test

config.json

@@ -1,33 +1,34 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "Pereki/llama-2-7b-chat-hf",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 16,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "up_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "v_proj"
+  "_name_or_path": "/home/alexandre/research/distilbert/pruned80_vnni/zoomodels/framework",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "vocab_size": 30522
+}

handler.py

@@ -1,38 +1,31 @@
-from typing import  Dict, List, Any
-from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from typing import Dict, Any
+from deepsparse import Pipeline
+from time import perf_counter
+
+class EndpointHandler:
 
-class EndpointHandler():
     def __init__(self, path=""):
-        quantization_config = BitsAndBytesConfig(load_in_4bit=True,  bnb_4bit_compute_dtype=torch.float16)
-        # load the optimized model
-        tokenizer = AutoTokenizer.from_pretrained(path)
-        model = AutoModelForCausalLM.from_pretrained(
-        path,
-        quantization_config=quantization_config,
-        device_map="auto",
-        torch_dtype='auto'
-        ).eval()
-        # create inference pipeline
-        self.pipeline = pipeline("text-classification", model=model, tokenizer=tokenizer)
 
+        self.pipeline = Pipeline.create(
+            task="text-classification", 
+            model_path=path, 
+            scheduler=”sync
+        )
 
-    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
         """
         Args:
-            data (:obj:):
-                includes the input data and the parameters for the inference.
-        Return:
-            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
-                - "label": A string representing what the label/class is. There can be multiple labels.
-                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
+            data (:obj:): prediction input text
         """
         inputs = data.pop("inputs", data)
-        parameters = data.pop("parameters", None)
 
-        # pass inputs with all kwargs in data
-        if parameters is not None:
-            prediction = self.pipeline(inputs, **parameters)
-        else:
-            prediction = self.pipeline(inputs)
-        # postprocess the prediction
-        return prediction
+        start = perf_counter()
+        prediction = self.pipeline(inputs)
+        end = perf_counter()
+        latency = end - start
+
+        return {
+            "labels": prediction.labels, 
+            "scores": prediction.scores,
+            "latency (secs.)": latency
+        }

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f814a1a6b4f818e07d1183e2204eedd0fb8c8fdd708326e5d97ce4ee44c3e5
+size 67197076

requirements.txt

@@ -0,0 +1 @@
+deepsparse>=1.2.0

test.py

@@ -0,0 +1,7 @@
+from sparsezoo import Model
+
+stub = "zoo:nlp/sentiment_analysis/distilbert-none/pytorch/huggingface/sst2/pruned80_quant-none-vnni"
+model = Model(stub, download_path="./deep")
+
+# Downloads and prints the download path of the model 
+print(model.deployment.path)

tokenizer_config.json

@@ -1,42 +1 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/alexandre/research/bert_base/sst2/framework", "tokenizer_class": "BertTokenizer"}