fc

.streamlit/secrets.toml

@@ -0,0 +1 @@
+api_key = "Bearer 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"

app.py

@@ -0,0 +1,64 @@
+import streamlit as st
+from streamlit_chat import message
+import requests
+from transformers import AutoModelWithLMHead, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained('microsoft/DialoGPT-small')
+model = AutoModelWithLMHead.from_pretrained('output-small-save')
+
+st.set_page_config(
+    page_title="COVID Doctor using DialoGPT",
+    page_icon=":robot:"
+)
+
+API_URL = "https://api-inference.huggingface.co/models/microsoft/DialoGPT-small"
+headers = {"Authorization": st.secrets['api_key']}
+
+st.header("Hello - Welcome to COVID Doctor using DialoGPT")
+st.markdown("[Github](https://github.com/rushic24/DialoGPT-Finetune)")
+
+if 'generated' not in st.session_state:
+    st.session_state['generated'] = []
+
+if 'past' not in st.session_state:
+    st.session_state['past'] = []
+
+def query(payload):
+    bot_input_ids = tokenizer.encode(payload.text + tokenizer.eos_token, return_tensors='pt')
+
+    chat_history_ids = model.generate(
+      bot_input_ids, max_length=100,
+      pad_token_id=tokenizer.eos_token_id,  
+      no_repeat_ngram_size=3,       
+      do_sample=True, 
+      top_k=10, 
+      top_p=0.7,
+      temperature = 0.8
+    )
+    output = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return {"generated_text": output}
+
+def get_text():
+    input_text = st.text_input("You: ","Hello, how are you?", key="input")
+    return input_text 
+
+
+user_input = get_text()
+
+if user_input:
+    output = query({
+        "inputs": {
+            "past_user_inputs": st.session_state.past,
+            "generated_responses": st.session_state.generated,
+            "text": user_input,
+        },"parameters": {"repetition_penalty": 1.33},
+    })
+    st.session_state.past.append(user_input)
+    st.session_state.generated.append(output["generated_text"])
+
+if st.session_state['generated']:
+
+    for i in range(len(st.session_state['generated'])-1, -1, -1):
+        message(st.session_state["generated"][i], key=str(i))
+        message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')
+

output-small-save/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-small",
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

output-small-save/eval_results.txt

@@ -0,0 +1 @@
+perplexity = tensor(14.1139)

output-small-save/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5daa96e110d2152fc73fe678e43840bc3dfde47bebef78509e547998c6642c
+size 510396521

output-small-save/special_tokens_map.json

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

output-small-save/tokenizer_config.json

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

output-small-save/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd284c2fddc21cfdc730eadda9ac9e85effb9459b9eed4096cca7edb48d7cd41
+size 1327