Bagel_local
#25
by
Lakaka19
- opened
- config.json +2 -55
- preprocessor_config.json +0 -24
config.json
CHANGED
|
@@ -1,58 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
-
"model_type": "bagel",
|
| 6 |
-
"visual_gen": true,
|
| 7 |
-
"visual_und": true,
|
| 8 |
-
"llm_config": {
|
| 9 |
-
"architectures": [
|
| 10 |
-
"Qwen2ForCausalLM"
|
| 11 |
-
],
|
| 12 |
-
"attention_dropout": 0.0,
|
| 13 |
-
"bos_token_id": 151643,
|
| 14 |
-
"eos_token_id": 151645,
|
| 15 |
-
"hidden_act": "silu",
|
| 16 |
-
"hidden_size": 3584,
|
| 17 |
-
"initializer_range": 0.02,
|
| 18 |
-
"intermediate_size": 18944,
|
| 19 |
-
"max_position_embeddings": 32768,
|
| 20 |
-
"max_window_layers": 28,
|
| 21 |
-
"model_type": "qwen2",
|
| 22 |
-
"num_attention_heads": 28,
|
| 23 |
-
"num_hidden_layers": 28,
|
| 24 |
-
"num_key_value_heads": 4,
|
| 25 |
-
"qk_norm": true,
|
| 26 |
-
"rms_norm_eps": 1e-06,
|
| 27 |
-
"rope_theta": 1000000.0,
|
| 28 |
-
"sliding_window": 131072,
|
| 29 |
-
"tie_word_embeddings": false,
|
| 30 |
-
"torch_dtype": "bfloat16",
|
| 31 |
-
"transformers_version": "4.43.1",
|
| 32 |
-
"use_cache": true,
|
| 33 |
-
"use_sliding_window": false,
|
| 34 |
-
"vocab_size": 152064
|
| 35 |
-
},
|
| 36 |
-
"vit_config": {
|
| 37 |
-
"hidden_size": 1152,
|
| 38 |
-
"image_size": 980,
|
| 39 |
-
"intermediate_size": 4304,
|
| 40 |
-
"model_type": "siglip_vision_model",
|
| 41 |
-
"num_attention_heads": 16,
|
| 42 |
-
"num_hidden_layers": 27,
|
| 43 |
-
"patch_size": 14,
|
| 44 |
-
"num_channels": 3
|
| 45 |
-
},
|
| 46 |
-
"vae_config": {
|
| 47 |
-
"z_channels": 16,
|
| 48 |
-
"downsample": 8
|
| 49 |
-
},
|
| 50 |
-
"latent_patch_size": 2,
|
| 51 |
-
"max_latent_size": 32,
|
| 52 |
-
"vit_max_num_patch_per_side": 70,
|
| 53 |
-
"connector_act": "gelu_pytorch_tanh",
|
| 54 |
-
"interpolate_pos": false,
|
| 55 |
-
"timestep_shift": 1.0,
|
| 56 |
-
"torch_dtype": "bfloat16",
|
| 57 |
-
"transformers_version": "4.49.0"
|
| 58 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"name": [
|
| 3 |
+
"BAGEL-7B-MoT"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
preprocessor_config.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": true,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.5,
|
| 8 |
-
0.5,
|
| 9 |
-
0.5
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "SiglipImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.5,
|
| 14 |
-
0.5,
|
| 15 |
-
0.5
|
| 16 |
-
],
|
| 17 |
-
"processor_class": "BagelProcessor",
|
| 18 |
-
"rescale_factor": 0.00392156862745098,
|
| 19 |
-
"resample": 3,
|
| 20 |
-
"size": {
|
| 21 |
-
"height": 980,
|
| 22 |
-
"width": 980
|
| 23 |
-
}
|
| 24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|