Hugging Face's logo

PrunaAI
/
DiatWork-GPT-Neox-MentalHealth-Finetune-10epoch-bnb-8bit-smashed

Safetensors
gpt_neo
pruna-ai
8-bit precision
bitsandbytes
Model card Files Community
1
DiatWork-GPT-Neox-MentalHealth-Finetune-10epoch-bnb-8bit-smashed
File size: 2,433 Bytes 
39a6b97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
 
{
    "_name_or_path": "/covalent/.cache/models/tmpedjt4xk980koy55w",
    "activation_function": "gelu_new",
    "architectures": [
        "GPTNeoForCausalLM"
    ],
    "attention_dropout": 0,
    "attention_layers": [
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local",
        "global",
        "local"
    ],
    "attention_types": [
        [
            [
                "global",
                "local"
            ],
            16
        ]
    ],
    "bos_token_id": 50256,
    "classifier_dropout": 0.1,
    "embed_dropout": 0,
    "eos_token_id": 50256,
    "gradient_checkpointing": false,
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": null,
    "layer_norm_epsilon": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "gpt_neo",
    "num_heads": 20,
    "num_layers": 32,
    "quantization_config": {
        "_load_in_4bit": false,
        "_load_in_8bit": true,
        "bnb_4bit_compute_dtype": "bfloat16",
        "bnb_4bit_quant_storage": "uint8",
        "bnb_4bit_quant_type": "fp4",
        "bnb_4bit_use_double_quant": false,
        "llm_int8_enable_fp32_cpu_offload": false,
        "llm_int8_has_fp16_weight": false,
        "llm_int8_skip_modules": [
            "lm_head"
        ],
        "llm_int8_threshold": 6.0,
        "load_in_4bit": false,
        "load_in_8bit": true,
        "quant_method": "bitsandbytes"
    },
    "resid_dropout": 0,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "task_specific_params": {
        "text-generation": {
            "do_sample": true,
            "max_length": 50,
            "temperature": 0.9
        }
    },
    "tokenizer_class": "GPT2Tokenizer",
    "torch_dtype": "float16",
    "transformers_version": "4.46.2",
    "use_cache": true,
    "vocab_size": 50257,
    "window_size": 256,
    "api_key": null
}