Spaces:
Sleeping
Sleeping
Commit
•
042c583
1
Parent(s):
d72bc8c
Initial commit with fine-tuned GPT-2 model and Streamlit app
Browse files
app.py
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
3 |
+
import gradio as gr
|
4 |
+
import torch
|
5 |
+
#from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
6 |
+
|
7 |
+
#import pickle
|
8 |
+
|
9 |
+
|
10 |
+
title = "🤖Deployment GUVI GPT Model using Hugging Face"
|
11 |
+
description = "Building open-domain chatbots is a challenging area for machine learning research."
|
12 |
+
examples = [["Guvi Details"]]
|
13 |
+
|
14 |
+
model_name = "fine_tuned_model123"
|
15 |
+
#model = GPT2LMHeadModel.from_pretrained(model_name)
|
16 |
+
#tokenizer = GPT2Tokenizer.from_pretrained(model_name)
|
17 |
+
|
18 |
+
# Load the tokenizer and model from Hugging Face Hub
|
19 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
20 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
21 |
+
|
22 |
+
def predict(input, history=[]):
|
23 |
+
# tokenize the new input sentence
|
24 |
+
new_user_input_ids = tokenizer.encode(
|
25 |
+
input + tokenizer.eos_token, return_tensors="pt"
|
26 |
+
)
|
27 |
+
|
28 |
+
# append the new user input tokens to the chat history
|
29 |
+
bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
|
30 |
+
|
31 |
+
# generate a response
|
32 |
+
history = model.generate(
|
33 |
+
bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
|
34 |
+
).tolist()
|
35 |
+
|
36 |
+
# convert the tokens to text, and then split the responses into lines
|
37 |
+
response = tokenizer.decode(history[0]).split("<|endoftext|>")
|
38 |
+
# print('decoded_response-->>'+str(response))
|
39 |
+
response = [
|
40 |
+
(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
|
41 |
+
] # convert to tuples of list
|
42 |
+
# print('response-->>'+str(response))
|
43 |
+
return response, history
|
44 |
+
|
45 |
+
|
46 |
+
gr.Interface(
|
47 |
+
fn=predict,
|
48 |
+
title=title,
|
49 |
+
description=description,
|
50 |
+
examples=examples,
|
51 |
+
inputs=["text", "state"],
|
52 |
+
outputs=["chatbot", "state"],
|
53 |
+
theme="finlaymacklon/boxy_violet",
|
54 |
+
).launch()
|
fine_tuned_model123/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.41.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
fine_tuned_model123/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
+
}
|
fine_tuned_model123/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
fine_tuned_model123/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
fine_tuned_model123/tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"bos_token": "<|endoftext|>",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"errors": "replace",
|
18 |
+
"model_max_length": 1024,
|
19 |
+
"pad_token": null,
|
20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
21 |
+
"unk_token": "<|endoftext|>"
|
22 |
+
}
|
fine_tuned_model123/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
transformers
|
3 |
+
torch
|
4 |
+
streamlit
|