madhiarasan commited on
Commit
1bbe699
1 Parent(s): 0836349

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +47 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tiiuae/falcon-7b-instruct",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "FalconForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_falcon.FalconConfig",
11
+ "AutoModel": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-7b-instruct--modeling_falcon.FalconForTokenClassification"
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": "falcon",
25
+ "multi_query": true,
26
+ "new_decoder_architecture": false,
27
+ "num_attention_heads": 71,
28
+ "num_hidden_layers": 32,
29
+ "num_kv_heads": 71,
30
+ "parallel_attn": true,
31
+ "quantization_config": {
32
+ "bnb_4bit_compute_dtype": "float32",
33
+ "bnb_4bit_quant_type": "fp4",
34
+ "bnb_4bit_use_double_quant": false,
35
+ "llm_int8_enable_fp32_cpu_offload": false,
36
+ "llm_int8_has_fp16_weight": false,
37
+ "llm_int8_skip_modules": null,
38
+ "llm_int8_threshold": 6.0,
39
+ "load_in_4bit": false,
40
+ "load_in_8bit": true,
41
+ "quant_method": "bitsandbytes"
42
+ },
43
+ "torch_dtype": "float16",
44
+ "transformers_version": "4.35.2",
45
+ "use_cache": true,
46
+ "vocab_size": 65024
47
+ }