Pushpendra817 commited on
Commit
fc0fd43
1 Parent(s): 48dfce3

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +55 -0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/paligemma-3b-mix-224",
3
+ "architectures": [
4
+ "PaliGemmaForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 1,
8
+ "hidden_size": 2048,
9
+ "ignore_index": -100,
10
+ "image_token_index": 257152,
11
+ "model_type": "paligemma",
12
+ "pad_token_id": 0,
13
+ "projection_dim": 2048,
14
+ "quantization_config": {
15
+ "_load_in_4bit": false,
16
+ "_load_in_8bit": true,
17
+ "bnb_4bit_compute_dtype": "float32",
18
+ "bnb_4bit_quant_storage": "uint8",
19
+ "bnb_4bit_quant_type": "fp4",
20
+ "bnb_4bit_use_double_quant": false,
21
+ "llm_int8_enable_fp32_cpu_offload": false,
22
+ "llm_int8_has_fp16_weight": false,
23
+ "llm_int8_skip_modules": null,
24
+ "llm_int8_threshold": 6.0,
25
+ "load_in_4bit": false,
26
+ "load_in_8bit": true,
27
+ "quant_method": "bitsandbytes"
28
+ },
29
+ "text_config": {
30
+ "hidden_size": 2048,
31
+ "intermediate_size": 16384,
32
+ "model_type": "gemma",
33
+ "num_attention_heads": 8,
34
+ "num_hidden_layers": 18,
35
+ "num_image_tokens": 256,
36
+ "num_key_value_heads": 1,
37
+ "torch_dtype": "float32",
38
+ "vocab_size": 257216
39
+ },
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.42.4",
42
+ "vision_config": {
43
+ "hidden_size": 1152,
44
+ "intermediate_size": 4304,
45
+ "model_type": "siglip_vision_model",
46
+ "num_attention_heads": 16,
47
+ "num_hidden_layers": 27,
48
+ "num_image_tokens": 256,
49
+ "patch_size": 14,
50
+ "projection_dim": 2048,
51
+ "projector_hidden_act": "gelu_fast",
52
+ "vision_use_head": false
53
+ },
54
+ "vocab_size": 257216
55
+ }