Upload LlamaForSequenceClassification

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "NEUTRAL",
+    "2": "POSITIVE",
+    "3": "MIXED"
+  },
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "label2id": {
+    "MIXED": 3,
+    "NEGATIVE": 0,
+    "NEUTRAL": 1,
+    "POSITIVE": 2
+  },
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 49152
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b075cabf9d494bc22faccf86b85b3711b4ebe8c0e672dcca06a2f8bc3e41b61
+size 538099704