beomi
/

Llama-3-Open-Ko-8B

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

beomi commited on Apr 30

Commit

75b0b10

•

1 Parent(s): f518d5c

Upload config

Files changed (1) hide show

config.json +6 -5

config.json CHANGED Viewed

@@ -1,10 +1,12 @@
 {
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -14,14 +16,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 128256
 }

 {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 128256
 }