Upload LlamaForSequenceClassification

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "HuggingFaceTB/SmolLM-135M",
   "architectures": [
     "LlamaForSequenceClassification"
   ],
@@ -10,9 +9,10 @@
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
-  "initializer_range": 0.02,
+  "initializer_range": 0.041666666666666664,
   "intermediate_size": 1536,
-  "max_position_embeddings": 2048,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 9,
@@ -21,11 +21,12 @@
   "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 100000,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.55.0",
   "use_cache": true,
   "vocab_size": 49152
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc0d940752badc483c93507fb84144d7f8ddf0e8aa6bff4130e96e425081b21
+oid sha256:6b9dd2b0108157f0668b65c18e9c18ffbd1dee7ebb4f535a75c30af33e68be7f
 size 538095096