DipanAI commited on
Commit
1b4958e
1 Parent(s): dc70f80

Upload config

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "RWForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
11
+ "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 4544,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "RefinedWebModel",
25
+ "multi_query": true,
26
+ "n_head": 71,
27
+ "n_layer": 32,
28
+ "parallel_attn": true,
29
+ "quantization_config": {
30
+ "bnb_4bit_compute_dtype": "float16",
31
+ "bnb_4bit_quant_type": "nf4",
32
+ "bnb_4bit_use_double_quant": false,
33
+ "llm_int8_enable_fp32_cpu_offload": false,
34
+ "llm_int8_has_fp16_weight": false,
35
+ "llm_int8_skip_modules": null,
36
+ "llm_int8_threshold": 6.0,
37
+ "load_in_4bit": true,
38
+ "load_in_8bit": false
39
+ },
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.30.0.dev0",
42
+ "use_cache": true,
43
+ "vocab_size": 65024
44
+ }