Upload LlamaForCausalLM

config.json

@@ -5,20 +5,19 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 16,
   "initializer_range": 0.02,
-  "intermediate_size": 64,
+  "intermediate_size": 32,
   "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 4,
-  "pad_token_id": -1,
+  "num_key_value_heads": 2,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": -1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.39.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f67a5c69a424890b1e1e8d0caa601e5ed0a5e71a6bfc05babb79ea614a3725
-size 4131280
+oid sha256:b778d76fb5199ed6dac95ea7a9ad9116c5a79e689ef2bc6b5c25ad53b89cac0e
+size 4116936