Upload 5 files

config.json

@@ -1,33 +1 @@
-{
-  "_name_or_path": "ai-forever/sage-fredt5-distilled-95m",
-  "architectures": [
-    "T5ForConditionalGeneration"
-  ],
-  "bos_token_id": 1,
-  "classifier_dropout": 0.0,
-  "d_ff": 1024,
-  "d_kv": 64,
-  "d_model": 512,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 2,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "max_length": 256,
-  "model_type": "t5",
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "transformers_version": "4.33.2",
-  "use_cache": true,
-  "vocab_size": 50364
-}
+{"model_name": "encoder_model_quantized", "device": "cpu"}

flare_model.py

@@ -1,25 +1,2 @@
-
-import random
-import json
-
-class FlareModel:
-    def __init__(self):
-        self.context = {}
-    
-    def analyze_message(self, message):
-        # Пример анализа сообщения
-        return f"Сообщение анализируется: {message}"
-    
-    def generate_response(self, message):
-        responses = [
-            "Привет, как я могу помочь?",
-            "Что-то еще? Спрашивай!",
-            "А что ты думаешь о том, что я только что сказал?"
-        ]
-        return random.choice(responses)
-    
-    def load_context(self, data):
-        self.context.update(data)
-    
-    def get_context(self):
-        return self.context
+# Model code for inference goes here
+print("Model loaded and ready for inference!")

generation_config.json

@@ -1,9 +1 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 2,
-  "max_length": 256,
-  "pad_token_id": 0,
-  "transformers_version": "4.33.2"
-}
+{"top_k": 50, "top_p": 0.95, "temperature": 0.7}

requirements.txt

@@ -1,2 +1,4 @@
 torch
 transformers
+onnx
+flask

run_flare.bat

@@ -0,0 +1,2 @@
+@echo off
+python flare_model.py --input "Enter your prompt"