TheBloke
/

vicuna-13B-v1.5-16K-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

TheBloke commited on Aug 9, 2023

Commit

43d3d60

•

1 Parent(s): 642c7ef

Initial GPTQ model commit

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-    "_name_or_path": "vicuna-13b-v1.5-16k",
     "architectures": [
         "LlamaForCausalLM"
     ],
@@ -9,8 +9,8 @@
     "hidden_size": 5120,
     "initializer_range": 0.02,
     "intermediate_size": 13824,
-    "max_sequence_length": 16384,
     "max_position_embeddings": 4096,
     "model_type": "llama",
     "num_attention_heads": 40,
     "num_hidden_layers": 40,

 {
+    "_name_or_path": "vicuna-13b-v1.5-16k/",
     "architectures": [
         "LlamaForCausalLM"
     ],
     "hidden_size": 5120,
     "initializer_range": 0.02,
     "intermediate_size": 13824,
     "max_position_embeddings": 4096,
+    "max_sequence_length": 16384,
     "model_type": "llama",
     "num_attention_heads": 40,
     "num_hidden_layers": 40,