Cesar42
/

TrainLlama2Dataset

Text Generation

Trained with AutoTrain

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Cesar42 commited on Oct 13, 2023

Commit

b33e2ef

•

1 Parent(s): 805a9e3

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,7 +9,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
-  "max_position_embeddings": 4096,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,7 +19,7 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000

 {
+  "_name_or_path": "TheBloke/Llama-2-7B-fp16",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32000