初始化项目，由ModelHub XC社区提供模型
Model: swap-uniba/LLaVA-NDiNO_pt_short_it 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
|
||||
79
README.md
Normal file
79
README.md
Normal file
@@ -0,0 +1,79 @@
|
||||
---
|
||||
license: llama3
|
||||
datasets:
|
||||
- swap-uniba/the_cauldron_ita
|
||||
language:
|
||||
- it
|
||||
base_model:
|
||||
- meta-llama/Meta-Llama-3-8B
|
||||
- openai/clip-vit-large-patch14-336
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Model Card for LLaVA-NDiNO_pt_short_it
|
||||
|
||||
## Model description
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
**LLaVA-NDiNO** is a family of *Large Vision Language Models (LVLMs)* that have been trained for the Italian language.
|
||||
|
||||
The model was trained by instruction-tuning [**LLaVA-NDiNO_pt**](https://huggingface.co/m-elio/LLaVA-NDiNO_pt) on an Italian machine-translated version of [The Cauldron](HuggingFaceM4/the_cauldron).
|
||||
|
||||
If you are interested in more details regarding the training procedure, you can find the code we used at the following link:
|
||||
- **Repository:** https://github.com/swapUniba/LLaVA-NDiNO
|
||||
|
||||
- **Developed by:** Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Giovanni Semeraro
|
||||
- **Funded by:** PNRR project FAIR - Future AI Research
|
||||
- **Compute infrastructure:** [Leonardo](https://www.hpc.cineca.it/systems/hardware/leonardo/) supercomputer
|
||||
- **Model type:** LLaMA 3 + CLIP
|
||||
- **Language(s) (NLP):** Italian
|
||||
- **License:** Llama 3 Community License
|
||||
- **Finetuned from model:** [swap-uniba/LLaVA-NDiNO_pt](https://huggingface.co/swap-uniba/LLaVA-NDiNO_pt)
|
||||
|
||||
|
||||
## Example Usage
|
||||
|
||||
```python
|
||||
import torch
|
||||
import requests
|
||||
|
||||
from PIL import Image
|
||||
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration, set_seed
|
||||
|
||||
model_name = "swap-uniba/LLaVA-NDiNO_pt_short_it"
|
||||
|
||||
processor = LlavaNextProcessor.from_pretrained(model_name)
|
||||
model = LlavaNextForConditionalGeneration.from_pretrained(model_name, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto")
|
||||
|
||||
url = "https://www.barnorama.com/wp-content/uploads/2016/12/03-Confusing-Pictures.jpg"
|
||||
image = Image.open(requests.get(url, stream=True).raw)
|
||||
|
||||
chat_template = "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
|
||||
|
||||
conversation = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "<image>\nCosa c'è di strano in questa immagine?"
|
||||
},
|
||||
]
|
||||
|
||||
prompt = processor.apply_chat_template(conversation, chat_template, add_generation_prompt=True)
|
||||
inputs = processor(prompt, image, return_tensors="pt")
|
||||
|
||||
set_seed(42)
|
||||
output = model.generate(**inputs, max_new_tokens=4096)
|
||||
|
||||
print(processor.decode(output[0][inputs.input_ids.shape[1]:]))
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@inproceedings{musacchioLLaVANDiNO,
|
||||
title={LLaVA-NDiNO: Empowering LLMs with Multimodality for the Italian Language},
|
||||
author={Musacchio, Elio and Siciliani, Lucia and Basile, Pierpaolo and Semeraro, Giovanni},
|
||||
booktitle={Proceedings of the Eighth Workshop on Natural Language for Artificial Intelligence (NL4AI 2024) co-located with 23th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2024)},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlavaNextForConditionalGeneration"
|
||||
],
|
||||
"ignore_index": -100,
|
||||
"image_grid_pinpoints": [
|
||||
[
|
||||
336,
|
||||
672
|
||||
],
|
||||
[
|
||||
672,
|
||||
336
|
||||
],
|
||||
[
|
||||
672,
|
||||
672
|
||||
],
|
||||
[
|
||||
1008,
|
||||
336
|
||||
],
|
||||
[
|
||||
336,
|
||||
1008
|
||||
]
|
||||
],
|
||||
"image_token_index": 128256,
|
||||
"model_type": "llava_next",
|
||||
"projector_hidden_act": "gelu",
|
||||
"text_config": {
|
||||
"_name_or_path": "models/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 500000.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"vocab_size": 128320
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.44.0",
|
||||
"use_image_newline_parameter": true,
|
||||
"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"
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"transformers_version": "4.44.0"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b065b077fae1a964bc4a9f97ee601092a835383302ad7375626596ab19a6b0aa
|
||||
size 4955137624
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2fa94ebec82f4bcc45ac1e265dde34965ed28c21133f950e004c55d0689c845d
|
||||
size 4915917552
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e49adca496434d7902a4d7af4b9cf0c6abe8dce2c58be9b14763a7bf97c8805
|
||||
size 4999820824
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3bde642e77b761df51b08d3fe5011c0fc4fa8868180cce79f6a6b50c66cb53f1
|
||||
size 1839769624
|
||||
694
model.safetensors.index.json
Normal file
694
model.safetensors.index.json
Normal file
@@ -0,0 +1,694 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16710553600
|
||||
},
|
||||
"weight_map": {
|
||||
"image_newline": "model-00001-of-00004.safetensors",
|
||||
"language_model.lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
|
||||
"multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
|
||||
"multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
|
||||
"multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00004.safetensors",
|
||||
"vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00004.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": "LlavaNextProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"shortest_edge": 336
|
||||
}
|
||||
}
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410572
tokenizer.json
Normal file
410572
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2071
tokenizer_config.json
Normal file
2071
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user