first commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoModelWithLMHead, AutoTokenizer
+import torch
+
+def flatten(l):
+    return [item for sublist in l for item in sublist]
+
+tokenizer = AutoTokenizer.from_pretrained("model")
+model = AutoModelWithLMHead.from_pretrained("model")
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.ClearButton([msg, chatbot])
+
+    def respond(message, chat_history):
+        input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
+        if len(chat_history):
+            tokenized_chat_history = [tokenizer.encode(x + tokenizer.eos_token, return_tensors='pt')[0] for x in flatten(chat_history)]
+            tokenized_chat_history = torch.cat(tokenized_chat_history).unsqueeze(0)
+        bot_input_ids = torch.cat([tokenized_chat_history, input_ids], dim=-1) if len(chat_history) else input_ids
+        output = model.generate(
+            bot_input_ids,
+            max_new_tokens=50, 
+            pad_token_id=tokenizer.eos_token_id,
+            do_sample=True,
+            top_k=50,
+            top_p=0.95,
+        )
+        bot_message = str(tokenizer.decode(output[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True))
+        chat_history.append((message, bot_message))
+        return "", chat_history
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+demo.launch()

model/added_tokens.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45618a46ae539c9ff102239db581a014f77f6dcd76a3cf6ef92e08223d25de68
+size 24

model/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410b155448976f61f3c5a36732411b49df18839c8f6b84b16080c5ed6c817fee
+size 948

model/eval_results.txt

@@ -0,0 +1 @@
+loss = tensor(2.4251)

model/generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3854cdd3fd2790a634d50e21520681f0ca1eca532df38b35dd10f7af176e2860
+size 125

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3b56c3412583582d423f14b29502b09619ba65486a6c0fd15f5bebe8e4f936
+size 1419391965

model/special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3571944d01dcab472528bad2e0a358bac38fd385ba5d499f2a9892043da0f8b6
+size 486

model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f683f0962ce6bc4f1488383ae983a11ebc689bd3ffd963c14c3117831cd545
+size 2107833

model/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7378573bdde7414178d6d207843c0aecb37f314085ada2adadb64602ef5870
+size 760

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2015d34d755eed00335e05d6536772d06dfa1bd32871d27ce87746d177a87c0a
+size 1147

model/vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba3c3109ff33976c4bd966589c11ee14fcaa1f4c9e5e154c2ed7f99d80709e7
+size 798156

requirements.txt

@@ -0,0 +1,3 @@
+gradio==3.38.0
+transformers==4.30.2
+torch==2.0.1