test

app.py

@@ -85,9 +85,7 @@ def main(api_name, base_url):
     #model = BertLMHeadModel.from_pretrained('google/codegemma-2b', is_decoder=True)
     # Example assuming you have a prepared dataset for classification
     #model = BertForSequenceClassification.from_pretrained('thenlper/gte-small', num_labels=2, is_decoder=True)  # binary classification
-    # Example: Offloading embeddings to CPU
-    model.embeddings.to('cpu')
-
+    
     model.to(device)  # Move model to the appropriate device
 
     train_model(model, tokenizer, data, device)

fine_tuned_model/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/codegemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "is_decoder": true,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}