Upload config
Browse files- config.json +2 -7
- config.py +1 -1
config.json
CHANGED
@@ -1,12 +1,8 @@
|
|
1 |
{
|
2 |
-
"architectures": [
|
3 |
-
"BharataiForCausalLM"
|
4 |
-
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"auto_map": {
|
8 |
-
"AutoConfig": "config.BharataiConfig"
|
9 |
-
"AutoModelForCausalLM": "model.BharataiForCausalLM"
|
10 |
},
|
11 |
"bos_token_id": 1,
|
12 |
"eos_token_id": 2,
|
@@ -15,7 +11,7 @@
|
|
15 |
"initializer_range": 0.02,
|
16 |
"intermediate_size": 11008,
|
17 |
"max_position_embeddings": 2048,
|
18 |
-
"model_type": "
|
19 |
"num_attention_heads": 8,
|
20 |
"num_hidden_layers": 8,
|
21 |
"num_key_value_heads": 8,
|
@@ -24,7 +20,6 @@
|
|
24 |
"rope_scaling": null,
|
25 |
"rope_theta": 10000.0,
|
26 |
"tie_word_embeddings": false,
|
27 |
-
"torch_dtype": "float32",
|
28 |
"transformers_version": "4.36.0.dev0",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 5000
|
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"attention_bias": false,
|
3 |
"attention_dropout": 0.0,
|
4 |
"auto_map": {
|
5 |
+
"AutoConfig": "config.BharataiConfig"
|
|
|
6 |
},
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 11008,
|
13 |
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "BharataiForCausalLM",
|
15 |
"num_attention_heads": 8,
|
16 |
"num_hidden_layers": 8,
|
17 |
"num_key_value_heads": 8,
|
|
|
20 |
"rope_scaling": null,
|
21 |
"rope_theta": 10000.0,
|
22 |
"tie_word_embeddings": false,
|
|
|
23 |
"transformers_version": "4.36.0.dev0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 5000
|
config.py
CHANGED
@@ -78,7 +78,7 @@ class BharataiConfig(PretrainedConfig):
|
|
78 |
|
79 |
```"""
|
80 |
|
81 |
-
model_type = "
|
82 |
keys_to_ignore_at_inference = ["past_key_values"]
|
83 |
|
84 |
def __init__(
|
|
|
78 |
|
79 |
```"""
|
80 |
|
81 |
+
model_type = "BharataiForCausalLM"
|
82 |
keys_to_ignore_at_inference = ["past_key_values"]
|
83 |
|
84 |
def __init__(
|