Upload LlamaForSequenceClassification

config.json

@@ -4,32 +4,42 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 2,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 8,
+  "hidden_size": 2048,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 32,
+  "intermediate_size": 8192,
   "label2id": {
     "LABEL_0": 0
   },
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 4,
+  "num_attention_heads": 32,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 2,
+  "num_key_value_heads": 8,
   "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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d11e2fb5b68abc4d3d4b78722417662b56bdcd507d6e4c61c164f42549ee70b
-size 4114216
+oid sha256:d7a0431983bacba6a2633d3027af2503fefc64f5522fd30877fd84330d054466
+size 768637224