Upload LlamaForCausalLM

config.json

@@ -4,27 +4,43 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 768,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 2048,
+  "intermediate_size": 768,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 12,
-  "pad_token_id": 0,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.1",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,7 +1,10 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "transformers_version": "4.54.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5af49d3cf4e8de6e5208c9e11d5a3effb421b2385d0ec0b93e79e3f125ef094
-size 136062744
+oid sha256:e2c5aeb07d4e6e23406ee8bcb36b04700fb73364cdebe8991491dab02777a9f3
+size 150233704