Update config.json
Browse files- config.json +38 -18
config.json
CHANGED
|
@@ -1,20 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
"inference_mode": true,
|
| 7 |
-
"init_lora_weights": true,
|
| 8 |
-
"layers_pattern": null,
|
| 9 |
-
"layers_to_transform": null,
|
| 10 |
-
"lora_alpha": 32,
|
| 11 |
-
"lora_dropout": 0.05,
|
| 12 |
-
"modules_to_save": null,
|
| 13 |
-
"peft_type": "LORA",
|
| 14 |
-
"r": 16,
|
| 15 |
-
"revision": null,
|
| 16 |
-
"target_modules": [
|
| 17 |
-
"query_key_value"
|
| 18 |
],
|
| 19 |
-
"
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Hugging Face's logo
|
| 2 |
+
Hugging Face
|
| 3 |
+
Search models, datasets, users...
|
| 4 |
+
Models
|
| 5 |
+
Datasets
|
| 6 |
+
|
| 7 |
{
|
| 8 |
+
"alibi": false,
|
| 9 |
+
"apply_residual_connection_post_layernorm": false,
|
| 10 |
+
"architectures": [
|
| 11 |
+
"FalconForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
],
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"auto_map": {
|
| 15 |
+
"AutoConfig": "configuration_falcon.FalconConfig",
|
| 16 |
+
"AutoModel": "modeling_falcon.FalconModel",
|
| 17 |
+
"AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
|
| 18 |
+
"AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
|
| 19 |
+
"AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
|
| 20 |
+
"AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
|
| 21 |
+
},
|
| 22 |
+
"bias": false,
|
| 23 |
+
"bos_token_id": 11,
|
| 24 |
+
"eos_token_id": 11,
|
| 25 |
+
"hidden_dropout": 0.0,
|
| 26 |
+
"hidden_size": 4544,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"layer_norm_epsilon": 1e-05,
|
| 29 |
+
"model_type": "falcon",
|
| 30 |
+
"multi_query": true,
|
| 31 |
+
"new_decoder_architecture": false,
|
| 32 |
+
"num_attention_heads": 71,
|
| 33 |
+
"num_hidden_layers": 32,
|
| 34 |
+
"parallel_attn": true,
|
| 35 |
+
"torch_dtype": "bfloat16",
|
| 36 |
+
"transformers_version": "4.27.4",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 65024
|
| 39 |
+
}
|
| 40 |
+
|