Upload folder using huggingface_hub
Browse files- config.json +38 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- qwen.tiktoken +0 -0
- special_tokens_map.json +3 -0
- tokenizer_config.json +14 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ucaslcl/GOT-OCR2_0",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GOTQwenForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "ucaslcl/GOT-OCR2_0--modeling_GOT.GOTConfig",
|
| 9 |
+
"AutoModel": "ucaslcl/GOT-OCR2_0--modeling_GOT.GOTQwenForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 151643,
|
| 12 |
+
"eos_token_id": 151643,
|
| 13 |
+
"freeze_vision_tower": false,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 1024,
|
| 16 |
+
"im_end_token": 151858,
|
| 17 |
+
"im_patch_token": 151859,
|
| 18 |
+
"im_start_token": 151857,
|
| 19 |
+
"image_token_len": 256,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 2816,
|
| 22 |
+
"max_position_embeddings": 32768,
|
| 23 |
+
"max_window_layers": 21,
|
| 24 |
+
"model_type": "GOT",
|
| 25 |
+
"num_attention_heads": 16,
|
| 26 |
+
"num_hidden_layers": 24,
|
| 27 |
+
"num_key_value_heads": 16,
|
| 28 |
+
"rms_norm_eps": 1e-06,
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.37.2",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"use_im_start_end": true,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151860
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.37.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a1008a384039d6886c2e82117a4515376fbba97930d382bfee11b8f345afca7
|
| 3 |
+
size 2242169024
|
qwen.tiktoken
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "<|endoftext|>"
|
| 3 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoTokenizer": [
|
| 5 |
+
"ucaslcl/GOT-OCR2_0--tokenization_qwen.QWenTokenizer",
|
| 6 |
+
null
|
| 7 |
+
]
|
| 8 |
+
},
|
| 9 |
+
"clean_up_tokenization_spaces": true,
|
| 10 |
+
"model_max_length": 8000,
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"padding_side": "right",
|
| 13 |
+
"tokenizer_class": "QWenTokenizer"
|
| 14 |
+
}
|