build: AutoGPTQ for meta-llama/Llama-2-7b-chat-hf: 4bits, gr128, desc_act=False
Browse files- config.json +1 -0
config.json
CHANGED
@@ -9,6 +9,7 @@
|
|
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,
|
|
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
+
"max_length": 4096,
|
13 |
"max_position_embeddings": 2048,
|
14 |
"model_type": "llama",
|
15 |
"num_attention_heads": 32,
|