Hugging Face's logo

vasimakram01
/
f_07_with_new_data

Text Generation
Transformers
RefinedWebModel
custom_code
text-generation-inference
4-bit precision
Model card Files Community
f_07_with_new_data
File size: 1,456 Bytes 
384941f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{ "_name_or_path": "tiiuae/falcon-7b",
  "alibi": false, 
  "apply_residual_connection_post_layernorm": false, 
  "architectures": [ "RWForCausalLM" ], 
  "attention_dropout": 0.0, 
  "auto_map": {
    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel", 
    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM", 
    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering", 
    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification" }, 
  "bias": false, 
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 0.0, 
  "hidden_size": 4544,
  "initializer_range": 0.02, 
  "layer_norm_epsilon": 1e-05,
  "model_type": "RefinedWebModel",
  "multi_query": true, 
  "n_head": 71,
  "n_layer": 32,
  "parallel_attn": true, 
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "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 },
  "torch_dtype": "bfloat16", 
  "transformers_version": "4.30.0.dev0",
  "use_cache": true, 
  "vocab_size": 65024 }