Upload 74 files

Dockerfile

@@ -0,0 +1,19 @@
+
+FROM python:3.10
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,187 @@
+"""FastAPI endpoint
+To run locally use 'uvicorn app:app --host localhost --port 7860'
+or
+`python -m uvicorn app:app --reload --host localhost --port 7860`
+"""
+import datetime as dt
+import json
+import logging
+import numpy as np
+import os
+import random
+from typing import Dict, List
+
+import uvicorn
+from fastapi import FastAPI, HTTPException, Request, Response
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from fastapi.templating import Jinja2Templates
+
+import scripts.sentiment as sentiment
+import scripts.twitter_scraper as ts
+import scripts.utils as utils
+from scripts import generative
+
+logging.basicConfig(level=logging.INFO)
+
+app = FastAPI()
+templates = Jinja2Templates(directory="templates")
+app.mount("/static", StaticFiles(directory="static"), name="static")
+# Construct absolute path to models folder
+models_path = os.path.abspath("models")
+
+username_list = [
+    "alikarimi_ak8",
+    "elonmusk",
+    "BarackObama",
+    "taylorlorenz",
+    "cathiedwood",
+    "ylecun",
+]
+
+## Static objects/paths
+start_date = dt.date(year=2023, month=2, day=1)
+end_date = dt.date(year=2023, month=3, day=22)
+
+
+@app.get("/", response_class=HTMLResponse)
+async def webpage(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+
+@app.get("/accounts", response_model=List[dict])
+def get_accounts() -> List[dict]:
+    logging.info(f"Pulling account information on {username_list}")
+    account_info_list = [
+        ts.get_twitter_account_info(twitter_handle=account) for account in username_list
+    ]
+    return account_info_list
+
+
+@app.get("/tweets/{username}", response_model=dict)
+def get_tweets(username: str) -> dict:
+    if username in username_list:
+        #query = f"from:{username} since:{start_date} until:{end_date}"
+        return ts.get_tweets(query=query)
+    else:
+        return {"detail": "Account not in scope of project."}
+
+
+@app.get("/audience/{username}", response_model=dict)
+def get_audience(username: str) -> dict:
+    if username in username_list:
+        query = f"from:{username} since:{start_date} until:{end_date}"
+        tweets = ts.get_tweets(query=query)
+
+        n_samples = 5
+        # Random sample 3 tweets from user
+        tweets_sampled = random.sample(tweets, n_samples)
+
+        # Get all replies to sampled tweets
+        tweet_threads = []
+        for tweet in tweets_sampled:
+            threads = ts.get_replies(
+                username=tweet["username"],
+                conversation_id=tweet["conversation_id"],
+                max_tweets=100,
+            )
+            tweet_threads += threads
+
+        # Get usernames from sample threads tweets
+        usernames = [t["username"] for t in tweet_threads]
+        # Get user info from sample replies to sampled tweets of user
+        info_accounts = [
+            ts.get_twitter_account_info(twitter_handle=account) for account in usernames
+        ]
+
+        # "follower_count":1,"friends_count":20,"verified":false}
+        # Get stats for followers/audience engaging with tweets
+        follower_counts = [
+            info_accounts[i]["follower_count"] for i in range(len(info_accounts))
+        ]
+        friends_counts = [
+            info_accounts[i]["friends_count"] for i in range(len(info_accounts))
+        ]
+        verified_counts = [
+            1 if info_accounts[i]["verified"] == True else 0
+            for i in range(len(info_accounts))
+        ]
+        return {
+            "sample_size": len(info_accounts),
+            "mean_follower_count": round(np.mean(follower_counts), 3),
+            "mean_friends_count": round(np.mean(friends_counts), 3),
+            "mean_verified": round(np.mean(verified_counts), 3),
+        }
+    else:
+        response = Response(content="Account not in scope of project.", status_code=404)
+        return response
+
+
+@app.get("/sentiment/{username}")
+async def get_sentiment(username: str) -> Dict[str, Dict[str, float]]:
+    if username not in username_list:
+        raise HTTPException(status_code=404, detail="Account not in scope of project.")
+
+    query = f"from:{username} since:{start_date} until:{end_date}"
+    tweets = ts.get_tweets(query=query)
+    n_samples = 5
+    tweets_sampled = random.sample(tweets, n_samples)
+
+    tweet_threads = []
+    for tweet in tweets_sampled:
+        threads = ts.get_replies(
+            username=tweet["username"],
+            conversation_id=tweet["conversation_id"],
+            max_tweets=100,
+        )
+        tweet_threads += threads
+
+    print(
+        f"Total replies to {n_samples} sampled tweets from username: {username}, {len(tweet_threads)}"
+    )
+
+    ## Sentiment scoring
+    print(f"Running tweet sentiment scoring on username: {username} tweets")
+    tweets_scores = sentiment.get_tweets_sentiment(tweets=tweets)
+    mean_tweets_score = round(np.mean(tweets_scores), 2)
+    ci_tweets = utils.wilson_score_interval(tweets_scores)
+
+    # Get sentiment of the threads from tweets
+    # Get username tweets sentiment
+    print(f"Running tweet thread sentiment scoring on username: {username} tweets")
+    threads_scores = sentiment.get_tweets_sentiment(tweets=tweet_threads)
+    mean_threads_score = round(np.mean(threads_scores), 2)
+    ci_threads = utils.wilson_score_interval(threads_scores)
+
+    return {
+        "thread_level": {
+            "mean": mean_threads_score,
+            "confidence_interal": ci_threads,
+        },
+        "audience_level": {
+            "mean": mean_tweets_score,
+            "confidence_interval": ci_tweets,
+        },
+    }
+
+
+@app.post("/api/generate")
+# async def generate_text(account: str, text: str):
+async def generate_text(request: Request):
+
+    data = await request.json()
+    print("*"*50)
+    print("POST Request:")
+    print(data['account'],data['text'])
+    generated_text = generative.generate_account_text(
+        prompt=data['text'], model_dir=os.path.join(models_path, data['account'])
+    )
+    # return one example
+    generated_text = generated_text[0]["generated_text"]
+    return {"generated_text": generated_text}
+
+
+
+# if __name__ == "__main__":
+#     # uvicorn.run(app, host="0.0.0.0", port=8000)
+#     uvicorn.run("app:app", host="127.0.0.1", port=5049, reload=True)

models/BarackObama/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/BarackObama/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/BarackObama/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c6382bf4651ffdfb464fcafe980119de8bf39d52e7e1ba5678130fcd1e9469
+size 510395581

models/BarackObama/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/BarackObama/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/BarackObama/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71684cf5cce747c17720cae37368baf794483b4018c616e0d26487886590e338
+size 3387

models/alikarimi_ak8/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/alikarimi_ak8/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/alikarimi_ak8/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfffa9a2034ca45dd1be4946de2c080045ed4c221e652275f13024078cd8e604
+size 510395581

models/alikarimi_ak8/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/alikarimi_ak8/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/alikarimi_ak8/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20869c5642f6be95f3a342a6133749dd150bfdecffedab7860d7e767a521ed74
+size 3387

models/cathiedwood/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/cathiedwood/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/cathiedwood/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecac4ae5b95aa181da1616db839314ca186f138d59bd2322960623bc537497e9
+size 510395581

models/cathiedwood/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/cathiedwood/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/cathiedwood/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e74b31b37904075ebd8760cd82fe42a6f239f874c9989a7fc199126050a4a5
+size 3387

models/elonmusk/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/elonmusk/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/elonmusk/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0305a3b73d7f97d5fd0ac0409407fe5fa80e32de4f5ae8b73305bbab896aff5
+size 510395581

models/elonmusk/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/elonmusk/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/elonmusk/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c50926e7c005b420f813373fa239e70fac310bdbcafef95f95dfb1e3145c544
+size 3387

models/taylorlorenz/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/taylorlorenz/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/taylorlorenz/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5075410d32a65bc98c38d578df472ecb270124c0f053b73477e6b7f1b3377003
+size 510395581

models/taylorlorenz/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/taylorlorenz/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/taylorlorenz/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad406657c6f7bdf6c5a07979f9b57f380adf0376b6c3d99b27a1ce2f9903e9f6
+size 3387

models/ylecun/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

models/ylecun/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

models/ylecun/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfffa9a2034ca45dd1be4946de2c080045ed4c221e652275f13024078cd8e604
+size 510395581

models/ylecun/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/ylecun/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/ylecun/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20869c5642f6be95f3a342a6133749dd150bfdecffedab7860d7e767a521ed74
+size 3387