Upload LlamaForCausalLM
Browse files- config.json +0 -1
- generation_config.json +1 -1
config.json
CHANGED
@@ -14,7 +14,6 @@
|
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 32,
|
17 |
-
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
|
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
16 |
"num_key_value_heads": 32,
|
|
|
17 |
"pretraining_tp": 1,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_scaling": null,
|
generation_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"eos_token_id": 2,
|
4 |
"max_length": 4096,
|
5 |
"max_memory": {
|
6 |
-
"cpu":
|
7 |
},
|
8 |
"no_split_module_classes": [
|
9 |
"LlamaDecoderLayer"
|
|
|
3 |
"eos_token_id": 2,
|
4 |
"max_length": 4096,
|
5 |
"max_memory": {
|
6 |
+
"cpu": 27833966592
|
7 |
},
|
8 |
"no_split_module_classes": [
|
9 |
"LlamaDecoderLayer"
|