Upload LlamaForCausalLM
Browse files- config.json +4 -5
- generation_config.json +2 -2
config.json
CHANGED
@@ -1,20 +1,19 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "sharpbai/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
-
"bos_token_id":
|
7 |
-
"eos_token_id":
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
"max_position_embeddings": 2048,
|
13 |
-
"max_sequence_length": 2048,
|
14 |
"model_type": "llama",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
-
"pad_token_id":
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"tie_word_embeddings": false,
|
20 |
"torch_dtype": "float16",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "sharpbai/llama-7b-hf",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
"max_position_embeddings": 2048,
|
|
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
"rms_norm_eps": 1e-06,
|
18 |
"tie_word_embeddings": false,
|
19 |
"torch_dtype": "float16",
|
generation_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
"pad_token_id": 0,
|
6 |
"transformers_version": "4.30.1"
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
"pad_token_id": 0,
|
6 |
"transformers_version": "4.30.1"
|
7 |
}
|