Lil2J commited on
Commit
e662c97
1 Parent(s): 83f68d9

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./model_save/pre1/checkpoint-1689",
3
+ "architectures": [
4
+ "QWenLMHeadModel"
5
+ ],
6
+ "attn_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_qwen.QWenConfig",
9
+ "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel"
10
+ },
11
+ "bf16": true,
12
+ "emb_dropout_prob": 0.0,
13
+ "fp16": false,
14
+ "fp32": false,
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "kv_channels": 128,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_position_embeddings": 8192,
21
+ "model_type": "qwen",
22
+ "no_bias": true,
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 16,
25
+ "onnx_safe": null,
26
+ "rotary_emb_base": 10000,
27
+ "rotary_pct": 1.0,
28
+ "scale_attn_weights": true,
29
+ "seq_length": 8192,
30
+ "softmax_in_fp32": false,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "QWenTokenizer",
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.32.0",
35
+ "use_cache": true,
36
+ "use_cache_kernel": false,
37
+ "use_cache_quantization": false,
38
+ "use_dynamic_ntk": true,
39
+ "use_flash_attn": true,
40
+ "use_logn_attn": true,
41
+ "vocab_size": 151936
42
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.32.0"
4
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee44089a0170ba8059f3233ff3f3af65f72a3635359674a37451e8eb10765c03
3
+ size 2864036054
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "<|im_end|>"
3
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_qwen.QWenTokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "clean_up_tokenization_spaces": true,
9
+ "model_max_length": 8192,
10
+ "tokenizer_class": "QWenTokenizer"
11
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff