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": 2,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0.dev0",
+  "rms_norm_eps": 1e-05,
+  "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,
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,6 +1,10 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.55.0.dev0"
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b93e16d46405615620d67e48ccc2950cf207f65c78390703a562b61e1638865
-size 8218384
+oid sha256:d36dd0a76fd31d98431972fefa6e3667f4a94c98923ebffd4f0b71e695d7d554
+size 4161744