Hugging Face's logo

2024-mcm-everitt-ryan
/
gemma-2-9b-job-bias-qlora-seq-cls

Text Classification
Transformers
Safetensors
English
gemma2
Eval Results
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
gemma-2-9b-job-bias-qlora-seq-cls
File size: 1,784 Bytes 
1d7e1c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "_name_or_path": "google/gemma-2-9b",
  "architectures": [
    "Gemma2ForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_logit_softcapping": 50.0,
  "bos_token_id": 2,
  "cache_implementation": "hybrid",
  "eos_token_id": 1,
  "final_logit_softcapping": 30.0,
  "head_dim": 256,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_activation": "gelu_pytorch_tanh",
  "hidden_size": 3584,
  "id2label": {
    "0": "age",
    "1": "disability",
    "2": "feminine",
    "3": "general",
    "4": "masculine",
    "5": "neutral",
    "6": "racial",
    "7": "sexuality"
  },
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "label2id": {
    "age": 0,
    "disability": 1,
    "feminine": 2,
    "general": 3,
    "masculine": 4,
    "neutral": 5,
    "racial": 6,
    "sexuality": 7
  },
  "max_position_embeddings": 8192,
  "model_type": "gemma2",
  "num_attention_heads": 16,
  "num_hidden_layers": 42,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "problem_type": "multi_label_classification",
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "query_pre_attn_scalar": 256,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "sliding_window_size": 4096,
  "torch_dtype": "float32",
  "transformers_version": "4.42.4",
  "use_cache": true,
  "vocab_size": 256000
}