thejagstudio commited on
Commit
110ede8
1 Parent(s): d24f9d1

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +30 -22
config.json CHANGED
@@ -1,25 +1,33 @@
1
  {
2
- "_name_or_path": "thejagstudio/Falcon-7b-Fined-Tuned",
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
5
- "bias": "none",
6
- "fan_in_fan_out": false,
7
- "inference_mode": true,
8
- "init_lora_weights": true,
9
- "layers_pattern": null,
10
- "layers_to_transform": null,
11
- "lora_alpha": 16,
12
- "lora_dropout": 0.1,
13
- "modules_to_save": null,
14
- "peft_type": "LORA",
15
- "r": 64,
16
- "revision": null,
17
- "target_modules": [
18
- "query_key_value",
19
- "dense",
20
- "dense_h_to_4h",
21
- "dense_4h_to_h"
22
  ],
23
- "task_type": "CAUSAL_LM",
24
- "model_type": "RefinedWebModel"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
 
1
  {
2
+ "_name_or_path": "tiiuae/falcon-7b",
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
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.30.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 65024
33
  }