sangmini
/

Meta-Llama-3-8B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

sangmini commited on May 20

Commit

d43a751

•

1 Parent(s): 648d256

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "kuotient/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,7 +19,7 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",

 {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 81920,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 200000000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",