haqishen
/

h2o-Llama-3-8B-Japanese-Instruct

Text Generation

large language model

text-generation-inference

Model card Files Files and versions Community

haqishen commited on Jun 24

Commit

6bc49b5

•

1 Parent(s): cdc92ad

Upload config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "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,
@@ -16,14 +16,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 128001,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
   "use_cache": true,
   "vocab_size": 128256
 }

   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 128009,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 128256
 }