Upload 8 files

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "/Users/migueldeguzman/Desktop/gpt2xl_algos/RLLMv10/v7/",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66592567ee15e4531d96c620346607ae327e531dee6b7376fe1e0c8e161af07
+size 6230624769

simulator-temp70_with_timestamp_100.py

@@ -0,0 +1,58 @@
+import torch
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+import time
+
+class GPT2Assistant:
+    def __init__(self, model_dir):
+        self.model = GPT2LMHeadModel.from_pretrained(model_dir)
+        self.tokenizer = GPT2Tokenizer.from_pretrained(model_dir)
+
+    def generate_answer(self, prompt, max_length=1024):
+        input_ids = self.tokenizer.encode(prompt, return_tensors="pt")
+        if self.tokenizer.pad_token_id is None:
+            self.tokenizer.pad_token = self.tokenizer.eos_token
+
+        attention_mask = (input_ids != self.tokenizer.pad_token_id).long()
+        output = self.model.generate(
+            input_ids,
+            attention_mask=attention_mask,
+            max_length=max_length,
+            num_return_sequences=1,
+            no_repeat_ngram_size=2,
+            do_sample=True,
+            top_k=50,
+            top_p=0.95,
+            temperature=0.70
+        )
+
+        answer = self.tokenizer.decode(output[0], skip_special_tokens=True)
+        return answer[len(prompt):]
+
+    def query(self, prompt):
+        generated_answer = self.generate_answer(prompt)
+        return generated_answer
+
+def main():
+    start_time = time.time()
+
+    model_output_dir = "/Users/migueldeguzman/Desktop/gpt2xl_algos/RLLMv10/v8-ice-cream-v1/"
+    assistant = GPT2Assistant(model_output_dir)
+
+    num_iterations = 50
+    prompt = input(f"Enter your question to ask the model {num_iterations} times: ")
+
+    for i in range(num_iterations):
+        print(f"Answering question {i + 1}/{num_iterations}...")
+        response = assistant.query(prompt)
+        print(f"Response {i + 1}: {response}\n")
+
+        end_time = time.time()
+        elapsed_time = (end_time - start_time) / 60  # Convert to minutes
+        print(f"Time-stamp: {elapsed_time:.2f} minutes")
+
+    end_time = time.time()
+    elapsed_time = (end_time - start_time) / 60  # Convert to minutes
+    print(f"Time taken to complete the task: {elapsed_time:.2f} minutes")
+
+if __name__ == "__main__":
+    main()

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}