add checkpoints
Browse files- config.json +47 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "None",
|
| 3 |
+
"additional_vocab_size": 2,
|
| 4 |
+
"alpha_initializer": "zeros",
|
| 5 |
+
"alpha_type": "float",
|
| 6 |
+
"alphas_initializer_range": 0.0,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"VLlamaForCausalLM"
|
| 9 |
+
],
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"cross_layer_activation_function": "swiglu",
|
| 12 |
+
"cross_layer_interval": 4,
|
| 13 |
+
"dropout": 0.0,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"freeze_lm_head": true,
|
| 16 |
+
"freeze_text_layers": true,
|
| 17 |
+
"freeze_text_module_exceptions": [],
|
| 18 |
+
"freeze_vision_layers": true,
|
| 19 |
+
"freeze_vision_module_exceptions": [],
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 4096,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 11008,
|
| 24 |
+
"max_position_embeddings": 2048,
|
| 25 |
+
"max_sequence_length": 2048,
|
| 26 |
+
"model_type": "vllama",
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_hidden_layers": 32,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"qk_layer_norms": true,
|
| 31 |
+
"qk_layer_norms_perceiver": true,
|
| 32 |
+
"resampler_depth": 6,
|
| 33 |
+
"resampler_head_dim": 96,
|
| 34 |
+
"resampler_n_heads": 16,
|
| 35 |
+
"resampler_n_latents": 64,
|
| 36 |
+
"rms_norm_eps": 1e-06,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.28.0.dev0",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"use_resampler": true,
|
| 42 |
+
"vision_embed_dim": 1280,
|
| 43 |
+
"vision_image_size": 224,
|
| 44 |
+
"vision_model_name": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
|
| 45 |
+
"vision_model_params": "{\"id2label\":{}, \"label2id\":{}}",
|
| 46 |
+
"vocab_size": 32000
|
| 47 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.0.dev0"
|
| 7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2676289dcb777a3ad96e1702d750857b67d3a3f278a450fa44d0d669197c5226
|
| 3 |
+
size 9971725808
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1208e8c8a72bbd7852d3049cde371c208748771e1794a740cb4b6a8e280a73d5
|
| 3 |
+
size 7887778480
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c20e9225c6cce75d43b3955e929cc6b8b31174bb0a133b1396225da75227667e
|
| 3 |
+
size 9971911147
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8d3234e836ab51aa50279de8db240763f4bf274eb25ac90887e72f7b111cae7
|
| 3 |
+
size 7887831155
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|