoProcessor",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"video_token": "<video>"
|
||||
}
|
||||
63
video_preprocessor_config.json
Normal file
63
video_preprocessor_config.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 336,
|
||||
"width": 336
|
||||
},
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": false,
|
||||
"device": null,
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": false,
|
||||
"fps": null,
|
||||
"image_grid_pinpoints": [
|
||||
[
|
||||
336,
|
||||
672
|
||||
],
|
||||
[
|
||||
672,
|
||||
336
|
||||
],
|
||||
[
|
||||
672,
|
||||
672
|
||||
],
|
||||
[
|
||||
1008,
|
||||
336
|
||||
],
|
||||
[
|
||||
336,
|
||||
1008
|
||||
]
|
||||
],
|
||||
"image_mean": [
|
||||
0.48145466,
|
||||
0.4578275,
|
||||
0.40821073
|
||||
],
|
||||
"image_processor_type": "LlavaNextImageProcessor",
|
||||
"image_std": [
|
||||
0.26862954,
|
||||
0.26130258,
|
||||
0.27577711
|
||||
],
|
||||
"input_data_format": null,
|
||||
"num_frames": null,
|
||||
"pad_size": null,
|
||||
"processor_class": "LlavaNextVideoProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"shortest_edge": 336
|
||||
},
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "LlavaNextVideoVideoProcessor"
|
||||
}
|
||||
Reference in New Issue
Block a user