4bit
/

Image-to-Text
Transformers
Safetensors
English
vlm
text-generation
image-captioning
visual-question-answering
Inference Endpoints
camenduru commited on
Commit
60b3795
1 Parent(s): 998465e

thanks to unum-cloud ❤

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ preview-girl.png filter=lfs diff=lfs merge=lfs -text
37
+ preview-interior.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: image-to-text
3
+ tags:
4
+ - image-captioning
5
+ - visual-question-answering
6
+ datasets:
7
+ - sbu_captions
8
+ - visual_genome
9
+ - HuggingFaceM4/VQAv2
10
+ - ChristophSchuhmann/MS_COCO_2017_URL_TEXT
11
+ language:
12
+ - en
13
+ license: apache-2.0
14
+ base_model: unum-cloud/uform-vl-english
15
+ widget:
16
+ - src: preview-interior.png
17
+ output:
18
+ text: "The living room is cozy, featuring a red leather chair and a white table. The chair is in the center, and the table is on the left side. A lamp on the left side illuminates the space. A large picture hangs on the wall, adding artistic flair. A vase on the table adds a decorative touch. The room is well-lit, creating a warm and inviting atmosphere."
19
+ - src: preview-girl.png
20
+ output:
21
+ text: "A young girl stands in a grassy field, holding an umbrella to shield herself from the rain. She dons a yellow dress and seems to relish her time outdoors. The umbrella is open, offering protection from the rain. The field is bordered by trees, fostering a tranquil and natural ambiance"
22
+ ---
23
+ <Gallery />
24
+
25
+ <h1 align="center">UForm</h1>
26
+ <h3 align="center">
27
+ Pocket-Sized Multimodal AI<br/>
28
+ For Content Understanding and Generation<br/>
29
+ </h3>
30
+
31
+ ## Description
32
+
33
+ UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model consists of two parts:
34
+
35
+ 1. [`uform-vl-english`](https://huggingface.co/unum-cloud/uform-vl-english) visual encoder,
36
+ 2. [`Sheared-LLaMA-1.3B`](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) language model tuned on instruction datasets.
37
+
38
+ The model was pre-trained on: MSCOCO, SBU Captions, Visual Genome, VQAv2, GQA and a few internal datasets.
39
+
40
+ ### Usage
41
+
42
+ ```bash
43
+ pip install uform
44
+ ```
45
+
46
+ The generative model can be used to caption images, summarize their content, or answer questions about them.
47
+ The exact behavior is controlled by prompts.
48
+
49
+ ```python
50
+ from uform.gen_model import VLMForCausalLM, VLMProcessor
51
+
52
+ model = VLMForCausalLM.from_pretrained("unum-cloud/uform-gen")
53
+ processor = VLMProcessor.from_pretrained("unum-cloud/uform-gen")
54
+
55
+ # [cap] Narrate the contents of the image with precision.
56
+ # [cap] Summarize the visual content of the image.
57
+ # [vqa] What is the main subject of the image?
58
+ prompt = "[cap] Summarize the visual content of the image."
59
+ image = Image.open("zebra.jpg")
60
+
61
+ inputs = processor(texts=[prompt], images=[image], return_tensors="pt")
62
+ with torch.inference_mode():
63
+ output = model.generate(
64
+ **inputs,
65
+ do_sample=False,
66
+ use_cache=True,
67
+ max_new_tokens=128,
68
+ eos_token_id=32001,
69
+ pad_token_id=processor.tokenizer.pad_token_id
70
+ )
71
+
72
+ prompt_len = inputs["input_ids"].shape[1]
73
+ decoded_text = processor.batch_decode(output[:, prompt_len:])[0]
74
+ ```
75
+
76
+
77
+ ## Evaluation
78
+
79
+ For captioning evaluation we measure CLIPScore and RefCLIPScore¹.
80
+
81
+ | Model | Size | Caption Length | CLIPScore | RefCLIPScore |
82
+ | :---------------------------------- | ---: | -------------: | --------: | -----------: |
83
+ | `llava-hf/llava-1.5-7b-hf` | 7B | Long | 0.878 | 0.529 |
84
+ | `llava-hf/llava-1.5-7b-hf` | 7B | Short | 0.886 | 0.531 |
85
+ | |
86
+ | `Salesforce/instructblip-vicuna-7b` | 7B | Long | 0.902 | 0.534 |
87
+ | `Salesforce/instructblip-vicuna-7b` | 7B | Short | 0.848 | 0.523 |
88
+ | | |
89
+ | `unum-cloud/uform-gen` | 1.5B | Long | 0.847 | 0.523 |
90
+ | `unum-cloud/uform-gen` | 1.5B | Short | 0.842 | 0.522 |
91
+
92
+ Results for VQAv2 evaluation.
93
+
94
+ | Model | Size | Accuracy |
95
+ | :------------------------- | ---: | -------: |
96
+ | `llava-hf/llava-1.5-7b-hf` | 7B | 78.5 |
97
+ | `unum-cloud/uform-gen` | 1.5B | 66.5 |
98
+
99
+ ¹ We used `apple/DFN5B-CLIP-ViT-H-14-378` CLIP model.
100
+
101
+
102
+ ## Speed
103
+
104
+ On RTX 3090, the following performance is expected on text token generation using `float16`, equivalent PyTorch settings, and greedy decoding.
105
+
106
+ | Model | Size | Speed | Speedup |
107
+ | :---------------------------------- | ---: | ------------------: | --------: |
108
+ | `llava-hf/llava-1.5-7b-hf` | 7B | ~ 40 tokens/second | |
109
+ | `Salesforce/instructblip-vicuna-7b` | 7B | ~ 40 tokens/second | |
110
+ | `unum-cloud/uform-gen` | 1.5B | ~ 140 tokens/second | __x 3.5__ |
111
+
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<image>": 32002,
3
+ "<|im_end|>": 32001,
4
+ "<|im_start|>": 32000
5
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uform-gen",
3
+ "architectures": [
4
+ "VLMForCausalLM"
5
+ ],
6
+ "center_crop": true,
7
+ "image_encoder_embedding_dim": 256,
8
+ "image_encoder_hidden_size": 768,
9
+ "image_encoder_num_heads": 12,
10
+ "image_encoder_num_layers": 12,
11
+ "image_encoder_patch_size": 16,
12
+ "image_encoder_pooling": "cls",
13
+ "image_pooler_intermediate_size": 5504,
14
+ "image_pooler_num_attn_heads": 16,
15
+ "image_pooler_num_latents": 196,
16
+ "image_size": 224,
17
+ "image_token_id": 32002,
18
+ "initializer_range": 0.02,
19
+ "model_type": "vlm",
20
+ "text_decoder_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
21
+ "tokenizer_name_or_path": "unum-cloud/uform-gen",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "use_cache": true
25
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.36.2"
4
+ }
input-girl.jpg ADDED
input-interior.jpg ADDED
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ae42a70765c8dc2d47ed8c5c2cdd7ced413b6d08b58f8983d639b96be87f4b
3
+ size 4984310240
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bff12925d06fc2207053223358a13175d0b698a78b947154182676266dda7f
3
+ size 973984040
model.safetensors.index.json ADDED
@@ -0,0 +1,470 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5958239744
4
+ },
5
+ "weight_map": {
6
+ "image_encoder.blocks.0.attn.key.bias": "model-00002-of-00002.safetensors",
7
+ "image_encoder.blocks.0.attn.key.weight": "model-00002-of-00002.safetensors",
8
+ "image_encoder.blocks.0.attn.out.bias": "model-00002-of-00002.safetensors",
9
+ "image_encoder.blocks.0.attn.out.weight": "model-00002-of-00002.safetensors",
10
+ "image_encoder.blocks.0.attn.query.bias": "model-00002-of-00002.safetensors",
11
+ "image_encoder.blocks.0.attn.query.weight": "model-00002-of-00002.safetensors",
12
+ "image_encoder.blocks.0.attn.value.bias": "model-00002-of-00002.safetensors",
13
+ "image_encoder.blocks.0.attn.value.weight": "model-00002-of-00002.safetensors",
14
+ "image_encoder.blocks.0.ls1.weight": "model-00002-of-00002.safetensors",
15
+ "image_encoder.blocks.0.ls2.weight": "model-00002-of-00002.safetensors",
16
+ "image_encoder.blocks.0.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
17
+ "image_encoder.blocks.0.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
18
+ "image_encoder.blocks.0.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
19
+ "image_encoder.blocks.0.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
20
+ "image_encoder.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
21
+ "image_encoder.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
22
+ "image_encoder.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
23
+ "image_encoder.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
24
+ "image_encoder.blocks.1.attn.key.bias": "model-00002-of-00002.safetensors",
25
+ "image_encoder.blocks.1.attn.key.weight": "model-00002-of-00002.safetensors",
26
+ "image_encoder.blocks.1.attn.out.bias": "model-00002-of-00002.safetensors",
27
+ "image_encoder.blocks.1.attn.out.weight": "model-00002-of-00002.safetensors",
28
+ "image_encoder.blocks.1.attn.query.bias": "model-00002-of-00002.safetensors",
29
+ "image_encoder.blocks.1.attn.query.weight": "model-00002-of-00002.safetensors",
30
+ "image_encoder.blocks.1.attn.value.bias": "model-00002-of-00002.safetensors",
31
+ "image_encoder.blocks.1.attn.value.weight": "model-00002-of-00002.safetensors",
32
+ "image_encoder.blocks.1.ls1.weight": "model-00002-of-00002.safetensors",
33
+ "image_encoder.blocks.1.ls2.weight": "model-00002-of-00002.safetensors",
34
+ "image_encoder.blocks.1.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
35
+ "image_encoder.blocks.1.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
36
+ "image_encoder.blocks.1.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
37
+ "image_encoder.blocks.1.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
38
+ "image_encoder.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
39
+ "image_encoder.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
40
+ "image_encoder.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
41
+ "image_encoder.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
42
+ "image_encoder.blocks.10.attn.key.bias": "model-00002-of-00002.safetensors",
43
+ "image_encoder.blocks.10.attn.key.weight": "model-00002-of-00002.safetensors",
44
+ "image_encoder.blocks.10.attn.out.bias": "model-00002-of-00002.safetensors",
45
+ "image_encoder.blocks.10.attn.out.weight": "model-00002-of-00002.safetensors",
46
+ "image_encoder.blocks.10.attn.query.bias": "model-00002-of-00002.safetensors",
47
+ "image_encoder.blocks.10.attn.query.weight": "model-00002-of-00002.safetensors",
48
+ "image_encoder.blocks.10.attn.value.bias": "model-00002-of-00002.safetensors",
49
+ "image_encoder.blocks.10.attn.value.weight": "model-00002-of-00002.safetensors",
50
+ "image_encoder.blocks.10.ls1.weight": "model-00002-of-00002.safetensors",
51
+ "image_encoder.blocks.10.ls2.weight": "model-00002-of-00002.safetensors",
52
+ "image_encoder.blocks.10.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
53
+ "image_encoder.blocks.10.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
54
+ "image_encoder.blocks.10.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
55
+ "image_encoder.blocks.10.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
56
+ "image_encoder.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
57
+ "image_encoder.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
58
+ "image_encoder.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
59
+ "image_encoder.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
60
+ "image_encoder.blocks.11.attn.key.bias": "model-00002-of-00002.safetensors",
61
+ "image_encoder.blocks.11.attn.key.weight": "model-00002-of-00002.safetensors",
62
+ "image_encoder.blocks.11.attn.out.bias": "model-00002-of-00002.safetensors",
63
+ "image_encoder.blocks.11.attn.out.weight": "model-00002-of-00002.safetensors",
64
+ "image_encoder.blocks.11.attn.query.bias": "model-00002-of-00002.safetensors",
65
+ "image_encoder.blocks.11.attn.query.weight": "model-00002-of-00002.safetensors",
66
+ "image_encoder.blocks.11.attn.value.bias": "model-00002-of-00002.safetensors",
67
+ "image_encoder.blocks.11.attn.value.weight": "model-00002-of-00002.safetensors",
68
+ "image_encoder.blocks.11.ls1.weight": "model-00002-of-00002.safetensors",
69
+ "image_encoder.blocks.11.ls2.weight": "model-00002-of-00002.safetensors",
70
+ "image_encoder.blocks.11.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
71
+ "image_encoder.blocks.11.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
72
+ "image_encoder.blocks.11.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
73
+ "image_encoder.blocks.11.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
74
+ "image_encoder.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
75
+ "image_encoder.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
76
+ "image_encoder.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
77
+ "image_encoder.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
78
+ "image_encoder.blocks.2.attn.key.bias": "model-00002-of-00002.safetensors",
79
+ "image_encoder.blocks.2.attn.key.weight": "model-00002-of-00002.safetensors",
80
+ "image_encoder.blocks.2.attn.out.bias": "model-00002-of-00002.safetensors",
81
+ "image_encoder.blocks.2.attn.out.weight": "model-00002-of-00002.safetensors",
82
+ "image_encoder.blocks.2.attn.query.bias": "model-00002-of-00002.safetensors",
83
+ "image_encoder.blocks.2.attn.query.weight": "model-00002-of-00002.safetensors",
84
+ "image_encoder.blocks.2.attn.value.bias": "model-00002-of-00002.safetensors",
85
+ "image_encoder.blocks.2.attn.value.weight": "model-00002-of-00002.safetensors",
86
+ "image_encoder.blocks.2.ls1.weight": "model-00002-of-00002.safetensors",
87
+ "image_encoder.blocks.2.ls2.weight": "model-00002-of-00002.safetensors",
88
+ "image_encoder.blocks.2.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
89
+ "image_encoder.blocks.2.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
90
+ "image_encoder.blocks.2.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
91
+ "image_encoder.blocks.2.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
92
+ "image_encoder.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
93
+ "image_encoder.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
94
+ "image_encoder.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
95
+ "image_encoder.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
96
+ "image_encoder.blocks.3.attn.key.bias": "model-00002-of-00002.safetensors",
97
+ "image_encoder.blocks.3.attn.key.weight": "model-00002-of-00002.safetensors",
98
+ "image_encoder.blocks.3.attn.out.bias": "model-00002-of-00002.safetensors",
99
+ "image_encoder.blocks.3.attn.out.weight": "model-00002-of-00002.safetensors",
100
+ "image_encoder.blocks.3.attn.query.bias": "model-00002-of-00002.safetensors",
101
+ "image_encoder.blocks.3.attn.query.weight": "model-00002-of-00002.safetensors",
102
+ "image_encoder.blocks.3.attn.value.bias": "model-00002-of-00002.safetensors",
103
+ "image_encoder.blocks.3.attn.value.weight": "model-00002-of-00002.safetensors",
104
+ "image_encoder.blocks.3.ls1.weight": "model-00002-of-00002.safetensors",
105
+ "image_encoder.blocks.3.ls2.weight": "model-00002-of-00002.safetensors",
106
+ "image_encoder.blocks.3.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
107
+ "image_encoder.blocks.3.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
108
+ "image_encoder.blocks.3.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
109
+ "image_encoder.blocks.3.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
110
+ "image_encoder.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
111
+ "image_encoder.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
112
+ "image_encoder.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
113
+ "image_encoder.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
114
+ "image_encoder.blocks.4.attn.key.bias": "model-00002-of-00002.safetensors",
115
+ "image_encoder.blocks.4.attn.key.weight": "model-00002-of-00002.safetensors",
116
+ "image_encoder.blocks.4.attn.out.bias": "model-00002-of-00002.safetensors",
117
+ "image_encoder.blocks.4.attn.out.weight": "model-00002-of-00002.safetensors",
118
+ "image_encoder.blocks.4.attn.query.bias": "model-00002-of-00002.safetensors",
119
+ "image_encoder.blocks.4.attn.query.weight": "model-00002-of-00002.safetensors",
120
+ "image_encoder.blocks.4.attn.value.bias": "model-00002-of-00002.safetensors",
121
+ "image_encoder.blocks.4.attn.value.weight": "model-00002-of-00002.safetensors",
122
+ "image_encoder.blocks.4.ls1.weight": "model-00002-of-00002.safetensors",
123
+ "image_encoder.blocks.4.ls2.weight": "model-00002-of-00002.safetensors",
124
+ "image_encoder.blocks.4.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
125
+ "image_encoder.blocks.4.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
126
+ "image_encoder.blocks.4.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
127
+ "image_encoder.blocks.4.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
128
+ "image_encoder.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
129
+ "image_encoder.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
130
+ "image_encoder.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
131
+ "image_encoder.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
132
+ "image_encoder.blocks.5.attn.key.bias": "model-00002-of-00002.safetensors",
133
+ "image_encoder.blocks.5.attn.key.weight": "model-00002-of-00002.safetensors",
134
+ "image_encoder.blocks.5.attn.out.bias": "model-00002-of-00002.safetensors",
135
+ "image_encoder.blocks.5.attn.out.weight": "model-00002-of-00002.safetensors",
136
+ "image_encoder.blocks.5.attn.query.bias": "model-00002-of-00002.safetensors",
137
+ "image_encoder.blocks.5.attn.query.weight": "model-00002-of-00002.safetensors",
138
+ "image_encoder.blocks.5.attn.value.bias": "model-00002-of-00002.safetensors",
139
+ "image_encoder.blocks.5.attn.value.weight": "model-00002-of-00002.safetensors",
140
+ "image_encoder.blocks.5.ls1.weight": "model-00002-of-00002.safetensors",
141
+ "image_encoder.blocks.5.ls2.weight": "model-00002-of-00002.safetensors",
142
+ "image_encoder.blocks.5.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
143
+ "image_encoder.blocks.5.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
144
+ "image_encoder.blocks.5.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
145
+ "image_encoder.blocks.5.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
146
+ "image_encoder.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
147
+ "image_encoder.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
148
+ "image_encoder.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
149
+ "image_encoder.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
150
+ "image_encoder.blocks.6.attn.key.bias": "model-00002-of-00002.safetensors",
151
+ "image_encoder.blocks.6.attn.key.weight": "model-00002-of-00002.safetensors",
152
+ "image_encoder.blocks.6.attn.out.bias": "model-00002-of-00002.safetensors",
153
+ "image_encoder.blocks.6.attn.out.weight": "model-00002-of-00002.safetensors",
154
+ "image_encoder.blocks.6.attn.query.bias": "model-00002-of-00002.safetensors",
155
+ "image_encoder.blocks.6.attn.query.weight": "model-00002-of-00002.safetensors",
156
+ "image_encoder.blocks.6.attn.value.bias": "model-00002-of-00002.safetensors",
157
+ "image_encoder.blocks.6.attn.value.weight": "model-00002-of-00002.safetensors",
158
+ "image_encoder.blocks.6.ls1.weight": "model-00002-of-00002.safetensors",
159
+ "image_encoder.blocks.6.ls2.weight": "model-00002-of-00002.safetensors",
160
+ "image_encoder.blocks.6.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
161
+ "image_encoder.blocks.6.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
162
+ "image_encoder.blocks.6.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
163
+ "image_encoder.blocks.6.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
164
+ "image_encoder.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
165
+ "image_encoder.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
166
+ "image_encoder.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
167
+ "image_encoder.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
168
+ "image_encoder.blocks.7.attn.key.bias": "model-00002-of-00002.safetensors",
169
+ "image_encoder.blocks.7.attn.key.weight": "model-00002-of-00002.safetensors",
170
+ "image_encoder.blocks.7.attn.out.bias": "model-00002-of-00002.safetensors",
171
+ "image_encoder.blocks.7.attn.out.weight": "model-00002-of-00002.safetensors",
172
+ "image_encoder.blocks.7.attn.query.bias": "model-00002-of-00002.safetensors",
173
+ "image_encoder.blocks.7.attn.query.weight": "model-00002-of-00002.safetensors",
174
+ "image_encoder.blocks.7.attn.value.bias": "model-00002-of-00002.safetensors",
175
+ "image_encoder.blocks.7.attn.value.weight": "model-00002-of-00002.safetensors",
176
+ "image_encoder.blocks.7.ls1.weight": "model-00002-of-00002.safetensors",
177
+ "image_encoder.blocks.7.ls2.weight": "model-00002-of-00002.safetensors",
178
+ "image_encoder.blocks.7.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
179
+ "image_encoder.blocks.7.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
180
+ "image_encoder.blocks.7.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
181
+ "image_encoder.blocks.7.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
182
+ "image_encoder.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
183
+ "image_encoder.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
184
+ "image_encoder.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
185
+ "image_encoder.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
186
+ "image_encoder.blocks.8.attn.key.bias": "model-00002-of-00002.safetensors",
187
+ "image_encoder.blocks.8.attn.key.weight": "model-00002-of-00002.safetensors",
188
+ "image_encoder.blocks.8.attn.out.bias": "model-00002-of-00002.safetensors",
189
+ "image_encoder.blocks.8.attn.out.weight": "model-00002-of-00002.safetensors",
190
+ "image_encoder.blocks.8.attn.query.bias": "model-00002-of-00002.safetensors",
191
+ "image_encoder.blocks.8.attn.query.weight": "model-00002-of-00002.safetensors",
192
+ "image_encoder.blocks.8.attn.value.bias": "model-00002-of-00002.safetensors",
193
+ "image_encoder.blocks.8.attn.value.weight": "model-00002-of-00002.safetensors",
194
+ "image_encoder.blocks.8.ls1.weight": "model-00002-of-00002.safetensors",
195
+ "image_encoder.blocks.8.ls2.weight": "model-00002-of-00002.safetensors",
196
+ "image_encoder.blocks.8.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
197
+ "image_encoder.blocks.8.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
198
+ "image_encoder.blocks.8.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
199
+ "image_encoder.blocks.8.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
200
+ "image_encoder.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
201
+ "image_encoder.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
202
+ "image_encoder.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
203
+ "image_encoder.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
204
+ "image_encoder.blocks.9.attn.key.bias": "model-00002-of-00002.safetensors",
205
+ "image_encoder.blocks.9.attn.key.weight": "model-00002-of-00002.safetensors",
206
+ "image_encoder.blocks.9.attn.out.bias": "model-00002-of-00002.safetensors",
207
+ "image_encoder.blocks.9.attn.out.weight": "model-00002-of-00002.safetensors",
208
+ "image_encoder.blocks.9.attn.query.bias": "model-00002-of-00002.safetensors",
209
+ "image_encoder.blocks.9.attn.query.weight": "model-00002-of-00002.safetensors",
210
+ "image_encoder.blocks.9.attn.value.bias": "model-00002-of-00002.safetensors",
211
+ "image_encoder.blocks.9.attn.value.weight": "model-00002-of-00002.safetensors",
212
+ "image_encoder.blocks.9.ls1.weight": "model-00002-of-00002.safetensors",
213
+ "image_encoder.blocks.9.ls2.weight": "model-00002-of-00002.safetensors",
214
+ "image_encoder.blocks.9.mlp.hidden_layer.bias": "model-00002-of-00002.safetensors",
215
+ "image_encoder.blocks.9.mlp.hidden_layer.weight": "model-00002-of-00002.safetensors",
216
+ "image_encoder.blocks.9.mlp.output_layer.bias": "model-00002-of-00002.safetensors",
217
+ "image_encoder.blocks.9.mlp.output_layer.weight": "model-00002-of-00002.safetensors",
218
+ "image_encoder.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
219
+ "image_encoder.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
220
+ "image_encoder.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
221
+ "image_encoder.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
222
+ "image_encoder.cls_token": "model-00002-of-00002.safetensors",
223
+ "image_encoder.embedding_projection.weight": "model-00002-of-00002.safetensors",
224
+ "image_encoder.norm.bias": "model-00002-of-00002.safetensors",
225
+ "image_encoder.norm.weight": "model-00002-of-00002.safetensors",
226
+ "image_encoder.patch_embed.bias": "model-00002-of-00002.safetensors",
227
+ "image_encoder.patch_embed.weight": "model-00002-of-00002.safetensors",
228
+ "image_encoder.pos_embed": "model-00002-of-00002.safetensors",
229
+ "image_pooler.image_latents": "model-00002-of-00002.safetensors",
230
+ "image_pooler.pooler.linear1.bias": "model-00002-of-00002.safetensors",
231
+ "image_pooler.pooler.linear1.weight": "model-00002-of-00002.safetensors",
232
+ "image_pooler.pooler.linear2.bias": "model-00002-of-00002.safetensors",
233
+ "image_pooler.pooler.linear2.weight": "model-00002-of-00002.safetensors",
234
+ "image_pooler.pooler.multihead_attn.in_proj_bias": "model-00002-of-00002.safetensors",
235
+ "image_pooler.pooler.multihead_attn.in_proj_weight": "model-00002-of-00002.safetensors",
236
+ "image_pooler.pooler.multihead_attn.out_proj.bias": "model-00002-of-00002.safetensors",
237
+ "image_pooler.pooler.multihead_attn.out_proj.weight": "model-00002-of-00002.safetensors",
238
+ "image_pooler.pooler.norm1.bias": "model-00002-of-00002.safetensors",
239
+ "image_pooler.pooler.norm1.weight": "model-00002-of-00002.safetensors",
240
+ "image_pooler.pooler.norm2.bias": "model-00002-of-00002.safetensors",
241
+ "image_pooler.pooler.norm2.weight": "model-00002-of-00002.safetensors",
242
+ "image_pooler.pooler.norm3.bias": "model-00002-of-00002.safetensors",
243
+ "image_pooler.pooler.norm3.weight": "model-00002-of-00002.safetensors",
244
+ "image_pooler.pooler.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
245
+ "image_pooler.pooler.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
246
+ "image_pooler.pooler.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
247
+ "image_pooler.pooler.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
248
+ "image_pooler.projection.bias": "model-00002-of-00002.safetensors",
249
+ "image_pooler.projection.weight": "model-00002-of-00002.safetensors",
250
+ "text_decoder.lm_head.weight": "model-00002-of-00002.safetensors",
251
+ "text_decoder.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
252
+ "text_decoder.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
253
+ "text_decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
254
+ "text_decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
255
+ "text_decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
256
+ "text_decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "text_decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "text_decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "text_decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
+ "text_decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "text_decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "text_decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "text_decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "text_decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "text_decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "text_decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
267
+ "text_decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
268
+ "text_decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
269
+ "text_decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
270
+ "text_decoder.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
271
+ "text_decoder.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
272
+ "text_decoder.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
273
+ "text_decoder.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
274
+ "text_decoder.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
275
+ "text_decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
276
+ "text_decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
277
+ "text_decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
278
+ "text_decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
279
+ "text_decoder.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
280
+ "text_decoder.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
281
+ "text_decoder.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
282
+ "text_decoder.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
283
+ "text_decoder.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "text_decoder.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
285
+ "text_decoder.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
286
+ "text_decoder.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
287
+ "text_decoder.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "text_decoder.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "text_decoder.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
290
+ "text_decoder.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
291
+ "text_decoder.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
292
+ "text_decoder.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "text_decoder.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
294
+ "text_decoder.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
295
+ "text_decoder.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
296
+ "text_decoder.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "text_decoder.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
298
+ "text_decoder.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
299
+ "text_decoder.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
300
+ "text_decoder.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
301
+ "text_decoder.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "text_decoder.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "text_decoder.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
304
+ "text_decoder.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
305
+ "text_decoder.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
306
+ "text_decoder.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
+ "text_decoder.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
308
+ "text_decoder.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
309
+ "text_decoder.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
310
+ "text_decoder.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
311
+ "text_decoder.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "text_decoder.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
313
+ "text_decoder.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
314
+ "text_decoder.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
315
+ "text_decoder.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
316
+ "text_decoder.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
317
+ "text_decoder.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
318
+ "text_decoder.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
319
+ "text_decoder.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
320
+ "text_decoder.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
321
+ "text_decoder.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
322
+ "text_decoder.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
323
+ "text_decoder.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
324
+ "text_decoder.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
325
+ "text_decoder.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
326
+ "text_decoder.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
327
+ "text_decoder.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
328
+ "text_decoder.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "text_decoder.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
330
+ "text_decoder.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
331
+ "text_decoder.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
332
+ "text_decoder.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "text_decoder.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
334
+ "text_decoder.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
335
+ "text_decoder.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
336
+ "text_decoder.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
337
+ "text_decoder.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "text_decoder.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
339
+ "text_decoder.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
340
+ "text_decoder.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
341
+ "text_decoder.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
342
+ "text_decoder.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "text_decoder.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
344
+ "text_decoder.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
345
+ "text_decoder.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
346
+ "text_decoder.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
347
+ "text_decoder.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
348
+ "text_decoder.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
349
+ "text_decoder.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
350
+ "text_decoder.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
351
+ "text_decoder.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
352
+ "text_decoder.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
353
+ "text_decoder.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
354
+ "text_decoder.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
355
+ "text_decoder.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
356
+ "text_decoder.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
357
+ "text_decoder.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
358
+ "text_decoder.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "text_decoder.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "text_decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "text_decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "text_decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "text_decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "text_decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "text_decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
366
+ "text_decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
367
+ "text_decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
368
+ "text_decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
369
+ "text_decoder.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "text_decoder.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
371
+ "text_decoder.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
372
+ "text_decoder.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "text_decoder.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "text_decoder.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "text_decoder.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
376
+ "text_decoder.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "text_decoder.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
378
+ "text_decoder.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
379
+ "text_decoder.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
380
+ "text_decoder.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
381
+ "text_decoder.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
382
+ "text_decoder.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "text_decoder.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
384
+ "text_decoder.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
385
+ "text_decoder.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
386
+ "text_decoder.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
387
+ "text_decoder.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
388
+ "text_decoder.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
389
+ "text_decoder.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
390
+ "text_decoder.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
391
+ "text_decoder.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "text_decoder.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
393
+ "text_decoder.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
394
+ "text_decoder.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
395
+ "text_decoder.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
396
+ "text_decoder.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
397
+ "text_decoder.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
398
+ "text_decoder.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
399
+ "text_decoder.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
400
+ "text_decoder.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
401
+ "text_decoder.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
402
+ "text_decoder.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
403
+ "text_decoder.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "text_decoder.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "text_decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "text_decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
407
+ "text_decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
408
+ "text_decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
409
+ "text_decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
410
+ "text_decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "text_decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
412
+ "text_decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "text_decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
414
+ "text_decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
415
+ "text_decoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
416
+ "text_decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
417
+ "text_decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
418
+ "text_decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
419
+ "text_decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
+ "text_decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
+ "text_decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
422
+ "text_decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
+ "text_decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
424
+ "text_decoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
425
+ "text_decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
426
+ "text_decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
427
+ "text_decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "text_decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
429
+ "text_decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
430
+ "text_decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
431
+ "text_decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
432
+ "text_decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "text_decoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
434
+ "text_decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
435
+ "text_decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
436
+ "text_decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
437
+ "text_decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
438
+ "text_decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
439
+ "text_decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
440
+ "text_decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
441
+ "text_decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "text_decoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
443
+ "text_decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
444
+ "text_decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
445
+ "text_decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
446
+ "text_decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
447
+ "text_decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
448
+ "text_decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
449
+ "text_decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "text_decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
451
+ "text_decoder.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
452
+ "text_decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
453
+ "text_decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
454
+ "text_decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
455
+ "text_decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
456
+ "text_decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
457
+ "text_decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
458
+ "text_decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
459
+ "text_decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
460
+ "text_decoder.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
461
+ "text_decoder.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
462
+ "text_decoder.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
+ "text_decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
464
+ "text_decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
465
+ "text_decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
466
+ "text_decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
467
+ "text_decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
468
+ "text_decoder.model.norm.weight": "model-00002-of-00002.safetensors"
469
+ }
470
+ }
preview-girl.png ADDED

Git LFS Details

  • SHA256: 765fbe907ead3316bbac16656e76648df888b6a4ad1b6945c3a500d0327e7b5c
  • Pointer size: 132 Bytes
  • Size of remote file: 2.89 MB
preview-interior.png ADDED

Git LFS Details

  • SHA256: 73ec696d1fb81753ff1365424772f463267ffe747b43a68acd65367adf314c61
  • Pointer size: 132 Bytes
  • Size of remote file: 1.15 MB
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "32001": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32002": {
46
+ "content": "<image>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ }
53
+ },
54
+ "bos_token": "<s>",
55
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + ' <|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
56
+ "clean_up_tokenization_spaces": false,
57
+ "eos_token": "</s>",
58
+ "max_length": 2048,
59
+ "model_max_length": 1000000000000000019884624838656,
60
+ "pad_token": "</s>",
61
+ "sp_model_kwargs": {},
62
+ "stride": 0,
63
+ "tokenizer_class": "LlamaTokenizer",
64
+ "truncation_side": "left",
65
+ "truncation_strategy": "longest_first",
66
+ "unk_token": "<unk>",
67
+ "use_default_system_prompt": false
68
+ }