Duplicate from georgesung/llama2_7b_uncensored_chat

Co-authored-by: George Sung <georgesung@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,13 @@
+---
+title: Llama2 7b Uncensored Chat
+emoji: 🏢
+colorFrom: blue
+colorTo: pink
+sdk: gradio
+sdk_version: 3.37.0
+app_file: app.py
+pinned: false
+duplicated_from: georgesung/llama2_7b_uncensored_chat
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,78 @@
+from transformers import LlamaForCausalLM, LlamaTokenizer, pipeline
+import torch
+
+import gradio as gr
+
+# LLM helper functions
+def get_response_text(data):
+    text = data[0]["generated_text"]
+
+    assistant_text_index = text.rfind('### RESPONSE:')
+    if assistant_text_index != -1:
+        text = text[assistant_text_index+len('### RESPONSE:'):].strip()
+
+    return text
+
+def get_llm_response(prompt, pipe):
+    raw_output = pipe(prompt)
+    text = get_response_text(raw_output)
+    return text
+
+# Load LLM
+model_id = "georgesung/llama2_7b_chat_uncensored"
+tokenizer = LlamaTokenizer.from_pretrained(model_id)
+model = LlamaForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True)
+
+# Llama tokenizer missing pad token
+tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_length=4096,  # Llama-2 default context window
+    temperature=0.7,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
+
+    def hist_to_prompt(history):
+        prompt = ""
+        for human_text, bot_text in history:
+            prompt += f"### HUMAN:\n{human_text}\n\n### RESPONSE:\n"
+            if bot_text:
+                prompt += f"{bot_text}\n\n"
+        return prompt
+
+    def get_bot_response(text):
+        bot_text_index = text.rfind('### RESPONSE:')
+        if bot_text_index != -1:
+            text = text[bot_text_index + len('### RESPONSE:'):].strip()
+        return text
+
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
+
+    def bot(history):
+        #bot_message = random.choice(["How are you?", "I love you", "I'm very hungry"])
+        #history[-1][1] = bot_message + '</s>'
+
+        hist_text = hist_to_prompt(history)
+        print(hist_text)
+        bot_message = get_llm_response(hist_text, pipe) + tokenizer.eos_token
+        history[-1][1] = bot_message  # add bot message to overall history
+
+        return history
+
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+torch
+sentencepiece
+accelerate
+bitsandbytes
+scipy