YALCINKAYA commited on
Commit
8d553cd
1 Parent(s): 5d7d723

Upload GPTNeoForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. config.json +99 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,6 @@
1
  ---
2
  license: apache-2.0
 
 
 
3
  ---
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-2.7B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "classifier_dropout": 0.1,
53
+ "embed_dropout": 0,
54
+ "eos_token_id": 50256,
55
+ "gradient_checkpointing": false,
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": null,
59
+ "layer_norm_epsilon": 1e-05,
60
+ "max_position_embeddings": 2048,
61
+ "model_type": "gpt_neo",
62
+ "num_heads": 20,
63
+ "num_layers": 32,
64
+ "pretraining_tp": 1,
65
+ "quantization_config": {
66
+ "_load_in_4bit": false,
67
+ "_load_in_8bit": true,
68
+ "bnb_4bit_compute_dtype": "float32",
69
+ "bnb_4bit_quant_storage": "uint8",
70
+ "bnb_4bit_quant_type": "fp4",
71
+ "bnb_4bit_use_double_quant": false,
72
+ "llm_int8_enable_fp32_cpu_offload": false,
73
+ "llm_int8_has_fp16_weight": false,
74
+ "llm_int8_skip_modules": null,
75
+ "llm_int8_threshold": 6.0,
76
+ "load_in_4bit": false,
77
+ "load_in_8bit": true,
78
+ "quant_method": "bitsandbytes"
79
+ },
80
+ "resid_dropout": 0,
81
+ "summary_activation": null,
82
+ "summary_first_dropout": 0.1,
83
+ "summary_proj_to_labels": true,
84
+ "summary_type": "cls_index",
85
+ "summary_use_proj": true,
86
+ "task_specific_params": {
87
+ "text-generation": {
88
+ "do_sample": true,
89
+ "max_length": 50,
90
+ "temperature": 0.9
91
+ }
92
+ },
93
+ "tokenizer_class": "GPT2Tokenizer",
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.45.2",
96
+ "use_cache": false,
97
+ "vocab_size": 50257,
98
+ "window_size": 256
99
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.45.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56d63e535689948dae6c3ab6be30cdff9c89dc9bc78d58f3ef747e32af6150a
3
+ size 3068860552