Update config.json
Browse files- config.json +15 -30
config.json
CHANGED
@@ -1,34 +1,19 @@
|
|
1 |
{
|
2 |
"base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
],
|
8 |
-
"
|
9 |
-
"auto_map": {
|
10 |
-
"AutoConfig": "configuration_falcon.FalconConfig",
|
11 |
-
"AutoModel": "modeling_falcon.FalconModel",
|
12 |
-
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
|
13 |
-
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
|
14 |
-
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
|
15 |
-
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
|
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 |
-
"parallel_attn": true,
|
30 |
-
"torch_dtype": "bfloat16",
|
31 |
-
"transformers_version": "4.27.4",
|
32 |
-
"use_cache": true,
|
33 |
-
"vocab_size": 65024
|
34 |
}
|
|
|
1 |
{
|
2 |
"base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.05,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 16,
|
14 |
+
"revision": null,
|
15 |
+
"target_modules": [
|
16 |
+
"query_key_value"
|
17 |
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|