Upload LlamaForCausalLM

config.json

@@ -4,26 +4,36 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 32,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 128,
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "max_position_embeddings": 2048,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.50.3",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,6 +1,10 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "transformers_version": "4.50.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32e7a376fe46206644c14a61471adc8c171f039b8679f54c3574275189395cf
-size 39457496
+oid sha256:43426d0d4bbea538b7c5921613b85c62218d3898ecd1776f331264a3594ec993
+size 474503296