Initialize
Browse files- added_tokens.json +16 -0
- config.json +82 -0
- configuration_chatglm.py +66 -0
- generation_config.json +10 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
- modeling_chatglm.py +1363 -0
- special_tokens_map.json +32 -0
- tokenization_chatglm.py +361 -0
- tokenizer.model +3 -0
- tokenizer_config.json +134 -0
- visual.py +171 -0
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<eop>": 151334,
|
3 |
+
"<sop>": 151333,
|
4 |
+
"<|assistant|>": 151337,
|
5 |
+
"<|begin_of_image|>": 151339,
|
6 |
+
"<|begin_of_video|>": 151341,
|
7 |
+
"<|end_of_image|>": 151340,
|
8 |
+
"<|end_of_video|>": 151342,
|
9 |
+
"<|endoftext|>": 151329,
|
10 |
+
"<|observation|>": 151338,
|
11 |
+
"<|system|>": 151335,
|
12 |
+
"<|user|>": 151336,
|
13 |
+
"[MASK]": 151330,
|
14 |
+
"[gMASK]": 151331,
|
15 |
+
"[sMASK]": 151332
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../Model",
|
3 |
+
"add_bias_linear": false,
|
4 |
+
"add_qkv_bias": true,
|
5 |
+
"apply_query_key_layer_scaling": true,
|
6 |
+
"apply_residual_connection_post_layernorm": false,
|
7 |
+
"architectures": [
|
8 |
+
"ChatGLMForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"attention_softmax_in_fp32": true,
|
12 |
+
"auto_map": {
|
13 |
+
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
14 |
+
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
15 |
+
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
16 |
+
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
17 |
+
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
|
18 |
+
},
|
19 |
+
"bias_dropout_fusion": true,
|
20 |
+
"boi_token_id": 151339,
|
21 |
+
"classifier_dropout": null,
|
22 |
+
"eoi_token_id": 151340,
|
23 |
+
"eos_token_id": [
|
24 |
+
151329,
|
25 |
+
151336,
|
26 |
+
151338
|
27 |
+
],
|
28 |
+
"ffn_hidden_size": 13696,
|
29 |
+
"fp32_residual_connection": false,
|
30 |
+
"hidden_dropout": 0.0,
|
31 |
+
"hidden_size": 4096,
|
32 |
+
"kv_channels": 128,
|
33 |
+
"layernorm_epsilon": 1.5625e-07,
|
34 |
+
"model_type": "chatglm",
|
35 |
+
"multi_query_attention": true,
|
36 |
+
"multi_query_group_num": 2,
|
37 |
+
"num_attention_heads": 32,
|
38 |
+
"num_layers": 40,
|
39 |
+
"original_rope": true,
|
40 |
+
"pad_token_id": 151329,
|
41 |
+
"padded_vocab_size": 151552,
|
42 |
+
"post_layer_norm": true,
|
43 |
+
"pre_seq_len": null,
|
44 |
+
"prefix_projection": false,
|
45 |
+
"quantization_config": {
|
46 |
+
"_load_in_4bit": true,
|
47 |
+
"_load_in_8bit": false,
|
48 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
49 |
+
"bnb_4bit_quant_storage": "uint8",
|
50 |
+
"bnb_4bit_quant_type": "nf4",
|
51 |
+
"bnb_4bit_use_double_quant": false,
|
52 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
53 |
+
"llm_int8_has_fp16_weight": false,
|
54 |
+
"llm_int8_skip_modules": null,
|
55 |
+
"llm_int8_threshold": 6.0,
|
56 |
+
"load_in_4bit": true,
|
57 |
+
"load_in_8bit": false,
|
58 |
+
"quant_method": "bitsandbytes"
|
59 |
+
},
|
60 |
+
"rmsnorm": true,
|
61 |
+
"rope_ratio": 1,
|
62 |
+
"seq_length": 8192,
|
63 |
+
"tie_word_embeddings": false,
|
64 |
+
"torch_dtype": "bfloat16",
|
65 |
+
"transformers_version": "4.41.2",
|
66 |
+
"use_cache": true,
|
67 |
+
"vision_config": {
|
68 |
+
"dropout_prob": 0.0,
|
69 |
+
"hidden_act": "gelu",
|
70 |
+
"hidden_size": 1792,
|
71 |
+
"image_size": 1120,
|
72 |
+
"in_channels": 3,
|
73 |
+
"intermediate_size": 15360,
|
74 |
+
"layer_norm_eps": 1e-06,
|
75 |
+
"num_heads": 16,
|
76 |
+
"num_hidden_layers": 63,
|
77 |
+
"num_positions": 6401,
|
78 |
+
"patch_size": 14,
|
79 |
+
"scaling_factor": 8
|
80 |
+
},
|
81 |
+
"vocab_size": 151552
|
82 |
+
}
|
configuration_chatglm.py
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import PretrainedConfig
|
2 |
+
|
3 |
+
|
4 |
+
class ChatGLMConfig(PretrainedConfig):
|
5 |
+
model_type = "chatglm"
|
6 |
+
|
7 |
+
def __init__(
|
8 |
+
self,
|
9 |
+
num_layers=28,
|
10 |
+
padded_vocab_size=65024,
|
11 |
+
hidden_size=4096,
|
12 |
+
ffn_hidden_size=13696,
|
13 |
+
kv_channels=128,
|
14 |
+
num_attention_heads=32,
|
15 |
+
seq_length=2048,
|
16 |
+
hidden_dropout=0.0,
|
17 |
+
classifier_dropout=None,
|
18 |
+
attention_dropout=0.0,
|
19 |
+
layernorm_epsilon=1e-5,
|
20 |
+
rmsnorm=True,
|
21 |
+
apply_residual_connection_post_layernorm=False,
|
22 |
+
post_layer_norm=True,
|
23 |
+
add_bias_linear=False,
|
24 |
+
add_qkv_bias=False,
|
25 |
+
bias_dropout_fusion=True,
|
26 |
+
multi_query_attention=False,
|
27 |
+
multi_query_group_num=1,
|
28 |
+
rope_ratio=1,
|
29 |
+
apply_query_key_layer_scaling=True,
|
30 |
+
attention_softmax_in_fp32=True,
|
31 |
+
fp32_residual_connection=False,
|
32 |
+
pre_seq_len=None,
|
33 |
+
prefix_projection=False,
|
34 |
+
boi_token_id=None,
|
35 |
+
eoi_token_id=None,
|
36 |
+
**kwargs
|
37 |
+
):
|
38 |
+
self.num_layers = num_layers
|
39 |
+
self.vocab_size = padded_vocab_size
|
40 |
+
self.padded_vocab_size = padded_vocab_size
|
41 |
+
self.hidden_size = hidden_size
|
42 |
+
self.ffn_hidden_size = ffn_hidden_size
|
43 |
+
self.kv_channels = kv_channels
|
44 |
+
self.num_attention_heads = num_attention_heads
|
45 |
+
self.seq_length = seq_length
|
46 |
+
self.hidden_dropout = hidden_dropout
|
47 |
+
self.classifier_dropout = classifier_dropout
|
48 |
+
self.attention_dropout = attention_dropout
|
49 |
+
self.layernorm_epsilon = layernorm_epsilon
|
50 |
+
self.rmsnorm = rmsnorm
|
51 |
+
self.apply_residual_connection_post_layernorm = apply_residual_connection_post_layernorm
|
52 |
+
self.post_layer_norm = post_layer_norm
|
53 |
+
self.add_bias_linear = add_bias_linear
|
54 |
+
self.add_qkv_bias = add_qkv_bias
|
55 |
+
self.bias_dropout_fusion = bias_dropout_fusion
|
56 |
+
self.multi_query_attention = multi_query_attention
|
57 |
+
self.multi_query_group_num = multi_query_group_num
|
58 |
+
self.rope_ratio = rope_ratio
|
59 |
+
self.apply_query_key_layer_scaling = apply_query_key_layer_scaling
|
60 |
+
self.attention_softmax_in_fp32 = attention_softmax_in_fp32
|
61 |
+
self.fp32_residual_connection = fp32_residual_connection
|
62 |
+
self.pre_seq_len = pre_seq_len
|
63 |
+
self.prefix_projection = prefix_projection
|
64 |
+
self.boi_token_id = boi_token_id
|
65 |
+
self.eoi_token_id = eoi_token_id
|
66 |
+
super().__init__(**kwargs)
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": [
|
4 |
+
151329,
|
5 |
+
151336,
|
6 |
+
151338
|
7 |
+
],
|
8 |
+
"pad_token_id": 151329,
|
9 |
+
"transformers_version": "4.41.2"
|
10 |
+
}
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3637af517517775dbba293981d34556387830424c5e1ea614d44329c1d0de964
|
3 |
+
size 1950093328
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aac439abe184f366ae894cbe82ccfd03d7d253da57c961b6a11d2bceb819c6f
|
3 |
+
size 1950743322
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40d26acb830bf1360f6f6ff851ea32c481545fab860d085bf2da7f5c4d4be667
|
3 |
+
size 1930670222
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ff9de174dfc8c918327940db113a445b98cf66dd753ebeb4aab01c3172a5991
|
3 |
+
size 1988336676
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8928a3a7659753bf9441293430035386a8059ce15dddd097ba839db6b1311ce
|
3 |
+
size 959021969
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
modeling_chatglm.py
ADDED
@@ -0,0 +1,1363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
""" PyTorch ChatGLM model. """
|
2 |
+
import json
|
3 |
+
import math
|
4 |
+
import copy
|
5 |
+
import warnings
|
6 |
+
import re
|
7 |
+
import sys
|
8 |
+
|
9 |
+
import torch
|
10 |
+
import torch.utils.checkpoint
|
11 |
+
import torch.nn.functional as F
|
12 |
+
from torch import nn
|
13 |
+
from torch.nn import CrossEntropyLoss, LayerNorm, MSELoss, BCEWithLogitsLoss
|
14 |
+
from torch.nn.utils import skip_init
|
15 |
+
from typing import Optional, Tuple, Union, List, Callable, Dict, Any
|
16 |
+
from copy import deepcopy
|
17 |
+
|
18 |
+
from transformers.modeling_outputs import (
|
19 |
+
BaseModelOutputWithPast,
|
20 |
+
CausalLMOutputWithPast,
|
21 |
+
SequenceClassifierOutputWithPast,
|
22 |
+
)
|
23 |
+
from transformers.modeling_utils import PreTrainedModel
|
24 |
+
from transformers.utils import logging
|
25 |
+
from transformers.generation.logits_process import LogitsProcessor
|
26 |
+
from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig, ModelOutput
|
27 |
+
|
28 |
+
from .configuration_chatglm import ChatGLMConfig
|
29 |
+
from .visual import EVA2CLIPModel
|
30 |
+
|
31 |
+
# flags required to enable jit fusion kernels
|
32 |
+
|
33 |
+
if sys.platform != 'darwin':
|
34 |
+
torch._C._jit_set_profiling_mode(False)
|
35 |
+
torch._C._jit_set_profiling_executor(False)
|
36 |
+
torch._C._jit_override_can_fuse_on_cpu(True)
|
37 |
+
torch._C._jit_override_can_fuse_on_gpu(True)
|
38 |
+
|
39 |
+
logger = logging.get_logger(__name__)
|
40 |
+
|
41 |
+
LANGUAGE_TOKEN_TYPE = 0
|
42 |
+
VISION_TOKEN_TYPE = 1
|
43 |
+
|
44 |
+
_CHECKPOINT_FOR_DOC = "THUDM/ChatGLM"
|
45 |
+
_CONFIG_FOR_DOC = "ChatGLMConfig"
|
46 |
+
|
47 |
+
CHATGLM_6B_PRETRAINED_MODEL_ARCHIVE_LIST = [
|
48 |
+
"THUDM/chatglm3-6b",
|
49 |
+
# See all ChatGLM models at https://huggingface.co/models?filter=chatglm
|
50 |
+
]
|
51 |
+
|
52 |
+
|
53 |
+
def default_init(cls, *args, **kwargs):
|
54 |
+
return cls(*args, **kwargs)
|
55 |
+
|
56 |
+
|
57 |
+
class InvalidScoreLogitsProcessor(LogitsProcessor):
|
58 |
+
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
|
59 |
+
if torch.isnan(scores).any() or torch.isinf(scores).any():
|
60 |
+
scores.zero_()
|
61 |
+
scores[..., 198] = 5e4
|
62 |
+
return scores
|
63 |
+
|
64 |
+
|
65 |
+
class PrefixEncoder(torch.nn.Module):
|
66 |
+
"""
|
67 |
+
The torch.nn model to encode the prefix
|
68 |
+
Input shape: (batch-size, prefix-length)
|
69 |
+
Output shape: (batch-size, prefix-length, 2*layers*hidden)
|
70 |
+
"""
|
71 |
+
|
72 |
+
def __init__(self, config: ChatGLMConfig):
|
73 |
+
super().__init__()
|
74 |
+
self.prefix_projection = config.prefix_projection
|
75 |
+
if self.prefix_projection:
|
76 |
+
# Use a two-layer MLP to encode the prefix
|
77 |
+
kv_size = config.num_layers * config.kv_channels * config.multi_query_group_num * 2
|
78 |
+
self.embedding = torch.nn.Embedding(config.pre_seq_len, kv_size)
|
79 |
+
self.trans = torch.nn.Sequential(
|
80 |
+
torch.nn.Linear(kv_size, config.hidden_size),
|
81 |
+
torch.nn.Tanh(),
|
82 |
+
torch.nn.Linear(config.hidden_size, kv_size)
|
83 |
+
)
|
84 |
+
else:
|
85 |
+
self.embedding = torch.nn.Embedding(config.pre_seq_len,
|
86 |
+
config.num_layers * config.kv_channels * config.multi_query_group_num * 2)
|
87 |
+
|
88 |
+
def forward(self, prefix: torch.Tensor):
|
89 |
+
if self.prefix_projection:
|
90 |
+
prefix_tokens = self.embedding(prefix)
|
91 |
+
past_key_values = self.trans(prefix_tokens)
|
92 |
+
else:
|
93 |
+
past_key_values = self.embedding(prefix)
|
94 |
+
return past_key_values
|
95 |
+
|
96 |
+
|
97 |
+
def split_tensor_along_last_dim(
|
98 |
+
tensor: torch.Tensor,
|
99 |
+
num_partitions: int,
|
100 |
+
contiguous_split_chunks: bool = False,
|
101 |
+
) -> List[torch.Tensor]:
|
102 |
+
"""Split a tensor along its last dimension.
|
103 |
+
|
104 |
+
Arguments:
|
105 |
+
tensor: input tensor.
|
106 |
+
num_partitions: number of partitions to split the tensor
|
107 |
+
contiguous_split_chunks: If True, make each chunk contiguous
|
108 |
+
in memory.
|
109 |
+
|
110 |
+
Returns:
|
111 |
+
A list of Tensors
|
112 |
+
"""
|
113 |
+
# Get the size and dimension.
|
114 |
+
last_dim = tensor.dim() - 1
|
115 |
+
last_dim_size = tensor.size()[last_dim] // num_partitions
|
116 |
+
# Split.
|
117 |
+
tensor_list = torch.split(tensor, last_dim_size, dim=last_dim)
|
118 |
+
# Note: torch.split does not create contiguous tensors by default.
|
119 |
+
if contiguous_split_chunks:
|
120 |
+
return tuple(chunk.contiguous() for chunk in tensor_list)
|
121 |
+
|
122 |
+
return tensor_list
|
123 |
+
|
124 |
+
|
125 |
+
class RotaryEmbedding(nn.Module):
|
126 |
+
def __init__(self, dim, rope_ratio=1, original_impl=False, device=None, dtype=None):
|
127 |
+
super().__init__()
|
128 |
+
inv_freq = 1.0 / (10000 ** (torch.arange(0, dim, 2, device=device).to(dtype=dtype) / dim))
|
129 |
+
self.register_buffer("inv_freq", inv_freq)
|
130 |
+
self.dim = dim
|
131 |
+
self.original_impl = original_impl
|
132 |
+
self.rope_ratio = rope_ratio
|
133 |
+
|
134 |
+
def impl(self, seq_length: int, dim: int, device: torch.device, dtype: torch.dtype):
|
135 |
+
base = 10000 * self.rope_ratio
|
136 |
+
inv_freq = 1.0 / (
|
137 |
+
base ** (torch.arange(0, dim, 2, device=device, dtype=torch.float32) / dim))
|
138 |
+
seq = torch.arange(seq_length, device=inv_freq.device, dtype=torch.float32)
|
139 |
+
freqs = torch.outer(seq, inv_freq)
|
140 |
+
# first part even vector components, second part odd vector components,
|
141 |
+
# 2 * dim in dimension size
|
142 |
+
emb = torch.cat((freqs, freqs), dim=-1)
|
143 |
+
return emb
|
144 |
+
|
145 |
+
def forward_impl(
|
146 |
+
self, seq_len: int, n_elem: int, dtype: torch.dtype, device: torch.device, base: int = 10000
|
147 |
+
):
|
148 |
+
"""Enhanced Transformer with Rotary Position Embedding.
|
149 |
+
|
150 |
+
Derived from: https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/
|
151 |
+
transformers/rope/__init__.py. MIT License:
|
152 |
+
https://github.com/labmlai/annotated_deep_learning_paper_implementations/blob/master/license.
|
153 |
+
"""
|
154 |
+
# $\Theta = {\theta_i = 10000^{\frac{2(i-1)}{d}}, i \in [1, 2, ..., \frac{d}{2}]}$
|
155 |
+
base = base * self.rope_ratio
|
156 |
+
theta = 1.0 / (base ** (torch.arange(0, n_elem, 2, dtype=torch.float, device=device) / n_elem))
|
157 |
+
|
158 |
+
# Create position indexes `[0, 1, ..., seq_len - 1]`
|
159 |
+
seq_idx = torch.arange(seq_len, dtype=torch.float, device=device)
|
160 |
+
|
161 |
+
# Calculate the product of position index and $\theta_i$
|
162 |
+
idx_theta = torch.outer(seq_idx, theta).float()
|
163 |
+
|
164 |
+
cache = torch.stack([torch.cos(idx_theta), torch.sin(idx_theta)], dim=-1)
|
165 |
+
|
166 |
+
# this is to mimic the behaviour of complex32, else we will get different results
|
167 |
+
if dtype in (torch.float16, torch.bfloat16, torch.int8):
|
168 |
+
cache = cache.bfloat16() if dtype == torch.bfloat16 else cache.half()
|
169 |
+
return cache
|
170 |
+
|
171 |
+
def forward(self, max_seq_len, offset=0):
|
172 |
+
if self.original_impl:
|
173 |
+
return self.forward_impl(
|
174 |
+
max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device
|
175 |
+
)
|
176 |
+
else:
|
177 |
+
return self.impl(max_seq_len, self.dim, dtype=self.inv_freq.dtype, device=self.inv_freq.device)
|
178 |
+
|
179 |
+
|
180 |
+
@torch.jit.script
|
181 |
+
def apply_rotary_pos_emb(x: torch.Tensor, rope_cache: torch.Tensor) -> torch.Tensor:
|
182 |
+
# x: [b, np, sq, hn]
|
183 |
+
b, np, sq, hn = x.size(0), x.size(1), x.size(2), x.size(3)
|
184 |
+
rot_dim = rope_cache.shape[-2] * 2
|
185 |
+
x, x_pass = x[..., :rot_dim], x[..., rot_dim:]
|
186 |
+
# truncate to support variable sizes
|
187 |
+
rope_cache = rope_cache[:, :sq]
|
188 |
+
xshaped = x.reshape(b, np, sq, rot_dim // 2, 2)
|
189 |
+
rope_cache = rope_cache.view(-1, 1, sq, xshaped.size(3), 2)
|
190 |
+
x_out2 = torch.stack(
|
191 |
+
[
|
192 |
+
xshaped[..., 0] * rope_cache[..., 0] - xshaped[..., 1] * rope_cache[..., 1],
|
193 |
+
xshaped[..., 1] * rope_cache[..., 0] + xshaped[..., 0] * rope_cache[..., 1],
|
194 |
+
],
|
195 |
+
-1,
|
196 |
+
)
|
197 |
+
x_out2 = x_out2.flatten(3)
|
198 |
+
return torch.cat((x_out2, x_pass), dim=-1)
|
199 |
+
|
200 |
+
|
201 |
+
class RMSNorm(torch.nn.Module):
|
202 |
+
def __init__(self, normalized_shape, eps=1e-5, device=None, dtype=None, **kwargs):
|
203 |
+
super().__init__()
|
204 |
+
self.weight = torch.nn.Parameter(torch.empty(normalized_shape, device=device, dtype=dtype))
|
205 |
+
self.eps = eps
|
206 |
+
|
207 |
+
def forward(self, hidden_states: torch.Tensor):
|
208 |
+
input_dtype = hidden_states.dtype
|
209 |
+
variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
|
210 |
+
hidden_states = hidden_states * torch.rsqrt(variance + self.eps)
|
211 |
+
|
212 |
+
return (self.weight * hidden_states).to(input_dtype)
|
213 |
+
|
214 |
+
|
215 |
+
class CoreAttention(torch.nn.Module):
|
216 |
+
def __init__(self, config: ChatGLMConfig, layer_number):
|
217 |
+
super(CoreAttention, self).__init__()
|
218 |
+
|
219 |
+
self.apply_query_key_layer_scaling = config.apply_query_key_layer_scaling
|
220 |
+
self.attention_softmax_in_fp32 = config.attention_softmax_in_fp32
|
221 |
+
if self.apply_query_key_layer_scaling:
|
222 |
+
self.attention_softmax_in_fp32 = True
|
223 |
+
self.layer_number = max(1, layer_number)
|
224 |
+
|
225 |
+
projection_size = config.kv_channels * config.num_attention_heads
|
226 |
+
|
227 |
+
# Per attention head and per partition values.
|
228 |
+
self.hidden_size_per_partition = projection_size
|
229 |
+
self.hidden_size_per_attention_head = projection_size // config.num_attention_heads
|
230 |
+
self.num_attention_heads_per_partition = config.num_attention_heads
|
231 |
+
|
232 |
+
coeff = None
|
233 |
+
self.norm_factor = math.sqrt(self.hidden_size_per_attention_head)
|
234 |
+
if self.apply_query_key_layer_scaling:
|
235 |
+
coeff = self.layer_number
|
236 |
+
self.norm_factor *= coeff
|
237 |
+
self.coeff = coeff
|
238 |
+
|
239 |
+
self.attention_dropout = torch.nn.Dropout(config.attention_dropout)
|
240 |
+
|
241 |
+
def forward(self, query_layer, key_layer, value_layer, attention_mask):
|
242 |
+
pytorch_major_version = int(torch.__version__.split('.')[0])
|
243 |
+
if pytorch_major_version >= 2:
|
244 |
+
if attention_mask is None and query_layer.shape[2] == key_layer.shape[2]:
|
245 |
+
context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
|
246 |
+
is_causal=True)
|
247 |
+
else:
|
248 |
+
if attention_mask is not None:
|
249 |
+
attention_mask = ~attention_mask
|
250 |
+
context_layer = torch.nn.functional.scaled_dot_product_attention(query_layer, key_layer, value_layer,
|
251 |
+
attention_mask)
|
252 |
+
context_layer = context_layer.transpose(1, 2).contiguous()
|
253 |
+
new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
|
254 |
+
context_layer = context_layer.reshape(*new_context_layer_shape)
|
255 |
+
else:
|
256 |
+
# Raw attention scores
|
257 |
+
|
258 |
+
# [b, np, sq, sk]
|
259 |
+
output_size = (query_layer.size(0), query_layer.size(1), query_layer.size(2), key_layer.size(2))
|
260 |
+
|
261 |
+
# [b, np, sq, hn] -> [b * np, sq, hn]
|
262 |
+
query_layer = query_layer.view(output_size[0] * output_size[1], output_size[2], -1)
|
263 |
+
# [b, np, sk, hn] -> [b * np, sk, hn]
|
264 |
+
key_layer = key_layer.view(output_size[0] * output_size[1], output_size[3], -1)
|
265 |
+
|
266 |
+
# preallocting input tensor: [b * np, sq, sk]
|
267 |
+
matmul_input_buffer = torch.empty(
|
268 |
+
output_size[0] * output_size[1], output_size[2], output_size[3], dtype=query_layer.dtype,
|
269 |
+
device=query_layer.device
|
270 |
+
)
|
271 |
+
|
272 |
+
# Raw attention scores. [b * np, sq, sk]
|
273 |
+
matmul_result = torch.baddbmm(
|
274 |
+
matmul_input_buffer,
|
275 |
+
query_layer, # [b * np, sq, hn]
|
276 |
+
key_layer.transpose(1, 2), # [b * np, hn, sk]
|
277 |
+
beta=0.0,
|
278 |
+
alpha=(1.0 / self.norm_factor),
|
279 |
+
)
|
280 |
+
|
281 |
+
# change view to [b, np, sq, sk]
|
282 |
+
attention_scores = matmul_result.view(*output_size)
|
283 |
+
|
284 |
+
# ===========================
|
285 |
+
# Attention probs and dropout
|
286 |
+
# ===========================
|
287 |
+
|
288 |
+
# attention scores and attention mask [b, np, sq, sk]
|
289 |
+
if self.attention_softmax_in_fp32:
|
290 |
+
attention_scores = attention_scores.float()
|
291 |
+
if self.coeff is not None:
|
292 |
+
attention_scores = attention_scores * self.coeff
|
293 |
+
if attention_mask is None and attention_scores.shape[2] == attention_scores.shape[3]:
|
294 |
+
attention_mask = torch.ones(output_size[0], 1, output_size[2], output_size[3],
|
295 |
+
device=attention_scores.device, dtype=torch.bool)
|
296 |
+
attention_mask.tril_()
|
297 |
+
attention_mask = ~attention_mask
|
298 |
+
if attention_mask is not None:
|
299 |
+
attention_scores = attention_scores.masked_fill(attention_mask, float("-inf"))
|
300 |
+
attention_probs = F.softmax(attention_scores, dim=-1)
|
301 |
+
attention_probs = attention_probs.type_as(value_layer)
|
302 |
+
|
303 |
+
# This is actually dropping out entire tokens to attend to, which might
|
304 |
+
# seem a bit unusual, but is taken from the original Transformer paper.
|
305 |
+
attention_probs = self.attention_dropout(attention_probs)
|
306 |
+
# =========================
|
307 |
+
# Context layer. [sq, b, hp]
|
308 |
+
# =========================
|
309 |
+
|
310 |
+
# value_layer -> context layer.
|
311 |
+
# [sk, b, np, hn] --> [b, np, sq, hn]
|
312 |
+
|
313 |
+
# context layer shape: [b, np, sq, hn]
|
314 |
+
output_size = (value_layer.size(1), value_layer.size(2), query_layer.size(0), value_layer.size(3))
|
315 |
+
# change view [b * np, sk, hn]
|
316 |
+
value_layer = value_layer.view(output_size[0] * output_size[1], value_layer.size(2), -1)
|
317 |
+
# change view [b * np, sq, sk]
|
318 |
+
attention_probs = attention_probs.view(output_size[0] * output_size[1], output_size[2], -1)
|
319 |
+
# matmul: [b * np, sq, hn]
|
320 |
+
context_layer = torch.bmm(attention_probs, value_layer)
|
321 |
+
# change view [b, np, sq, hn]
|
322 |
+
context_layer = context_layer.view(*output_size)
|
323 |
+
# [b, np, sq, hn] --> [b, sq, np, hn]
|
324 |
+
context_layer = context_layer.transpose(1, 2).contiguous()
|
325 |
+
# [b, sq, np, hn] --> [b, sq, hp]
|
326 |
+
new_context_layer_shape = context_layer.size()[:-2] + (self.hidden_size_per_partition,)
|
327 |
+
context_layer = context_layer.reshape(*new_context_layer_shape)
|
328 |
+
|
329 |
+
return context_layer
|
330 |
+
|
331 |
+
|
332 |
+
class SelfAttention(torch.nn.Module):
|
333 |
+
"""Parallel self-attention layer abstract class.
|
334 |
+
|
335 |
+
Self-attention layer takes input with size [s, b, h]
|
336 |
+
and returns output of the same size.
|
337 |
+
"""
|
338 |
+
|
339 |
+
def __init__(self, config: ChatGLMConfig, layer_number, device=None):
|
340 |
+
super(SelfAttention, self).__init__()
|
341 |
+
self.layer_number = max(1, layer_number)
|
342 |
+
|
343 |
+
self.projection_size = config.kv_channels * config.num_attention_heads
|
344 |
+
|
345 |
+
# Per attention head and per partition values.
|
346 |
+
self.hidden_size_per_attention_head = self.projection_size // config.num_attention_heads
|
347 |
+
self.num_attention_heads_per_partition = config.num_attention_heads
|
348 |
+
|
349 |
+
self.multi_query_attention = config.multi_query_attention
|
350 |
+
self.qkv_hidden_size = 3 * self.projection_size
|
351 |
+
self.original_rope = config.original_rope
|
352 |
+
if self.multi_query_attention:
|
353 |
+
self.num_multi_query_groups_per_partition = config.multi_query_group_num
|
354 |
+
self.qkv_hidden_size = (
|
355 |
+
self.projection_size + 2 * self.hidden_size_per_attention_head * config.multi_query_group_num
|
356 |
+
)
|
357 |
+
self.query_key_value = nn.Linear(config.hidden_size, self.qkv_hidden_size,
|
358 |
+
bias=config.add_bias_linear or config.add_qkv_bias,
|
359 |
+
device=device, **_config_to_kwargs(config)
|
360 |
+
)
|
361 |
+
|
362 |
+
self.core_attention = CoreAttention(config, self.layer_number)
|
363 |
+
|
364 |
+
# Output.
|
365 |
+
self.dense = nn.Linear(self.projection_size, config.hidden_size, bias=config.add_bias_linear,
|
366 |
+
device=device, **_config_to_kwargs(config)
|
367 |
+
)
|
368 |
+
|
369 |
+
def _allocate_memory(self, inference_max_sequence_len, batch_size, device=None, dtype=None):
|
370 |
+
if self.multi_query_attention:
|
371 |
+
num_attention_heads = self.num_multi_query_groups_per_partition
|
372 |
+
else:
|
373 |
+
num_attention_heads = self.num_attention_heads_per_partition
|
374 |
+
return torch.empty(
|
375 |
+
inference_max_sequence_len,
|
376 |
+
batch_size,
|
377 |
+
num_attention_heads,
|
378 |
+
self.hidden_size_per_attention_head,
|
379 |
+
dtype=dtype,
|
380 |
+
device=device,
|
381 |
+
)
|
382 |
+
|
383 |
+
def forward(
|
384 |
+
self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True
|
385 |
+
):
|
386 |
+
# hidden_states: [b, sq, h]
|
387 |
+
|
388 |
+
# =================================================
|
389 |
+
# Pre-allocate memory for key-values for inference.
|
390 |
+
# =================================================
|
391 |
+
# =====================
|
392 |
+
# Query, Key, and Value
|
393 |
+
# =====================
|
394 |
+
|
395 |
+
# Attention heads [b, sq, h] --> [b, sq, (np * 3 * hn)]
|
396 |
+
mixed_x_layer = self.query_key_value(hidden_states)
|
397 |
+
|
398 |
+
if self.multi_query_attention:
|
399 |
+
(query_layer, key_layer, value_layer) = mixed_x_layer.split(
|
400 |
+
[
|
401 |
+
self.num_attention_heads_per_partition * self.hidden_size_per_attention_head,
|
402 |
+
self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
|
403 |
+
self.num_multi_query_groups_per_partition * self.hidden_size_per_attention_head,
|
404 |
+
],
|
405 |
+
dim=-1,
|
406 |
+
)
|
407 |
+
query_layer = query_layer.view(
|
408 |
+
query_layer.size()[:-1] + (self.num_attention_heads_per_partition, self.hidden_size_per_attention_head)
|
409 |
+
)
|
410 |
+
key_layer = key_layer.view(
|
411 |
+
key_layer.size()[:-1] + (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
|
412 |
+
)
|
413 |
+
value_layer = value_layer.view(
|
414 |
+
value_layer.size()[:-1]
|
415 |
+
+ (self.num_multi_query_groups_per_partition, self.hidden_size_per_attention_head)
|
416 |
+
)
|
417 |
+
else:
|
418 |
+
new_tensor_shape = mixed_x_layer.size()[:-1] + \
|
419 |
+
(self.num_attention_heads_per_partition,
|
420 |
+
3 * self.hidden_size_per_attention_head)
|
421 |
+
mixed_x_layer = mixed_x_layer.view(*new_tensor_shape)
|
422 |
+
|
423 |
+
# [b, sq, np, 3 * hn] --> 3 [b, sq, np, hn]
|
424 |
+
(query_layer, key_layer, value_layer) = split_tensor_along_last_dim(mixed_x_layer, 3)
|
425 |
+
|
426 |
+
# [b, sq, np, hn] -> [b, np, sq, hn]
|
427 |
+
query_layer, key_layer, value_layer = [k.transpose(1, 2) for k in [query_layer, key_layer, value_layer]]
|
428 |
+
|
429 |
+
# apply relative positional encoding (rotary embedding)
|
430 |
+
if rotary_pos_emb is not None:
|
431 |
+
query_layer = apply_rotary_pos_emb(query_layer, rotary_pos_emb)
|
432 |
+
key_layer = apply_rotary_pos_emb(key_layer, rotary_pos_emb)
|
433 |
+
|
434 |
+
# adjust key and value for inference
|
435 |
+
if kv_cache is not None:
|
436 |
+
cache_k, cache_v = kv_cache
|
437 |
+
key_layer = torch.cat((cache_k, key_layer), dim=2)
|
438 |
+
value_layer = torch.cat((cache_v, value_layer), dim=2)
|
439 |
+
if use_cache:
|
440 |
+
kv_cache = (key_layer, value_layer)
|
441 |
+
else:
|
442 |
+
kv_cache = None
|
443 |
+
|
444 |
+
if self.multi_query_attention:
|
445 |
+
key_layer = key_layer.unsqueeze(2)
|
446 |
+
key_layer = key_layer.expand(
|
447 |
+
-1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1, -1
|
448 |
+
)
|
449 |
+
key_layer = key_layer.contiguous().view(
|
450 |
+
key_layer.size()[:1] + (self.num_attention_heads_per_partition,) + key_layer.size()[3:]
|
451 |
+
)
|
452 |
+
value_layer = value_layer.unsqueeze(2)
|
453 |
+
value_layer = value_layer.expand(
|
454 |
+
-1, -1, self.num_attention_heads_per_partition // self.num_multi_query_groups_per_partition, -1, -1
|
455 |
+
)
|
456 |
+
value_layer = value_layer.contiguous().view(
|
457 |
+
value_layer.size()[:1] + (self.num_attention_heads_per_partition,) + value_layer.size()[3:]
|
458 |
+
)
|
459 |
+
|
460 |
+
# ==================================
|
461 |
+
# core attention computation
|
462 |
+
# ==================================
|
463 |
+
|
464 |
+
context_layer = self.core_attention(query_layer, key_layer, value_layer, attention_mask)
|
465 |
+
|
466 |
+
# =================
|
467 |
+
# Output. [sq, b, h]
|
468 |
+
# =================
|
469 |
+
|
470 |
+
output = self.dense(context_layer)
|
471 |
+
|
472 |
+
return output, kv_cache
|
473 |
+
|
474 |
+
|
475 |
+
def _config_to_kwargs(args):
|
476 |
+
common_kwargs = {
|
477 |
+
"dtype": args.torch_dtype,
|
478 |
+
}
|
479 |
+
return common_kwargs
|
480 |
+
|
481 |
+
|
482 |
+
class MLP(torch.nn.Module):
|
483 |
+
"""MLP.
|
484 |
+
|
485 |
+
MLP will take the input with h hidden state, project it to 4*h
|
486 |
+
hidden dimension, perform nonlinear transformation, and project the
|
487 |
+
state back into h hidden dimension.
|
488 |
+
"""
|
489 |
+
|
490 |
+
def __init__(self, config: ChatGLMConfig, device=None):
|
491 |
+
super(MLP, self).__init__()
|
492 |
+
|
493 |
+
self.add_bias = config.add_bias_linear
|
494 |
+
|
495 |
+
# Project to 4h. If using swiglu double the output width, see https://arxiv.org/pdf/2002.05202.pdf
|
496 |
+
self.dense_h_to_4h = nn.Linear(
|
497 |
+
config.hidden_size,
|
498 |
+
config.ffn_hidden_size * 2,
|
499 |
+
bias=self.add_bias,
|
500 |
+
device=device,
|
501 |
+
**_config_to_kwargs(config)
|
502 |
+
)
|
503 |
+
|
504 |
+
def swiglu(x):
|
505 |
+
x = torch.chunk(x, 2, dim=-1)
|
506 |
+
return F.silu(x[0]) * x[1]
|
507 |
+
|
508 |
+
self.activation_func = swiglu
|
509 |
+
|
510 |
+
# Project back to h.
|
511 |
+
self.dense_4h_to_h = nn.Linear(
|
512 |
+
config.ffn_hidden_size,
|
513 |
+
config.hidden_size,
|
514 |
+
bias=self.add_bias,
|
515 |
+
device=device,
|
516 |
+
**_config_to_kwargs(config)
|
517 |
+
)
|
518 |
+
|
519 |
+
def forward(self, hidden_states):
|
520 |
+
# [s, b, 4hp]
|
521 |
+
intermediate_parallel = self.dense_h_to_4h(hidden_states)
|
522 |
+
intermediate_parallel = self.activation_func(intermediate_parallel)
|
523 |
+
# [s, b, h]
|
524 |
+
output = self.dense_4h_to_h(intermediate_parallel)
|
525 |
+
return output
|
526 |
+
|
527 |
+
|
528 |
+
class GLMBlock(torch.nn.Module):
|
529 |
+
"""A single transformer layer.
|
530 |
+
|
531 |
+
Transformer layer takes input with size [s, b, h] and returns an
|
532 |
+
output of the same size.
|
533 |
+
"""
|
534 |
+
|
535 |
+
def __init__(self, config: ChatGLMConfig, layer_number, device=None):
|
536 |
+
super(GLMBlock, self).__init__()
|
537 |
+
self.layer_number = layer_number
|
538 |
+
|
539 |
+
self.apply_residual_connection_post_layernorm = config.apply_residual_connection_post_layernorm
|
540 |
+
|
541 |
+
self.fp32_residual_connection = config.fp32_residual_connection
|
542 |
+
|
543 |
+
LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
|
544 |
+
# Layernorm on the input data.
|
545 |
+
self.input_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
|
546 |
+
dtype=config.torch_dtype)
|
547 |
+
|
548 |
+
# Self attention.
|
549 |
+
self.self_attention = SelfAttention(config, layer_number, device=device)
|
550 |
+
self.hidden_dropout = config.hidden_dropout
|
551 |
+
|
552 |
+
# Layernorm on the attention output
|
553 |
+
self.post_attention_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
|
554 |
+
dtype=config.torch_dtype)
|
555 |
+
|
556 |
+
# MLP
|
557 |
+
self.mlp = MLP(config, device=device)
|
558 |
+
|
559 |
+
def forward(
|
560 |
+
self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,
|
561 |
+
):
|
562 |
+
# hidden_states: [s, b, h]
|
563 |
+
|
564 |
+
# Layer norm at the beginning of the transformer layer.
|
565 |
+
layernorm_output = self.input_layernorm(hidden_states)
|
566 |
+
# Self attention.
|
567 |
+
attention_output, kv_cache = self.self_attention(
|
568 |
+
layernorm_output,
|
569 |
+
attention_mask,
|
570 |
+
rotary_pos_emb,
|
571 |
+
kv_cache=kv_cache,
|
572 |
+
use_cache=use_cache
|
573 |
+
)
|
574 |
+
|
575 |
+
# Residual connection.
|
576 |
+
if self.apply_residual_connection_post_layernorm:
|
577 |
+
residual = layernorm_output
|
578 |
+
else:
|
579 |
+
residual = hidden_states
|
580 |
+
|
581 |
+
layernorm_input = torch.nn.functional.dropout(attention_output, p=self.hidden_dropout, training=self.training)
|
582 |
+
layernorm_input = residual + layernorm_input
|
583 |
+
|
584 |
+
# Layer norm post the self attention.
|
585 |
+
layernorm_output = self.post_attention_layernorm(layernorm_input)
|
586 |
+
|
587 |
+
# MLP.
|
588 |
+
mlp_output = self.mlp(layernorm_output)
|
589 |
+
|
590 |
+
# Second residual connection.
|
591 |
+
if self.apply_residual_connection_post_layernorm:
|
592 |
+
residual = layernorm_output
|
593 |
+
else:
|
594 |
+
residual = layernorm_input
|
595 |
+
|
596 |
+
output = torch.nn.functional.dropout(mlp_output, p=self.hidden_dropout, training=self.training)
|
597 |
+
output = residual + output
|
598 |
+
|
599 |
+
return output, kv_cache
|
600 |
+
|
601 |
+
|
602 |
+
class GLMTransformer(torch.nn.Module):
|
603 |
+
"""Transformer class."""
|
604 |
+
|
605 |
+
def __init__(self, config: ChatGLMConfig, device=None):
|
606 |
+
super(GLMTransformer, self).__init__()
|
607 |
+
|
608 |
+
self.fp32_residual_connection = config.fp32_residual_connection
|
609 |
+
self.post_layer_norm = config.post_layer_norm
|
610 |
+
|
611 |
+
# Number of layers.
|
612 |
+
self.num_layers = config.num_layers
|
613 |
+
|
614 |
+
# Transformer layers.
|
615 |
+
def build_layer(layer_number):
|
616 |
+
return GLMBlock(config, layer_number, device=device)
|
617 |
+
|
618 |
+
self.layers = torch.nn.ModuleList([build_layer(i + 1) for i in range(self.num_layers)])
|
619 |
+
|
620 |
+
if self.post_layer_norm:
|
621 |
+
LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
|
622 |
+
# Final layer norm before output.
|
623 |
+
self.final_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
|
624 |
+
dtype=config.torch_dtype)
|
625 |
+
|
626 |
+
self.gradient_checkpointing = False
|
627 |
+
|
628 |
+
def _get_layer(self, layer_number):
|
629 |
+
return self.layers[layer_number]
|
630 |
+
|
631 |
+
def forward(
|
632 |
+
self, hidden_states, attention_mask, rotary_pos_emb, kv_caches=None,
|
633 |
+
use_cache: Optional[bool] = True,
|
634 |
+
output_hidden_states: Optional[bool] = False,
|
635 |
+
):
|
636 |
+
if not kv_caches:
|
637 |
+
kv_caches = [None for _ in range(self.num_layers)]
|
638 |
+
presents = () if use_cache else None
|
639 |
+
if self.gradient_checkpointing and self.training:
|
640 |
+
if use_cache:
|
641 |
+
logger.warning_once(
|
642 |
+
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
|
643 |
+
)
|
644 |
+
use_cache = False
|
645 |
+
|
646 |
+
all_self_attentions = None
|
647 |
+
all_hidden_states = () if output_hidden_states else None
|
648 |
+
for index in range(self.num_layers):
|
649 |
+
if output_hidden_states:
|
650 |
+
all_hidden_states = all_hidden_states + (hidden_states,)
|
651 |
+
|
652 |
+
layer = self._get_layer(index)
|
653 |
+
if self.gradient_checkpointing and self.training:
|
654 |
+
layer_ret = torch.utils.checkpoint.checkpoint(
|
655 |
+
layer,
|
656 |
+
hidden_states,
|
657 |
+
attention_mask,
|
658 |
+
rotary_pos_emb,
|
659 |
+
kv_caches[index],
|
660 |
+
use_cache,
|
661 |
+
use_reentrant=False
|
662 |
+
)
|
663 |
+
else:
|
664 |
+
layer_ret = layer(
|
665 |
+
hidden_states,
|
666 |
+
attention_mask,
|
667 |
+
rotary_pos_emb,
|
668 |
+
kv_cache=kv_caches[index],
|
669 |
+
use_cache=use_cache
|
670 |
+
)
|
671 |
+
hidden_states, kv_cache = layer_ret
|
672 |
+
if use_cache:
|
673 |
+
presents = presents + (kv_cache,)
|
674 |
+
|
675 |
+
if output_hidden_states:
|
676 |
+
all_hidden_states = all_hidden_states + (hidden_states,)
|
677 |
+
|
678 |
+
# Final layer norm.
|
679 |
+
if self.post_layer_norm:
|
680 |
+
hidden_states = self.final_layernorm(hidden_states)
|
681 |
+
|
682 |
+
return hidden_states, presents, all_hidden_states, all_self_attentions
|
683 |
+
|
684 |
+
|
685 |
+
class ChatGLMPreTrainedModel(PreTrainedModel):
|
686 |
+
"""
|
687 |
+
An abstract class to handle weights initialization and
|
688 |
+
a simple interface for downloading and loading pretrained models.
|
689 |
+
"""
|
690 |
+
|
691 |
+
is_parallelizable = False
|
692 |
+
supports_gradient_checkpointing = True
|
693 |
+
config_class = ChatGLMConfig
|
694 |
+
base_model_prefix = "transformer"
|
695 |
+
_no_split_modules = ["GLMBlock"]
|
696 |
+
|
697 |
+
def _init_weights(self, module: nn.Module):
|
698 |
+
"""Initialize the weights."""
|
699 |
+
return
|
700 |
+
|
701 |
+
def get_masks(self, input_ids, past_key_values, padding_mask=None):
|
702 |
+
batch_size, seq_length = input_ids.shape
|
703 |
+
full_attention_mask = torch.ones(batch_size, seq_length, seq_length, device=input_ids.device)
|
704 |
+
full_attention_mask.tril_()
|
705 |
+
past_length = 0
|
706 |
+
if past_key_values:
|
707 |
+
past_length = past_key_values[0][0].shape[2]
|
708 |
+
if past_length:
|
709 |
+
full_attention_mask = torch.cat((torch.ones(batch_size, seq_length, past_length,
|
710 |
+
device=input_ids.device), full_attention_mask), dim=-1)
|
711 |
+
if padding_mask is not None:
|
712 |
+
full_attention_mask = full_attention_mask * padding_mask.unsqueeze(1)
|
713 |
+
if not past_length and padding_mask is not None:
|
714 |
+
full_attention_mask -= padding_mask.unsqueeze(-1) - 1
|
715 |
+
full_attention_mask = (full_attention_mask < 0.5).bool()
|
716 |
+
full_attention_mask.unsqueeze_(1)
|
717 |
+
return full_attention_mask
|
718 |
+
|
719 |
+
def get_position_ids(self, input_ids, device):
|
720 |
+
batch_size, seq_length = input_ids.shape
|
721 |
+
position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)
|
722 |
+
return position_ids
|
723 |
+
|
724 |
+
def get_multimodal_position_ids(self, input_ids, device):
|
725 |
+
batch_size, seq_length = input_ids.shape
|
726 |
+
position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)
|
727 |
+
|
728 |
+
def gradient_checkpointing_enable(self, gradient_checkpointing_kwargs=None):
|
729 |
+
if not self.supports_gradient_checkpointing:
|
730 |
+
raise ValueError(f"{self.__class__.__name__} does not support gradient checkpointing.")
|
731 |
+
|
732 |
+
|
733 |
+
class Embedding(torch.nn.Module):
|
734 |
+
"""Language model embeddings."""
|
735 |
+
|
736 |
+
def __init__(self, config: ChatGLMConfig, device=None):
|
737 |
+
super(Embedding, self).__init__()
|
738 |
+
|
739 |
+
self.hidden_size = config.hidden_size
|
740 |
+
# Word embeddings (parallel).
|
741 |
+
self.word_embeddings = nn.Embedding(
|
742 |
+
config.padded_vocab_size,
|
743 |
+
self.hidden_size,
|
744 |
+
dtype=config.torch_dtype,
|
745 |
+
device=device
|
746 |
+
)
|
747 |
+
self.fp32_residual_connection = config.fp32_residual_connection
|
748 |
+
|
749 |
+
def forward(self, input_ids):
|
750 |
+
# Embeddings.
|
751 |
+
words_embeddings = self.word_embeddings(input_ids)
|
752 |
+
embeddings = words_embeddings
|
753 |
+
# If the input flag for fp32 residual connection is set, convert for float.
|
754 |
+
if self.fp32_residual_connection:
|
755 |
+
embeddings = embeddings.float()
|
756 |
+
return embeddings
|
757 |
+
|
758 |
+
|
759 |
+
def is_empty(images_list: Optional[List[List[torch.Tensor]]]):
|
760 |
+
if images_list is None or len(images_list) == 0:
|
761 |
+
return True
|
762 |
+
for image_list in images_list:
|
763 |
+
if image_list is not None:
|
764 |
+
return False
|
765 |
+
return True
|
766 |
+
|
767 |
+
|
768 |
+
class ChatGLMModel(ChatGLMPreTrainedModel):
|
769 |
+
def __init__(self, config: ChatGLMConfig, device=None, empty_init=True):
|
770 |
+
super().__init__(config)
|
771 |
+
if empty_init:
|
772 |
+
init_method = skip_init
|
773 |
+
else:
|
774 |
+
init_method = default_init
|
775 |
+
init_kwargs = {}
|
776 |
+
if device is not None:
|
777 |
+
init_kwargs["device"] = device
|
778 |
+
self.embedding = init_method(Embedding, config, **init_kwargs)
|
779 |
+
self.num_layers = config.num_layers
|
780 |
+
self.multi_query_group_num = config.multi_query_group_num
|
781 |
+
self.kv_channels = config.kv_channels
|
782 |
+
|
783 |
+
# Rotary positional embeddings
|
784 |
+
self.seq_length = config.seq_length
|
785 |
+
rotary_dim = (
|
786 |
+
config.hidden_size // config.num_attention_heads if config.kv_channels is None else config.kv_channels
|
787 |
+
)
|
788 |
+
|
789 |
+
self.rotary_pos_emb = RotaryEmbedding(rotary_dim // 2, rope_ratio=config.rope_ratio,
|
790 |
+
original_impl=config.original_rope,
|
791 |
+
device=device, dtype=config.torch_dtype)
|
792 |
+
self.encoder = init_method(GLMTransformer, config, **init_kwargs)
|
793 |
+
self.output_layer = init_method(nn.Linear, config.hidden_size, config.padded_vocab_size, bias=False,
|
794 |
+
dtype=config.torch_dtype, **init_kwargs)
|
795 |
+
self.pre_seq_len = config.pre_seq_len
|
796 |
+
self.prefix_projection = config.prefix_projection
|
797 |
+
if self.pre_seq_len is not None:
|
798 |
+
for param in self.parameters():
|
799 |
+
param.requires_grad = False
|
800 |
+
self.prefix_tokens = torch.arange(self.pre_seq_len).long()
|
801 |
+
self.prefix_encoder = PrefixEncoder(config)
|
802 |
+
self.dropout = torch.nn.Dropout(0.1)
|
803 |
+
|
804 |
+
self.vision = EVA2CLIPModel(config)
|
805 |
+
|
806 |
+
def get_input_embeddings(self):
|
807 |
+
return self.embedding.word_embeddings
|
808 |
+
|
809 |
+
def set_input_embeddings(self, value):
|
810 |
+
self.embedding.word_embeddings = value
|
811 |
+
|
812 |
+
def get_prompt(self, batch_size, device, dtype=torch.half):
|
813 |
+
prefix_tokens = self.prefix_tokens.unsqueeze(0).expand(batch_size, -1).to(device)
|
814 |
+
past_key_values = self.prefix_encoder(prefix_tokens).type(dtype)
|
815 |
+
past_key_values = past_key_values.view(
|
816 |
+
batch_size,
|
817 |
+
self.pre_seq_len,
|
818 |
+
self.pre_seq_len,
|
819 |
+
self.num_layers * 2,
|
820 |
+
self.multi_query_group_num,
|
821 |
+
self.kv_channels
|
822 |
+
)
|
823 |
+
# seq_len, b, nh, hidden_size
|
824 |
+
past_key_values = self.dropout(past_key_values)
|
825 |
+
past_key_values = past_key_values.permute([2, 1, 0, 3, 4]).split(2)
|
826 |
+
return past_key_values
|
827 |
+
|
828 |
+
def forward(
|
829 |
+
self,
|
830 |
+
input_ids: torch.LongTensor = None,
|
831 |
+
images: torch.Tensor = None,
|
832 |
+
position_ids: Optional[torch.Tensor] = None,
|
833 |
+
attention_mask: Optional[torch.BoolTensor] = None,
|
834 |
+
full_attention_mask: Optional[torch.BoolTensor] = None,
|
835 |
+
past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
|
836 |
+
inputs_embeds: Optional[torch.Tensor] = None,
|
837 |
+
use_cache: Optional[bool] = None,
|
838 |
+
output_hidden_states: Optional[bool] = None,
|
839 |
+
return_dict: Optional[bool] = None,
|
840 |
+
) -> Union[Tuple, BaseModelOutputWithPast]:
|
841 |
+
"""take care of image_encode, position_ids and (attention_mask = None is fine)"""
|
842 |
+
|
843 |
+
# generate mode with past_key_values. the image features are already mapped
|
844 |
+
if past_key_values is None:
|
845 |
+
# not allow for inputs_embeds, because we want to process image feature
|
846 |
+
assert input_ids is not None and inputs_embeds is None, f"{input_ids} {inputs_embeds}"
|
847 |
+
if not is_empty(images): # multi-modality
|
848 |
+
image_size: int = self.config.vision_config['image_size']
|
849 |
+
patch_size: int = self.config.vision_config['patch_size']
|
850 |
+
num_patches = (image_size // patch_size // 2) ** 2
|
851 |
+
assert len(input_ids) == len(images), f"{len(input_ids)} {len(images)}"
|
852 |
+
inputs_embeds = self.embedding(input_ids)
|
853 |
+
|
854 |
+
images = images.to(dtype=inputs_embeds.dtype)
|
855 |
+
images_features = self.vision(images)
|
856 |
+
|
857 |
+
if position_ids is None:
|
858 |
+
position_ids = self.get_position_ids(input_ids, device=inputs_embeds.device)
|
859 |
+
new_input_embeds, new_position_ids = [], []
|
860 |
+
|
861 |
+
for i in range(len(input_ids)):
|
862 |
+
input_id = input_ids[i].tolist()
|
863 |
+
boi_token_pos, eoi_token_pos = input_id.index(self.config.boi_token_id), input_id.index(
|
864 |
+
self.config.eoi_token_id)
|
865 |
+
assert eoi_token_pos - boi_token_pos == 2
|
866 |
+
new_input_embeds.append(torch.cat(
|
867 |
+
(inputs_embeds[i, :boi_token_pos], images_features[i], inputs_embeds[i, eoi_token_pos + 1:])))
|
868 |
+
new_position_ids.append(torch.cat(
|
869 |
+
(position_ids[i, :boi_token_pos + 1], position_ids[i, boi_token_pos + 1].repeat(num_patches),
|
870 |
+
position_ids[i, eoi_token_pos:])
|
871 |
+
))
|
872 |
+
inputs_embeds = torch.stack(new_input_embeds, dim=0)
|
873 |
+
position_ids = torch.stack(new_position_ids, dim=0)
|
874 |
+
|
875 |
+
output_hidden_states = (
|
876 |
+
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
|
877 |
+
)
|
878 |
+
use_cache = use_cache if use_cache is not None else self.config.use_cache
|
879 |
+
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
880 |
+
|
881 |
+
batch_size, seq_length = input_ids.shape
|
882 |
+
|
883 |
+
if inputs_embeds is None:
|
884 |
+
inputs_embeds = self.embedding(input_ids)
|
885 |
+
|
886 |
+
if self.pre_seq_len is not None:
|
887 |
+
if past_key_values is None:
|
888 |
+
past_key_values = self.get_prompt(batch_size=batch_size, device=input_ids.device,
|
889 |
+
dtype=inputs_embeds.dtype)
|
890 |
+
if attention_mask is not None:
|
891 |
+
attention_mask = torch.cat([attention_mask.new_ones((batch_size, self.pre_seq_len)),
|
892 |
+
attention_mask], dim=-1)
|
893 |
+
|
894 |
+
if full_attention_mask is None:
|
895 |
+
if (attention_mask is not None and not attention_mask.all()) or (past_key_values and seq_length != 1):
|
896 |
+
full_attention_mask = self.get_masks(input_ids, past_key_values, padding_mask=attention_mask)
|
897 |
+
|
898 |
+
# Rotary positional embeddings
|
899 |
+
rotary_pos_emb = self.rotary_pos_emb(self.seq_length)
|
900 |
+
if position_ids is not None:
|
901 |
+
rotary_pos_emb = rotary_pos_emb[position_ids]
|
902 |
+
else:
|
903 |
+
rotary_pos_emb = rotary_pos_emb[None, :seq_length]
|
904 |
+
|
905 |
+
# Run encoder.
|
906 |
+
hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
|
907 |
+
inputs_embeds, full_attention_mask, rotary_pos_emb=rotary_pos_emb,
|
908 |
+
kv_caches=past_key_values, use_cache=use_cache, output_hidden_states=output_hidden_states
|
909 |
+
)
|
910 |
+
|
911 |
+
if not return_dict:
|
912 |
+
return tuple(v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None)
|
913 |
+
|
914 |
+
return BaseModelOutputWithPast(
|
915 |
+
last_hidden_state=hidden_states,
|
916 |
+
past_key_values=presents,
|
917 |
+
hidden_states=all_hidden_states,
|
918 |
+
attentions=all_self_attentions,
|
919 |
+
)
|
920 |
+
|
921 |
+
|
922 |
+
def _history_to_prompt(history, query):
|
923 |
+
prompt = ''
|
924 |
+
flag = False
|
925 |
+
for i, (old_query, response) in enumerate(history):
|
926 |
+
prompt += ('<|user|>' if flag else '') + old_query + "<|assistant|>" + response + "<|endoftext|>"
|
927 |
+
flag = True
|
928 |
+
prompt += '{}{}<|assistant|>'.format('<|user|>' if flag else '', query)
|
929 |
+
return prompt
|
930 |
+
|
931 |
+
|
932 |
+
class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
|
933 |
+
def __init__(self, config: ChatGLMConfig, empty_init=False, device=None):
|
934 |
+
super().__init__(config)
|
935 |
+
|
936 |
+
self.max_sequence_length = config.max_length
|
937 |
+
self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
|
938 |
+
self.config = config
|
939 |
+
|
940 |
+
def _update_model_kwargs_for_generation(
|
941 |
+
self,
|
942 |
+
outputs: ModelOutput,
|
943 |
+
model_kwargs: Dict[str, Any],
|
944 |
+
is_encoder_decoder: bool = False,
|
945 |
+
standardize_cache_format: bool = False,
|
946 |
+
) -> Dict[str, Any]:
|
947 |
+
# update past_key_values
|
948 |
+
model_kwargs["past_key_values"] = self._extract_past_from_model_output(
|
949 |
+
outputs, standardize_cache_format=standardize_cache_format
|
950 |
+
)
|
951 |
+
|
952 |
+
# update attention mask
|
953 |
+
if "attention_mask" in model_kwargs:
|
954 |
+
attention_mask = model_kwargs["attention_mask"]
|
955 |
+
model_kwargs["attention_mask"] = torch.cat(
|
956 |
+
[attention_mask, attention_mask.new_ones((attention_mask.shape[0], 1))], dim=-1
|
957 |
+
)
|
958 |
+
|
959 |
+
# update position ids
|
960 |
+
if "position_ids" in model_kwargs:
|
961 |
+
position_ids = model_kwargs["position_ids"]
|
962 |
+
new_position_id = position_ids[..., -1:].clone()
|
963 |
+
new_position_id += 1
|
964 |
+
model_kwargs["position_ids"] = torch.cat(
|
965 |
+
[position_ids, new_position_id], dim=-1
|
966 |
+
)
|
967 |
+
|
968 |
+
model_kwargs["is_first_forward"] = False
|
969 |
+
return model_kwargs
|
970 |
+
|
971 |
+
def prepare_inputs_for_generation(
|
972 |
+
self,
|
973 |
+
input_ids: torch.LongTensor,
|
974 |
+
images: Optional[torch.Tensor] = None,
|
975 |
+
past_key_values: Optional[torch.Tensor] = None,
|
976 |
+
attention_mask: Optional[torch.Tensor] = None,
|
977 |
+
position_ids: Optional[torch.Tensor] = None,
|
978 |
+
use_cache: Optional[bool] = None,
|
979 |
+
is_first_forward: bool = True,
|
980 |
+
**kwargs
|
981 |
+
) -> dict:
|
982 |
+
# only last token for input_ids if past is not None
|
983 |
+
if position_ids is None:
|
984 |
+
position_ids = self.get_position_ids(input_ids, device=input_ids.device)
|
985 |
+
if not is_first_forward:
|
986 |
+
if past_key_values is not None:
|
987 |
+
position_ids = position_ids[..., -1:]
|
988 |
+
input_ids = input_ids[:, -1:]
|
989 |
+
return {
|
990 |
+
"input_ids": input_ids,
|
991 |
+
"images": images,
|
992 |
+
"past_key_values": past_key_values,
|
993 |
+
"position_ids": position_ids,
|
994 |
+
"attention_mask": attention_mask,
|
995 |
+
"return_last_logit": True,
|
996 |
+
"use_cache": use_cache
|
997 |
+
}
|
998 |
+
|
999 |
+
def forward(
|
1000 |
+
self,
|
1001 |
+
input_ids: Optional[torch.Tensor] = None,
|
1002 |
+
images: List[List[torch.Tensor]] = None,
|
1003 |
+
position_ids: Optional[torch.Tensor] = None,
|
1004 |
+
attention_mask: Optional[torch.Tensor] = None,
|
1005 |
+
past_key_values: Optional[Tuple[torch.FloatTensor]] = None,
|
1006 |
+
inputs_embeds: Optional[torch.Tensor] = None,
|
1007 |
+
labels: Optional[torch.Tensor] = None,
|
1008 |
+
use_cache: Optional[bool] = None,
|
1009 |
+
output_attentions: Optional[bool] = None,
|
1010 |
+
output_hidden_states: Optional[bool] = None,
|
1011 |
+
return_dict: Optional[bool] = None,
|
1012 |
+
return_last_logit: Optional[bool] = False,
|
1013 |
+
):
|
1014 |
+
use_cache = use_cache if use_cache is not None else self.config.use_cache
|
1015 |
+
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
1016 |
+
|
1017 |
+
transformer_outputs = self.transformer(
|
1018 |
+
input_ids=input_ids,
|
1019 |
+
images=images,
|
1020 |
+
position_ids=position_ids,
|
1021 |
+
attention_mask=attention_mask,
|
1022 |
+
past_key_values=past_key_values,
|
1023 |
+
inputs_embeds=inputs_embeds,
|
1024 |
+
use_cache=use_cache,
|
1025 |
+
output_hidden_states=output_hidden_states,
|
1026 |
+
return_dict=return_dict,
|
1027 |
+
)
|
1028 |
+
|
1029 |
+
hidden_states = transformer_outputs[0]
|
1030 |
+
if return_last_logit:
|
1031 |
+
hidden_states = hidden_states[:, -1:]
|
1032 |
+
lm_logits = self.transformer.output_layer(hidden_states)
|
1033 |
+
|
1034 |
+
loss = None
|
1035 |
+
if labels is not None:
|
1036 |
+
lm_logits = lm_logits.to(torch.float32)
|
1037 |
+
|
1038 |
+
# Shift so that tokens < n predict n
|
1039 |
+
shift_logits = lm_logits[..., :-1, :].contiguous()
|
1040 |
+
shift_labels = labels[..., 1:].contiguous()
|
1041 |
+
# Flatten the tokens
|
1042 |
+
loss_fct = CrossEntropyLoss(ignore_index=-100)
|
1043 |
+
loss = loss_fct(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
|
1044 |
+
|
1045 |
+
lm_logits = lm_logits.to(hidden_states.dtype)
|
1046 |
+
loss = loss.to(hidden_states.dtype)
|
1047 |
+
|
1048 |
+
if not return_dict:
|
1049 |
+
output = (lm_logits,) + transformer_outputs[1:]
|
1050 |
+
return ((loss,) + output) if loss is not None else output
|
1051 |
+
|
1052 |
+
return CausalLMOutputWithPast(
|
1053 |
+
loss=loss,
|
1054 |
+
logits=lm_logits,
|
1055 |
+
past_key_values=transformer_outputs.past_key_values,
|
1056 |
+
hidden_states=transformer_outputs.hidden_states,
|
1057 |
+
attentions=transformer_outputs.attentions,
|
1058 |
+
)
|
1059 |
+
|
1060 |
+
@staticmethod
|
1061 |
+
def _reorder_cache(
|
1062 |
+
past: Tuple[Tuple[torch.Tensor, torch.Tensor], ...], beam_idx: torch.LongTensor
|
1063 |
+
) -> Tuple[Tuple[torch.Tensor, torch.Tensor], ...]:
|
1064 |
+
"""
|
1065 |
+
This function is used to re-order the `past_key_values` cache if [`~PreTrainedModel.beam_search`] or
|
1066 |
+
[`~PreTrainedModel.beam_sample`] is called. This is required to match `past_key_values` with the correct
|
1067 |
+
beam_idx at every generation step.
|
1068 |
+
|
1069 |
+
Output shares the same memory storage as `past`.
|
1070 |
+
"""
|
1071 |
+
return tuple(
|
1072 |
+
(
|
1073 |
+
layer_past[0].index_select(0, beam_idx.to(layer_past[0].device)),
|
1074 |
+
layer_past[1].index_select(0, beam_idx.to(layer_past[1].device)),
|
1075 |
+
)
|
1076 |
+
for layer_past in past
|
1077 |
+
)
|
1078 |
+
|
1079 |
+
def process_response(self, output, history):
|
1080 |
+
content = ""
|
1081 |
+
history = deepcopy(history)
|
1082 |
+
for response in output.split("<|assistant|>"):
|
1083 |
+
if "\n" in response:
|
1084 |
+
metadata, content = response.split("\n", maxsplit=1)
|
1085 |
+
else:
|
1086 |
+
metadata, content = "", response
|
1087 |
+
if not metadata.strip():
|
1088 |
+
content = content.strip()
|
1089 |
+
history.append({"role": "assistant", "metadata": metadata, "content": content})
|
1090 |
+
content = content.replace("[[训练时间]]", "2023年")
|
1091 |
+
else:
|
1092 |
+
history.append({"role": "assistant", "metadata": metadata, "content": content})
|
1093 |
+
if history[0]["role"] == "system" and "tools" in history[0]:
|
1094 |
+
parameters = json.loads(content)
|
1095 |
+
content = {"name": metadata.strip(), "parameters": parameters}
|
1096 |
+
else:
|
1097 |
+
content = {"name": metadata.strip(), "content": content}
|
1098 |
+
return content, history
|
1099 |
+
|
1100 |
+
@torch.inference_mode()
|
1101 |
+
def chat(self, tokenizer, query: str, history: List[Dict] = None, role: str = "user", image=None,
|
1102 |
+
max_length: int = 8192, num_beams=1, do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None,
|
1103 |
+
**kwargs):
|
1104 |
+
if history is None:
|
1105 |
+
history = []
|
1106 |
+
if logits_processor is None:
|
1107 |
+
logits_processor = LogitsProcessorList()
|
1108 |
+
logits_processor.append(InvalidScoreLogitsProcessor())
|
1109 |
+
gen_kwargs = {"max_length": max_length, "num_beams": num_beams, "do_sample": do_sample, "top_p": top_p,
|
1110 |
+
"temperature": temperature, "logits_processor": logits_processor, **kwargs}
|
1111 |
+
message = {"role": role, "content": query}
|
1112 |
+
if image is not None:
|
1113 |
+
message["image"] = image
|
1114 |
+
history.append(message)
|
1115 |
+
inputs = tokenizer.apply_chat_template(history, add_generation_prompt=True, tokenize=True,
|
1116 |
+
return_tensors="pt", return_dict=True)
|
1117 |
+
inputs = inputs.to(self.device)
|
1118 |
+
eos_token_id = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|user|>"),
|
1119 |
+
tokenizer.convert_tokens_to_ids("<|observation|>")]
|
1120 |
+
outputs = self.generate(**inputs, **gen_kwargs, eos_token_id=eos_token_id)
|
1121 |
+
outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):-1]
|
1122 |
+
response = tokenizer.decode(outputs)
|
1123 |
+
response, history = self.process_response(response, history)
|
1124 |
+
return response, history
|
1125 |
+
|
1126 |
+
@torch.inference_mode()
|
1127 |
+
def stream_chat(self, tokenizer, query: str, history: List[Dict] = None, role: str = "user", image=None,
|
1128 |
+
past_key_values=None, max_length: int = 8192, do_sample=True, top_p=0.8, temperature=0.8,
|
1129 |
+
logits_processor=None, return_past_key_values=False, **kwargs):
|
1130 |
+
if history is None:
|
1131 |
+
history = []
|
1132 |
+
if logits_processor is None:
|
1133 |
+
logits_processor = LogitsProcessorList()
|
1134 |
+
logits_processor.append(InvalidScoreLogitsProcessor())
|
1135 |
+
eos_token_id = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|user|>"),
|
1136 |
+
tokenizer.convert_tokens_to_ids("<|observation|>")]
|
1137 |
+
gen_kwargs = {"max_length": max_length, "do_sample": do_sample, "top_p": top_p,
|
1138 |
+
"temperature": temperature, "logits_processor": logits_processor, **kwargs}
|
1139 |
+
message = {"role": role, "content": "query"}
|
1140 |
+
if image is not None:
|
1141 |
+
message["image"] = image
|
1142 |
+
if past_key_values is None:
|
1143 |
+
inputs = tokenizer.apply_chat_template(history + [message],
|
1144 |
+
add_generation_prompt=True, tokenize=True, return_tensors="pt",
|
1145 |
+
return_dict=True)
|
1146 |
+
else:
|
1147 |
+
inputs = tokenizer.apply_chat_template([message], add_special_tokens=False,
|
1148 |
+
add_generation_prompt=True, tokenize=True, return_tensors="pt",
|
1149 |
+
return_dict=True)
|
1150 |
+
inputs = inputs.to(self.device)
|
1151 |
+
if past_key_values is not None:
|
1152 |
+
past_length = past_key_values[0][0].shape[2]
|
1153 |
+
if self.transformer.pre_seq_len is not None:
|
1154 |
+
past_length -= self.transformer.pre_seq_len
|
1155 |
+
inputs.position_ids += past_length
|
1156 |
+
attention_mask = inputs.attention_mask
|
1157 |
+
attention_mask = torch.cat((attention_mask.new_ones(1, past_length), attention_mask), dim=1)
|
1158 |
+
inputs['attention_mask'] = attention_mask
|
1159 |
+
history.append({"role": role, "content": query})
|
1160 |
+
for outputs in self.stream_generate(**inputs, past_key_values=past_key_values,
|
1161 |
+
eos_token_id=eos_token_id, return_past_key_values=return_past_key_values,
|
1162 |
+
**gen_kwargs):
|
1163 |
+
if return_past_key_values:
|
1164 |
+
outputs, past_key_values = outputs
|
1165 |
+
outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):-1]
|
1166 |
+
response = tokenizer.decode(outputs)
|
1167 |
+
if response and response[-1] != "�":
|
1168 |
+
response, new_history = self.process_response(response, history)
|
1169 |
+
if return_past_key_values:
|
1170 |
+
yield response, new_history, past_key_values
|
1171 |
+
else:
|
1172 |
+
yield response, new_history
|
1173 |
+
|
1174 |
+
@torch.inference_mode()
|
1175 |
+
def stream_generate(
|
1176 |
+
self,
|
1177 |
+
input_ids,
|
1178 |
+
generation_config: Optional[GenerationConfig] = None,
|
1179 |
+
logits_processor: Optional[LogitsProcessorList] = None,
|
1180 |
+
stopping_criteria: Optional[StoppingCriteriaList] = None,
|
1181 |
+
prefix_allowed_tokens_fn: Optional[Callable[[int, torch.Tensor], List[int]]] = None,
|
1182 |
+
return_past_key_values=False,
|
1183 |
+
**kwargs,
|
1184 |
+
):
|
1185 |
+
batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
|
1186 |
+
|
1187 |
+
if generation_config is None:
|
1188 |
+
generation_config = self.generation_config
|
1189 |
+
generation_config = copy.deepcopy(generation_config)
|
1190 |
+
model_kwargs = generation_config.update(**kwargs)
|
1191 |
+
model_kwargs["use_cache"] = generation_config.use_cache
|
1192 |
+
bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
|
1193 |
+
|
1194 |
+
if isinstance(eos_token_id, int):
|
1195 |
+
eos_token_id = [eos_token_id]
|
1196 |
+
eos_token_id_tensor = torch.tensor(eos_token_id).to(input_ids.device) if eos_token_id is not None else None
|
1197 |
+
|
1198 |
+
has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
|
1199 |
+
if has_default_max_length and generation_config.max_new_tokens is None:
|
1200 |
+
warnings.warn(
|
1201 |
+
f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
|
1202 |
+
"This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
|
1203 |
+
" recommend using `max_new_tokens` to control the maximum length of the generation.",
|
1204 |
+
UserWarning,
|
1205 |
+
)
|
1206 |
+
elif generation_config.max_new_tokens is not None:
|
1207 |
+
generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
|
1208 |
+
if not has_default_max_length:
|
1209 |
+
logger.warn(
|
1210 |
+
f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
|
1211 |
+
f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
|
1212 |
+
"Please refer to the documentation for more information. "
|
1213 |
+
"(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
|
1214 |
+
UserWarning,
|
1215 |
+
)
|
1216 |
+
|
1217 |
+
if input_ids_seq_length >= generation_config.max_length:
|
1218 |
+
input_ids_string = "decoder_input_ids" if self.config.is_encoder_decoder else "input_ids"
|
1219 |
+
logger.warning(
|
1220 |
+
f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
|
1221 |
+
f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
|
1222 |
+
" increasing `max_new_tokens`."
|
1223 |
+
)
|
1224 |
+
|
1225 |
+
# 2. Set generation parameters if not already defined
|
1226 |
+
logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
|
1227 |
+
stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
|
1228 |
+
|
1229 |
+
logits_processor = self._get_logits_processor(
|
1230 |
+
generation_config=generation_config,
|
1231 |
+
input_ids_seq_length=input_ids_seq_length,
|
1232 |
+
encoder_input_ids=input_ids,
|
1233 |
+
prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
|
1234 |
+
logits_processor=logits_processor,
|
1235 |
+
)
|
1236 |
+
|
1237 |
+
stopping_criteria = self._get_stopping_criteria(
|
1238 |
+
generation_config=generation_config, stopping_criteria=stopping_criteria
|
1239 |
+
)
|
1240 |
+
logits_warper = self._get_logits_warper(generation_config)
|
1241 |
+
|
1242 |
+
unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
|
1243 |
+
scores = None
|
1244 |
+
while True:
|
1245 |
+
model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
|
1246 |
+
# forward pass to get next token
|
1247 |
+
outputs = self(
|
1248 |
+
**model_inputs,
|
1249 |
+
return_dict=True,
|
1250 |
+
output_attentions=False,
|
1251 |
+
output_hidden_states=False,
|
1252 |
+
)
|
1253 |
+
|
1254 |
+
next_token_logits = outputs.logits[:, -1, :]
|
1255 |
+
|
1256 |
+
# pre-process distribution
|
1257 |
+
next_token_scores = logits_processor(input_ids, next_token_logits)
|
1258 |
+
next_token_scores = logits_warper(input_ids, next_token_scores)
|
1259 |
+
|
1260 |
+
# sample
|
1261 |
+
probs = nn.functional.softmax(next_token_scores, dim=-1)
|
1262 |
+
if generation_config.do_sample:
|
1263 |
+
next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
|
1264 |
+
else:
|
1265 |
+
next_tokens = torch.argmax(probs, dim=-1)
|
1266 |
+
# update generated ids, model inputs, and length for next step
|
1267 |
+
input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
|
1268 |
+
model_kwargs = self._update_model_kwargs_for_generation(
|
1269 |
+
outputs, model_kwargs, is_encoder_decoder=self.config.is_encoder_decoder
|
1270 |
+
)
|
1271 |
+
unfinished_sequences = unfinished_sequences.mul(
|
1272 |
+
next_tokens.tile(eos_token_id_tensor.shape[0], 1).ne(eos_token_id_tensor.unsqueeze(1)).prod(dim=0)
|
1273 |
+
)
|
1274 |
+
if return_past_key_values:
|
1275 |
+
yield input_ids, outputs.past_key_values
|
1276 |
+
else:
|
1277 |
+
yield input_ids
|
1278 |
+
# stop when each sentence is finished, or if we exceed the maximum length
|
1279 |
+
if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
|
1280 |
+
break
|
1281 |
+
|
1282 |
+
|
1283 |
+
class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
|
1284 |
+
def __init__(self, config: ChatGLMConfig, empty_init=True, device=None):
|
1285 |
+
super().__init__(config)
|
1286 |
+
|
1287 |
+
self.num_labels = config.num_labels
|
1288 |
+
self.transformer = ChatGLMModel(config, empty_init=empty_init, device=device)
|
1289 |
+
|
1290 |
+
self.classifier_head = nn.Linear(config.hidden_size, config.num_labels, bias=True, dtype=torch.half)
|
1291 |
+
if config.classifier_dropout is not None:
|
1292 |
+
self.dropout = nn.Dropout(config.classifier_dropout)
|
1293 |
+
else:
|
1294 |
+
self.dropout = None
|
1295 |
+
self.config = config
|
1296 |
+
|
1297 |
+
def forward(
|
1298 |
+
self,
|
1299 |
+
input_ids: Optional[torch.LongTensor] = None,
|
1300 |
+
position_ids: Optional[torch.LongTensor] = None,
|
1301 |
+
attention_mask: Optional[torch.Tensor] = None,
|
1302 |
+
full_attention_mask: Optional[torch.Tensor] = None,
|
1303 |
+
past_key_values: Optional[Tuple[Tuple[torch.Tensor, torch.Tensor], ...]] = None,
|
1304 |
+
inputs_embeds: Optional[torch.LongTensor] = None,
|
1305 |
+
labels: Optional[torch.LongTensor] = None,
|
1306 |
+
use_cache: Optional[bool] = None,
|
1307 |
+
output_hidden_states: Optional[bool] = None,
|
1308 |
+
return_dict: Optional[bool] = None,
|
1309 |
+
) -> Union[Tuple[torch.Tensor, ...], SequenceClassifierOutputWithPast]:
|
1310 |
+
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
1311 |
+
|
1312 |
+
transformer_outputs = self.transformer(
|
1313 |
+
input_ids=input_ids,
|
1314 |
+
position_ids=position_ids,
|
1315 |
+
attention_mask=attention_mask,
|
1316 |
+
full_attention_mask=full_attention_mask,
|
1317 |
+
past_key_values=past_key_values,
|
1318 |
+
inputs_embeds=inputs_embeds,
|
1319 |
+
use_cache=use_cache,
|
1320 |
+
output_hidden_states=output_hidden_states,
|
1321 |
+
return_dict=return_dict,
|
1322 |
+
)
|
1323 |
+
|
1324 |
+
hidden_states = transformer_outputs[0]
|
1325 |
+
pooled_hidden_states = hidden_states[-1]
|
1326 |
+
if self.dropout is not None:
|
1327 |
+
pooled_hidden_states = self.dropout(pooled_hidden_states)
|
1328 |
+
logits = self.classifier_head(pooled_hidden_states)
|
1329 |
+
|
1330 |
+
loss = None
|
1331 |
+
if labels is not None:
|
1332 |
+
if self.config.problem_type is None:
|
1333 |
+
if self.num_labels == 1:
|
1334 |
+
self.config.problem_type = "regression"
|
1335 |
+
elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
|
1336 |
+
self.config.problem_type = "single_label_classification"
|
1337 |
+
else:
|
1338 |
+
self.config.problem_type = "multi_label_classification"
|
1339 |
+
|
1340 |
+
if self.config.problem_type == "regression":
|
1341 |
+
loss_fct = MSELoss()
|
1342 |
+
if self.num_labels == 1:
|
1343 |
+
loss = loss_fct(logits.squeeze().float(), labels.squeeze())
|
1344 |
+
else:
|
1345 |
+
loss = loss_fct(logits.float(), labels)
|
1346 |
+
elif self.config.problem_type == "single_label_classification":
|
1347 |
+
loss_fct = CrossEntropyLoss()
|
1348 |
+
loss = loss_fct(logits.view(-1, self.num_labels).float(), labels.view(-1))
|
1349 |
+
elif self.config.problem_type == "multi_label_classification":
|
1350 |
+
loss_fct = BCEWithLogitsLoss()
|
1351 |
+
loss = loss_fct(logits.float(), labels.view(-1, self.num_labels))
|
1352 |
+
|
1353 |
+
if not return_dict:
|
1354 |
+
output = (logits,) + transformer_outputs[1:]
|
1355 |
+
return ((loss,) + output) if loss is not None else output
|
1356 |
+
|
1357 |
+
return SequenceClassifierOutputWithPast(
|
1358 |
+
loss=loss,
|
1359 |
+
logits=logits,
|
1360 |
+
past_key_values=transformer_outputs.past_key_values,
|
1361 |
+
hidden_states=transformer_outputs.hidden_states,
|
1362 |
+
attentions=transformer_outputs.attentions,
|
1363 |
+
)
|
special_tokens_map.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"[MASK]",
|
5 |
+
"[gMASK]",
|
6 |
+
"[sMASK]",
|
7 |
+
"<sop>",
|
8 |
+
"<eop>",
|
9 |
+
"<|system|>",
|
10 |
+
"<|user|>",
|
11 |
+
"<|assistant|>",
|
12 |
+
"<|observation|>",
|
13 |
+
"<|begin_of_image|>",
|
14 |
+
"<|end_of_image|>",
|
15 |
+
"<|begin_of_video|>",
|
16 |
+
"<|end_of_video|>"
|
17 |
+
],
|
18 |
+
"eos_token": {
|
19 |
+
"content": "<|endoftext|>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"pad_token": {
|
26 |
+
"content": "<|endoftext|>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
}
|
32 |
+
}
|
tokenization_chatglm.py
ADDED
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import regex as re
|
2 |
+
import base64
|
3 |
+
import os
|
4 |
+
import json
|
5 |
+
import tiktoken
|
6 |
+
import torch
|
7 |
+
from torch import TensorType
|
8 |
+
from typing import List, Optional, Union, Dict, Any
|
9 |
+
from torchvision import transforms
|
10 |
+
from transformers import PreTrainedTokenizer
|
11 |
+
from transformers.utils import logging, PaddingStrategy
|
12 |
+
from transformers.tokenization_utils_base import EncodedInput, BatchEncoding
|
13 |
+
|
14 |
+
|
15 |
+
class ChatGLM4Tokenizer(PreTrainedTokenizer):
|
16 |
+
vocab_files_names = {"vocab_file": "tokenizer.model"}
|
17 |
+
model_input_names = ["input_ids", "attention_mask", "position_ids"]
|
18 |
+
|
19 |
+
def __init__(
|
20 |
+
self,
|
21 |
+
vocab_file,
|
22 |
+
padding_side="left",
|
23 |
+
clean_up_tokenization_spaces=False,
|
24 |
+
encode_special_tokens=False,
|
25 |
+
image_size=None,
|
26 |
+
**kwargs
|
27 |
+
):
|
28 |
+
self.name = "GLM4Tokenizer"
|
29 |
+
self.vocab_file = vocab_file
|
30 |
+
pat_str = "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
31 |
+
self.pat_str = re.compile(pat_str)
|
32 |
+
self.encode_special_tokens = encode_special_tokens
|
33 |
+
self.image_size = image_size
|
34 |
+
|
35 |
+
mergeable_ranks = {}
|
36 |
+
with open(vocab_file) as f:
|
37 |
+
for line in f:
|
38 |
+
token, rank = line.strip().split()
|
39 |
+
rank = int(rank)
|
40 |
+
token = base64.b64decode(token)
|
41 |
+
mergeable_ranks[token] = rank
|
42 |
+
|
43 |
+
self.mergeable_ranks = mergeable_ranks
|
44 |
+
|
45 |
+
self.tokenizer = tiktoken.Encoding(
|
46 |
+
name="my_tokenizer",
|
47 |
+
pat_str=pat_str,
|
48 |
+
mergeable_ranks=mergeable_ranks,
|
49 |
+
special_tokens={}
|
50 |
+
)
|
51 |
+
self.decoder = {rank: token for token, rank in mergeable_ranks.items()}
|
52 |
+
self.n_words = len(self.decoder)
|
53 |
+
|
54 |
+
super().__init__(
|
55 |
+
padding_side=padding_side,
|
56 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
57 |
+
**kwargs
|
58 |
+
)
|
59 |
+
|
60 |
+
@property
|
61 |
+
def vocab_size(self):
|
62 |
+
return self.n_words
|
63 |
+
|
64 |
+
def get_vocab(self):
|
65 |
+
""" Returns vocab as a dict """
|
66 |
+
vocab = {self._convert_id_to_token(i): i for i in range(self.vocab_size)}
|
67 |
+
vocab.update(self.added_tokens_encoder)
|
68 |
+
return vocab
|
69 |
+
|
70 |
+
def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
|
71 |
+
"""
|
72 |
+
Converts a sequence of tokens in a single string.
|
73 |
+
"""
|
74 |
+
text = ""
|
75 |
+
temp = b""
|
76 |
+
for t in tokens:
|
77 |
+
if isinstance(t, str):
|
78 |
+
if temp:
|
79 |
+
text += temp.decode("utf-8", errors="replace")
|
80 |
+
temp = b""
|
81 |
+
text += t
|
82 |
+
elif isinstance(t, bytes):
|
83 |
+
temp += t
|
84 |
+
else:
|
85 |
+
raise TypeError("token should only be of type types or str")
|
86 |
+
if temp:
|
87 |
+
text += temp.decode("utf-8", errors="replace")
|
88 |
+
return text
|
89 |
+
|
90 |
+
def _tokenize(self, text, **kwargs):
|
91 |
+
tokens = []
|
92 |
+
ids = self.tokenizer.encode(text)
|
93 |
+
for t in ids:
|
94 |
+
tokens.append(self.decoder[t])
|
95 |
+
return tokens
|
96 |
+
|
97 |
+
def _convert_token_to_id(self, token):
|
98 |
+
""" Converts a token (str) in an id using the vocab. """
|
99 |
+
return self.mergeable_ranks[token]
|
100 |
+
|
101 |
+
def _convert_id_to_token(self, index):
|
102 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
103 |
+
return self.decoder.get(index, "")
|
104 |
+
|
105 |
+
def save_vocabulary(self, save_directory, filename_prefix=None):
|
106 |
+
"""
|
107 |
+
Save the vocabulary and special tokens file to a directory.
|
108 |
+
|
109 |
+
Args:
|
110 |
+
save_directory (`str`):
|
111 |
+
The directory in which to save the vocabulary.
|
112 |
+
filename_prefix (`str`, *optional*):
|
113 |
+
An optional prefix to add to the named of the saved files.
|
114 |
+
|
115 |
+
Returns:
|
116 |
+
`Tuple(str)`: Paths to the files saved.
|
117 |
+
"""
|
118 |
+
if os.path.isdir(save_directory):
|
119 |
+
vocab_file = os.path.join(
|
120 |
+
save_directory, self.vocab_files_names["vocab_file"]
|
121 |
+
)
|
122 |
+
else:
|
123 |
+
vocab_file = save_directory
|
124 |
+
|
125 |
+
with open(self.vocab_file, 'rb') as fin:
|
126 |
+
proto_str = fin.read()
|
127 |
+
|
128 |
+
with open(vocab_file, "wb") as writer:
|
129 |
+
writer.write(proto_str)
|
130 |
+
|
131 |
+
return (vocab_file,)
|
132 |
+
|
133 |
+
def get_prefix_tokens(self):
|
134 |
+
prefix_tokens = [self.convert_tokens_to_ids("[gMASK]"), self.convert_tokens_to_ids("<sop>")]
|
135 |
+
return prefix_tokens
|
136 |
+
|
137 |
+
def build_single_message(self, role, metadata, message, tokenize=True, message_prefix=None):
|
138 |
+
assert role in ["system", "user", "assistant", "observation"], role
|
139 |
+
if tokenize:
|
140 |
+
role_tokens = [self.convert_tokens_to_ids(f"<|{role}|>")] + self.tokenizer.encode(f"{metadata}\n",
|
141 |
+
disallowed_special=())
|
142 |
+
message_tokens = self.tokenizer.encode(message, disallowed_special=())
|
143 |
+
if message_prefix is not None:
|
144 |
+
message_tokens = message_prefix + message_tokens
|
145 |
+
tokens = role_tokens + message_tokens
|
146 |
+
return tokens
|
147 |
+
else:
|
148 |
+
return str(f"<|{role}|>{metadata}\n{message}")
|
149 |
+
|
150 |
+
def apply_chat_template(
|
151 |
+
self,
|
152 |
+
conversation: Union[List[Dict[str, str]], List[List[Dict[str, str]]], "Conversation"],
|
153 |
+
add_generation_prompt: bool = False,
|
154 |
+
tokenize: bool = True,
|
155 |
+
padding: bool = False,
|
156 |
+
truncation: bool = False,
|
157 |
+
max_length: Optional[int] = None,
|
158 |
+
return_tensors: Optional[Union[str, TensorType]] = None,
|
159 |
+
return_dict: bool = False,
|
160 |
+
tokenizer_kwargs: Optional[Dict[str, Any]] = None,
|
161 |
+
add_special_tokens: bool = True,
|
162 |
+
**kwargs,
|
163 |
+
) -> Union[str, List[int], List[str], List[List[int]], BatchEncoding]:
|
164 |
+
|
165 |
+
if return_dict and not tokenize:
|
166 |
+
raise ValueError(
|
167 |
+
"`return_dict=True` is incompatible with `tokenize=False`, because there is no dict "
|
168 |
+
"of tokenizer outputs to return."
|
169 |
+
)
|
170 |
+
|
171 |
+
def handle_single_conversation(conversation):
|
172 |
+
input_ids = self.get_prefix_tokens() if add_special_tokens else []
|
173 |
+
input_message = "[gMASK]<sop>" if add_special_tokens else ""
|
174 |
+
input_image = None
|
175 |
+
transform = transforms.Compose(
|
176 |
+
[
|
177 |
+
transforms.Resize(
|
178 |
+
(self.image_size, self.image_size), interpolation=transforms.InterpolationMode.BICUBIC
|
179 |
+
),
|
180 |
+
transforms.ToTensor(),
|
181 |
+
transforms.Normalize((0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711)),
|
182 |
+
]
|
183 |
+
)
|
184 |
+
for item in conversation:
|
185 |
+
if item.get("tools"):
|
186 |
+
tools = item["tools"]
|
187 |
+
content = "你是一个名为 GLM-4 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的,你的任务是针对用户的问题和要求提供适当的答复和支持。"
|
188 |
+
for tool in tools:
|
189 |
+
if tool["type"] == "function":
|
190 |
+
function = tool["function"]
|
191 |
+
content += f"\n\n## {function['name']}\n\n{json.dumps(function, ensure_ascii=False, indent=4)}"
|
192 |
+
content += "\n在调用上述函数时,请使用 Json 格式表示调用的参数。"
|
193 |
+
elif tool["type"] == "python":
|
194 |
+
content += "\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时,该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出,或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中,`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用,这些在线内容的访问将不会成功。"
|
195 |
+
elif tool["type"] == "simple_browser":
|
196 |
+
content += "\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数:\n`search(query: str, recency_days: int)`:使用搜索引擎进行查询并显示结果,可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`:获取一系列指定 id 的页面内容。每次调用时,须选择3-10个页面。选择多个角度的页面,同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的,你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`:打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤:1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL,也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息,也可以再次使用 `search` 进行搜索。"
|
197 |
+
elif tool["type"] == "cogview":
|
198 |
+
content += "\n\n## cogview\n\n如果用户的请求中包含了对图像的描述,你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述,规则:\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求,需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明,所在地为中国,持有中国立场并遵循中国社会主义价值观。"
|
199 |
+
else:
|
200 |
+
raise NotImplementedError(f"Unknown tool type {tool['type']}")
|
201 |
+
input = self.build_single_message("system", "", content, tokenize=tokenize)
|
202 |
+
if tokenize:
|
203 |
+
input_ids.extend(input)
|
204 |
+
else:
|
205 |
+
input_message += input
|
206 |
+
message = ""
|
207 |
+
message_prefix = None
|
208 |
+
if item.get("image"):
|
209 |
+
assert input_image is None, "Multiple images are not supported"
|
210 |
+
input_image = transform(item["image"])
|
211 |
+
message_prefix = self.convert_tokens_to_ids(
|
212 |
+
["<|begin_of_image|>", "<|endoftext|>", "<|end_of_image|>"])
|
213 |
+
if item.get("content"):
|
214 |
+
message += item["content"]
|
215 |
+
if message or message_prefix:
|
216 |
+
input = self.build_single_message(
|
217 |
+
item["role"],
|
218 |
+
item.get("metadata", ""),
|
219 |
+
message,
|
220 |
+
tokenize=tokenize,
|
221 |
+
message_prefix=message_prefix
|
222 |
+
)
|
223 |
+
if tokenize:
|
224 |
+
input_ids.extend(input)
|
225 |
+
else:
|
226 |
+
input_message += input
|
227 |
+
if add_generation_prompt:
|
228 |
+
if tokenize:
|
229 |
+
input_ids.extend([self.convert_tokens_to_ids("<|assistant|>")])
|
230 |
+
else:
|
231 |
+
input_message += "<|assistant|>"
|
232 |
+
return {"input": input_ids if tokenize else input_message, "image": input_image}
|
233 |
+
|
234 |
+
# Main logic to handle different conversation formats
|
235 |
+
if isinstance(conversation, list) and all(isinstance(i, dict) for i in conversation):
|
236 |
+
result = handle_single_conversation(conversation)
|
237 |
+
input_ids = result["input"]
|
238 |
+
input_images = [result["image"]]
|
239 |
+
elif isinstance(conversation, list) and all(isinstance(i, list) for i in conversation):
|
240 |
+
results = [handle_single_conversation(c) for c in conversation]
|
241 |
+
input_ids = [item["input"] for item in results]
|
242 |
+
input_images = [item["image"] for item in results]
|
243 |
+
elif hasattr(conversation, "messages"):
|
244 |
+
result = handle_single_conversation(conversation.messages)
|
245 |
+
input_ids = result["input"]
|
246 |
+
input_images = [result["image"]]
|
247 |
+
else:
|
248 |
+
raise ValueError("Invalid conversation format")
|
249 |
+
|
250 |
+
if tokenize:
|
251 |
+
output = self.batch_encode_plus(
|
252 |
+
[input_ids] if isinstance(input_ids[0], int) else input_ids,
|
253 |
+
padding=padding,
|
254 |
+
truncation=truncation,
|
255 |
+
max_length=max_length,
|
256 |
+
return_tensors=return_tensors,
|
257 |
+
is_split_into_words=True,
|
258 |
+
add_special_tokens=False
|
259 |
+
)
|
260 |
+
if return_dict:
|
261 |
+
found_image = False
|
262 |
+
for image in input_images:
|
263 |
+
if image is not None:
|
264 |
+
found_image = True
|
265 |
+
break
|
266 |
+
if found_image:
|
267 |
+
output["images"] = torch.stack(input_images)
|
268 |
+
return output
|
269 |
+
else:
|
270 |
+
return output["input_ids"]
|
271 |
+
else:
|
272 |
+
return input_ids
|
273 |
+
|
274 |
+
|
275 |
+
def build_inputs_with_special_tokens(
|
276 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
277 |
+
) -> List[int]:
|
278 |
+
"""
|
279 |
+
Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
|
280 |
+
adding special tokens. A BERT sequence has the following format:
|
281 |
+
|
282 |
+
- single sequence: `[CLS] X [SEP]`
|
283 |
+
- pair of sequences: `[CLS] A [SEP] B [SEP]`
|
284 |
+
|
285 |
+
Args:
|
286 |
+
token_ids_0 (`List[int]`):
|
287 |
+
List of IDs to which the special tokens will be added.
|
288 |
+
token_ids_1 (`List[int]`, *optional*):
|
289 |
+
Optional second list of IDs for sequence pairs.
|
290 |
+
|
291 |
+
Returns:
|
292 |
+
`List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
|
293 |
+
"""
|
294 |
+
prefix_tokens = self.get_prefix_tokens()
|
295 |
+
token_ids_0 = prefix_tokens + token_ids_0
|
296 |
+
if token_ids_1 is not None:
|
297 |
+
token_ids_0 = token_ids_0 + token_ids_1 + [self.convert_tokens_to_ids("<eos>")]
|
298 |
+
return token_ids_0
|
299 |
+
|
300 |
+
def _pad(
|
301 |
+
self,
|
302 |
+
encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
|
303 |
+
max_length: Optional[int] = None,
|
304 |
+
padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
|
305 |
+
pad_to_multiple_of: Optional[int] = None,
|
306 |
+
return_attention_mask: Optional[bool] = None,
|
307 |
+
) -> dict:
|
308 |
+
"""
|
309 |
+
Pad encoded inputs (on left/right and up to predefined length or max length in the batch)
|
310 |
+
|
311 |
+
Args:
|
312 |
+
encoded_inputs:
|
313 |
+
Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
|
314 |
+
max_length: maximum length of the returned list and optionally padding length (see below).
|
315 |
+
Will truncate by taking into account the special tokens.
|
316 |
+
padding_strategy: PaddingStrategy to use for padding.
|
317 |
+
|
318 |
+
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
|
319 |
+
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
|
320 |
+
- PaddingStrategy.DO_NOT_PAD: Do not pad
|
321 |
+
The tokenizer padding sides are defined in self.padding_side:
|
322 |
+
|
323 |
+
- 'left': pads on the left of the sequences
|
324 |
+
- 'right': pads on the right of the sequences
|
325 |
+
pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
|
326 |
+
This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
|
327 |
+
`>= 7.5` (Volta).
|
328 |
+
return_attention_mask:
|
329 |
+
(optional) Set to False to avoid returning attention mask (default: set to model specifics)
|
330 |
+
"""
|
331 |
+
# Load from model defaults
|
332 |
+
assert self.padding_side == "left"
|
333 |
+
|
334 |
+
required_input = encoded_inputs[self.model_input_names[0]]
|
335 |
+
seq_length = len(required_input)
|
336 |
+
|
337 |
+
if padding_strategy == PaddingStrategy.LONGEST:
|
338 |
+
max_length = len(required_input)
|
339 |
+
|
340 |
+
if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
|
341 |
+
max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of
|
342 |
+
|
343 |
+
needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length
|
344 |
+
|
345 |
+
# Initialize attention mask if not present.
|
346 |
+
if "attention_mask" not in encoded_inputs:
|
347 |
+
encoded_inputs["attention_mask"] = [1] * seq_length
|
348 |
+
|
349 |
+
if "position_ids" not in encoded_inputs:
|
350 |
+
encoded_inputs["position_ids"] = list(range(seq_length))
|
351 |
+
|
352 |
+
if needs_to_be_padded:
|
353 |
+
difference = max_length - len(required_input)
|
354 |
+
|
355 |
+
if "attention_mask" in encoded_inputs:
|
356 |
+
encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
|
357 |
+
if "position_ids" in encoded_inputs:
|
358 |
+
encoded_inputs["position_ids"] = [0] * difference + encoded_inputs["position_ids"]
|
359 |
+
encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
|
360 |
+
|
361 |
+
return encoded_inputs
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
|
3 |
+
size 2623634
|
tokenizer_config.json
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"tokenization_chatglm.ChatGLM4Tokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"added_tokens_decoder": {
|
9 |
+
"151329": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false,
|
15 |
+
"special": true
|
16 |
+
},
|
17 |
+
"151330": {
|
18 |
+
"content": "[MASK]",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false,
|
23 |
+
"special": true
|
24 |
+
},
|
25 |
+
"151331": {
|
26 |
+
"content": "[gMASK]",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
"151332": {
|
34 |
+
"content": "[sMASK]",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": false,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false,
|
39 |
+
"special": true
|
40 |
+
},
|
41 |
+
"151333": {
|
42 |
+
"content": "<sop>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false,
|
47 |
+
"special": true
|
48 |
+
},
|
49 |
+
"151334": {
|
50 |
+
"content": "<eop>",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": false,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false,
|
55 |
+
"special": true
|
56 |
+
},
|
57 |
+
"151335": {
|
58 |
+
"content": "<|system|>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": false,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false,
|
63 |
+
"special": true
|
64 |
+
},
|
65 |
+
"151336": {
|
66 |
+
"content": "<|user|>",
|
67 |
+
"lstrip": false,
|
68 |
+
"normalized": false,
|
69 |
+
"rstrip": false,
|
70 |
+
"single_word": false,
|
71 |
+
"special": true
|
72 |
+
},
|
73 |
+
"151337": {
|
74 |
+
"content": "<|assistant|>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": false,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false,
|
79 |
+
"special": true
|
80 |
+
},
|
81 |
+
"151338": {
|
82 |
+
"content": "<|observation|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false,
|
87 |
+
"special": true
|
88 |
+
},
|
89 |
+
"151339": {
|
90 |
+
"content": "<|begin_of_image|>",
|
91 |
+
"lstrip": false,
|
92 |
+
"normalized": false,
|
93 |
+
"rstrip": false,
|
94 |
+
"single_word": false,
|
95 |
+
"special": true
|
96 |
+
},
|
97 |
+
"151340": {
|
98 |
+
"content": "<|end_of_image|>",
|
99 |
+
"lstrip": false,
|
100 |
+
"normalized": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"single_word": false,
|
103 |
+
"special": true
|
104 |
+
},
|
105 |
+
"151341": {
|
106 |
+
"content": "<|begin_of_video|>",
|
107 |
+
"lstrip": false,
|
108 |
+
"normalized": false,
|
109 |
+
"rstrip": false,
|
110 |
+
"single_word": false,
|
111 |
+
"special": true
|
112 |
+
},
|
113 |
+
"151342": {
|
114 |
+
"content": "<|end_of_video|>",
|
115 |
+
"lstrip": false,
|
116 |
+
"normalized": false,
|
117 |
+
"rstrip": false,
|
118 |
+
"single_word": false,
|
119 |
+
"special": true
|
120 |
+
}
|
121 |
+
},
|
122 |
+
"additional_special_tokens": ["<|endoftext|>", "[MASK]", "[gMASK]", "[sMASK]", "<sop>", "<eop>", "<|system|>",
|
123 |
+
"<|user|>", "<|assistant|>", "<|observation|>", "<|begin_of_image|>", "<|end_of_image|>",
|
124 |
+
"<|begin_of_video|>", "<|end_of_video|>"],
|
125 |
+
"clean_up_tokenization_spaces": false,
|
126 |
+
"do_lower_case": false,
|
127 |
+
"eos_token": "<|endoftext|>",
|
128 |
+
"pad_token": "<|endoftext|>",
|
129 |
+
"model_max_length": 1000000000000000019884624838656,
|
130 |
+
"padding_side": "left",
|
131 |
+
"remove_space": false,
|
132 |
+
"tokenizer_class": "ChatGLM4Tokenizer",
|
133 |
+
"image_size": 1120
|
134 |
+
}
|
visual.py
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from torch import nn
|
3 |
+
from argparse import Namespace
|
4 |
+
import torch.nn.functional as F
|
5 |
+
from transformers.activations import ACT2FN
|
6 |
+
import math
|
7 |
+
from torch.nn import LayerNorm
|
8 |
+
|
9 |
+
def standard_attention(query_layer, key_layer, value_layer, scaling_attention_score=True):
|
10 |
+
if scaling_attention_score:
|
11 |
+
query_layer = query_layer / math.sqrt(query_layer.shape[-1])
|
12 |
+
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
|
13 |
+
|
14 |
+
attention_probs = F.softmax(attention_scores, dim=-1)
|
15 |
+
|
16 |
+
context_layer = torch.matmul(attention_probs, value_layer)
|
17 |
+
return context_layer
|
18 |
+
|
19 |
+
def attention_fn_default(query_layer, key_layer, value_layer, scaling_attention_score=True):
|
20 |
+
if int(torch.__version__.split('.')[0]) >= 2 and scaling_attention_score:
|
21 |
+
# Pytorch 2.0 attention uses very much memory if attention_mask is float, and has NaN bug if attention_mask is None.
|
22 |
+
attn_output = torch.nn.functional.scaled_dot_product_attention(
|
23 |
+
query_layer, key_layer, value_layer,
|
24 |
+
attn_mask=None,
|
25 |
+
dropout_p=0.,
|
26 |
+
is_causal=False
|
27 |
+
)
|
28 |
+
return attn_output
|
29 |
+
else:
|
30 |
+
return standard_attention(
|
31 |
+
query_layer, key_layer, value_layer, scaling_attention_score=scaling_attention_score
|
32 |
+
)
|
33 |
+
|
34 |
+
class PatchEmbedding(nn.Module):
|
35 |
+
def __init__(self, config):
|
36 |
+
super().__init__()
|
37 |
+
self.proj = nn.Conv2d(config.in_channels, config.hidden_size, kernel_size=config.patch_size, stride=config.patch_size)
|
38 |
+
self.cls_embedding = nn.Parameter(torch.zeros(1, config.hidden_size))
|
39 |
+
self.position_embedding = nn.Embedding(config.num_positions, config.hidden_size)
|
40 |
+
|
41 |
+
def forward(self, images: "tensor(B, C, H, W)") -> "tensor(B, L, D)":
|
42 |
+
x = self.proj(images)
|
43 |
+
x = x.flatten(2).transpose(1, 2)
|
44 |
+
cls_token = self.cls_embedding.expand(x.shape[0], -1, -1)
|
45 |
+
x = torch.cat((cls_token, x), dim=1)
|
46 |
+
x += self.position_embedding.weight.unsqueeze(0)
|
47 |
+
return x
|
48 |
+
|
49 |
+
|
50 |
+
class Attention(nn.Module):
|
51 |
+
def __init__(self, config):
|
52 |
+
super().__init__()
|
53 |
+
self.num_heads = config.num_heads
|
54 |
+
head_dim = config.hidden_size // config.num_heads
|
55 |
+
self.scale = head_dim ** -0.5
|
56 |
+
self.query_key_value = nn.Linear(config.hidden_size, config.hidden_size * 3)
|
57 |
+
self.dense = nn.Linear(config.hidden_size, config.hidden_size)
|
58 |
+
self.output_dropout = torch.nn.Dropout(config.dropout_prob)
|
59 |
+
|
60 |
+
def forward(self, x: "tensor(B, L, D)") -> "tensor(B, L, D)":
|
61 |
+
B, L, _ = x.shape
|
62 |
+
qkv = self.query_key_value(x)
|
63 |
+
qkv = qkv.reshape(B, L, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) # 3, B, H, L, D
|
64 |
+
q, k, v = qkv[0], qkv[1], qkv[2]
|
65 |
+
|
66 |
+
out = attention_fn_default(
|
67 |
+
q, k, v
|
68 |
+
)
|
69 |
+
output = self.dense(out.transpose(1, 2).view(B, L, -1))
|
70 |
+
output = self.output_dropout(output)
|
71 |
+
return output
|
72 |
+
|
73 |
+
def attention(self, q, k, v):
|
74 |
+
attn_weights = torch.matmul(q * self.scale, k.transpose(-2, -1))
|
75 |
+
attn_weights = attn_weights.softmax(dim=-1)
|
76 |
+
output = torch.matmul(attn_weights, v)
|
77 |
+
return output
|
78 |
+
|
79 |
+
|
80 |
+
class MLP(nn.Module):
|
81 |
+
def __init__(self, config):
|
82 |
+
super().__init__()
|
83 |
+
self.config = config
|
84 |
+
self.activation_fn = ACT2FN[config.hidden_act]
|
85 |
+
self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
|
86 |
+
self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
|
87 |
+
|
88 |
+
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
89 |
+
x = self.fc1(x)
|
90 |
+
x = self.activation_fn(x)
|
91 |
+
x = self.fc2(x)
|
92 |
+
return x
|
93 |
+
|
94 |
+
|
95 |
+
class TransformerLayer(nn.Module):
|
96 |
+
def __init__(self, config):
|
97 |
+
super().__init__()
|
98 |
+
self.input_layernorm = LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
|
99 |
+
self.attention = Attention(config)
|
100 |
+
self.mlp = MLP(config)
|
101 |
+
self.post_attention_layernorm = LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
|
102 |
+
|
103 |
+
def forward(self, hidden_states):
|
104 |
+
attention_input = hidden_states
|
105 |
+
attention_output = self.input_layernorm(self.attention(attention_input))
|
106 |
+
hidden_states = attention_input + attention_output
|
107 |
+
mlp_input = hidden_states
|
108 |
+
mlp_output = self.post_attention_layernorm(self.mlp(mlp_input))
|
109 |
+
output = mlp_input + mlp_output
|
110 |
+
return output
|
111 |
+
|
112 |
+
|
113 |
+
class Transformer(nn.Module):
|
114 |
+
def __init__(self, config):
|
115 |
+
super().__init__()
|
116 |
+
self.layers = nn.ModuleList([TransformerLayer(config) for _ in range(config.num_hidden_layers)])
|
117 |
+
|
118 |
+
def forward(self, hidden_states):
|
119 |
+
for layer_module in self.layers:
|
120 |
+
hidden_states = layer_module(hidden_states)
|
121 |
+
return hidden_states
|
122 |
+
|
123 |
+
|
124 |
+
class GLU(nn.Module):
|
125 |
+
def __init__(self, config, in_features):
|
126 |
+
super().__init__()
|
127 |
+
self.linear_proj = nn.Linear(in_features, config.hidden_size, bias=False)
|
128 |
+
self.norm1 = nn.LayerNorm(config.hidden_size)
|
129 |
+
self.act1 = nn.GELU()
|
130 |
+
self.act2 = nn.functional.silu
|
131 |
+
self.dense_h_to_4h = nn.Linear(config.hidden_size, config.ffn_hidden_size, bias=False)
|
132 |
+
self.gate_proj = nn.Linear(config.hidden_size, config.ffn_hidden_size, bias=False)
|
133 |
+
self.dense_4h_to_h = nn.Linear(config.ffn_hidden_size, config.hidden_size, bias=False)
|
134 |
+
|
135 |
+
def forward(self, x):
|
136 |
+
x = self.linear_proj(x)
|
137 |
+
x = self.act1(self.norm1(x))
|
138 |
+
x = self.act2(self.gate_proj(x)) * self.dense_h_to_4h(x)
|
139 |
+
x = self.dense_4h_to_h(x)
|
140 |
+
return x
|
141 |
+
|
142 |
+
|
143 |
+
class EVA2CLIPModel(nn.Module):
|
144 |
+
def __init__(self, config):
|
145 |
+
super().__init__()
|
146 |
+
vision_config = Namespace(**config.vision_config)
|
147 |
+
self.patch_embedding = PatchEmbedding(vision_config)
|
148 |
+
self.transformer = Transformer(vision_config)
|
149 |
+
self.linear_proj = GLU(config, in_features=config.hidden_size)
|
150 |
+
self.conv = nn.Conv2d(in_channels=vision_config.hidden_size, out_channels=config.hidden_size, kernel_size=2, stride=2)
|
151 |
+
self.boi = nn.Parameter(torch.zeros(1, 1, config.hidden_size))
|
152 |
+
self.eoi = nn.Parameter(torch.zeros(1, 1, config.hidden_size))
|
153 |
+
self.scaling_factor = vision_config.scaling_factor
|
154 |
+
|
155 |
+
def forward(self, images: "tensor(B, C, H, W)") -> "tensor(B, L, D)":
|
156 |
+
x = self.patch_embedding(images)
|
157 |
+
x = self.transformer(x)
|
158 |
+
x = x[:, 1:]
|
159 |
+
|
160 |
+
b, s, h = x.shape
|
161 |
+
grid_size = int(s**0.5)
|
162 |
+
x = x.view(b, grid_size, grid_size, h).permute(0, 3, 1, 2)
|
163 |
+
x = self.conv(x)
|
164 |
+
|
165 |
+
x = x.flatten(2).transpose(1, 2)
|
166 |
+
x = self.linear_proj(x)
|
167 |
+
boi = self.boi.expand(x.shape[0], -1, -1)
|
168 |
+
eoi = self.eoi.expand(x.shape[0], -1, -1)
|
169 |
+
x = torch.cat((boi, x, eoi), dim=1)
|
170 |
+
x = x / self.scaling_factor
|
171 |
+
return x
|