RichardErkhov
commited on
Commit
•
bcaf7a3
1
Parent(s):
1b8823d
uploaded model
Browse files- config.json +98 -0
config.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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 |
+
"quantization_config": {
|
65 |
+
"_load_in_4bit": false,
|
66 |
+
"_load_in_8bit": true,
|
67 |
+
"bnb_4bit_compute_dtype": "float32",
|
68 |
+
"bnb_4bit_quant_storage": "uint8",
|
69 |
+
"bnb_4bit_quant_type": "fp4",
|
70 |
+
"bnb_4bit_use_double_quant": false,
|
71 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
72 |
+
"llm_int8_has_fp16_weight": false,
|
73 |
+
"llm_int8_skip_modules": null,
|
74 |
+
"llm_int8_threshold": 6.0,
|
75 |
+
"load_in_4bit": false,
|
76 |
+
"load_in_8bit": true,
|
77 |
+
"quant_method": "bitsandbytes"
|
78 |
+
},
|
79 |
+
"resid_dropout": 0,
|
80 |
+
"summary_activation": null,
|
81 |
+
"summary_first_dropout": 0.1,
|
82 |
+
"summary_proj_to_labels": true,
|
83 |
+
"summary_type": "cls_index",
|
84 |
+
"summary_use_proj": true,
|
85 |
+
"task_specific_params": {
|
86 |
+
"text-generation": {
|
87 |
+
"do_sample": true,
|
88 |
+
"max_length": 50,
|
89 |
+
"temperature": 0.9
|
90 |
+
}
|
91 |
+
},
|
92 |
+
"tokenizer_class": "GPT2Tokenizer",
|
93 |
+
"torch_dtype": "float16",
|
94 |
+
"transformers_version": "4.39.3",
|
95 |
+
"use_cache": true,
|
96 |
+
"vocab_size": 50257,
|
97 |
+
"window_size": 256
|
98 |
+
}
|