cleanup

.gitignore

@@ -0,0 +1,165 @@
+
+tmp/
+
+# Below are from https://github.com/github/gitignore/blob/main/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE.txt

@@ -0,0 +1,126 @@
+LLAMA 2 COMMUNITY LICENSE AGREEMENT	
+Llama 2 Version Release Date: July 18, 2023
+
+"Agreement" means the terms and conditions for use, reproduction, distribution and 
+modification of the Llama Materials set forth herein.
+
+"Documentation" means the specifications, manuals and documentation 
+accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
+libraries/llama-downloads/.
+
+"Licensee" or "you" means you, or your employer or any other person or entity (if 
+you are entering into this Agreement on such person or entity's behalf), of the age 
+required under applicable laws, rules or regulations to provide legal consent and that 
+has legal authority to bind your employer or such other person or entity if you are 
+entering in this Agreement on their behalf.
+
+"Llama 2" means the foundational large language models and software and 
+algorithms, including machine-learning model code, trained model weights, 
+inference-enabling code, training-enabling code, fine-tuning enabling code and other 
+elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
+libraries/llama-downloads/.
+
+"Llama Materials" means, collectively, Meta's proprietary Llama 2 and 
+Documentation (and any portion thereof) made available under this Agreement.
+
+"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you 
+are an entity, your principal place of business is in the EEA or Switzerland) and Meta 
+Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+By clicking "I Accept" below or by using or distributing any portion or element of the 
+Llama Materials, you agree to be bound by this Agreement.
+
+1. License Rights and Redistribution. 
+
+      a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
+transferable and royalty-free limited license under Meta's intellectual property or 
+other rights owned by Meta embodied in the Llama Materials to use, reproduce, 
+distribute, copy, create derivative works of, and make modifications to the Llama 
+Materials.  
+      
+      b. Redistribution and Use.  
+
+            i. If you distribute or make the Llama Materials, or any derivative works 
+thereof, available to a third party, you shall provide a copy of this Agreement to such 
+third party. 
+            ii.  If you receive Llama Materials, or any derivative works thereof, from 
+a Licensee as part of an integrated end user product, then Section 2 of this 
+Agreement will not apply to you. 
+
+            iii. You must retain in all copies of the Llama Materials that you 
+distribute the following attribution notice within a "Notice" text file distributed as a 
+part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License, 
+Copyright (c) Meta Platforms, Inc. All Rights Reserved."
+
+            iv. Your use of the Llama Materials must comply with applicable laws 
+and regulations (including trade compliance laws and regulations) and adhere to the 
+Acceptable Use Policy for the Llama Materials (available at 
+https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into 
+this Agreement.
+
+            v. You will not use the Llama Materials or any output or results of the 
+Llama Materials to improve any other large language model (excluding Llama 2 or 
+derivative works thereof).  
+
+2. Additional Commercial Terms. If, on the Llama 2 version release date, the 
+monthly active users of the products or services made available by or for Licensee, 
+or Licensee's affiliates, is greater than 700 million monthly active users in the 
+preceding calendar month, you must request a license from Meta, which Meta may 
+grant to you in its sole discretion, and you are not authorized to exercise any of the 
+rights under this Agreement unless or until Meta otherwise expressly grants you 
+such rights.
+            
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE 
+LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE 
+PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, 
+EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY 
+WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR 
+FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE 
+FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING 
+THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR 
+USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE 
+LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, 
+NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS 
+AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, 
+CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF 
+ANY OF THE FOREGOING.
+ 
+5. Intellectual Property.
+
+      a. No trademark licenses are granted under this Agreement, and in 
+connection with the Llama Materials, neither Meta nor Licensee may use any name 
+or mark owned by or associated with the other or any of its affiliates, except as 
+required for reasonable and customary use in describing and redistributing the 
+Llama Materials.
+
+      b. Subject to Meta's ownership of Llama Materials and derivatives made by or 
+for Meta, with respect to any derivative works and modifications of the Llama 
+Materials that are made by you, as between you and Meta, you are and will be the 
+owner of such derivative works and modifications.
+
+      c. If you institute litigation or other proceedings against Meta or any entity 
+(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama 
+Materials or Llama 2 outputs or results, or any portion of any of the foregoing, 
+constitutes infringement of intellectual property or other rights owned or licensable 
+by you, then any licenses granted to you under this Agreement shall terminate as of 
+the date such litigation or claim is filed or instituted. You will indemnify and hold 
+harmless Meta from and against any claim by any third party arising out of or related 
+to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your 
+acceptance of this Agreement or access to the Llama Materials and will continue in 
+full force and effect until terminated in accordance with the terms and conditions 
+herein. Meta may terminate this Agreement if you are in breach of any term or 
+condition of this Agreement. Upon termination of this Agreement, you shall delete 
+and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the 
+termination of this Agreement. 
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and 
+construed under the laws of the State of California without regard to choice of law 
+principles, and the UN Convention on Contracts for the International Sale of Goods 
+does not apply to this Agreement. The courts of California shall have exclusive 
+jurisdiction of any dispute arising out of this Agreement. 
+

README.md

@@ -1,13 +1,13 @@
 ---
 title: Kanji Streaming
-emoji: 🉑
-colorFrom: purple
-colorTo: gray
+emoji: 🉑 🈶 🈚 🈺
+colorFrom: yellow
+colorTo: purple
 sdk: gradio
 sdk_version: 4.19.2
-app_file: app.py
-pinned: false
-# suggested_hardware: a10g-small
+app_file: app-mixtral.py
+pinned: true
+suggested_hardware: a10g-small
 models:
 - mistralai/Mixtral-8x7B-Instruct-v0.1
 - runwayml/stable-diffusion-v1-5
@@ -16,4 +16,4 @@ models:
 
 ---
 
-Check out [original repo](https://github.com/AgainstEntropy/kanji) for mroe details!
+Check out the [original repo](https://github.com/AgainstEntropy/kanji) for mroe details!

USE_POLICY.md

@@ -0,0 +1,50 @@
+# Llama 2 Acceptable Use Policy
+
+Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
+
+## Prohibited Uses
+We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to: 
+
+1. Violate the law or others’ rights, including to:
+    1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as: 
+        1. Violence or terrorism 
+        2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+        3. Human trafficking, exploitation, and sexual violence
+        4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+        5. Sexual solicitation
+        6. Any other criminal activity
+    2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+    3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+    4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices 
+    5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
+    6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
+    7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system 
+
+
+
+2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
+    1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
+    2. Guns and illegal weapons (including weapon development)
+    3. Illegal drugs and regulated/controlled substances
+    4. Operation of critical infrastructure, transportation technologies, or heavy machinery
+    5. Self-harm or harm to others, including suicide, cutting, and eating disorders
+    6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+
+
+
+3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
+    1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+    2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+    3. Generating, promoting, or further distributing spam
+    4. Impersonating another individual without consent, authorization, or legal right
+    5. Representing that the use of Llama 2 or outputs are human-generated
+    6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+4. Fail to appropriately disclose to end users any known dangers of your AI system 
+
+Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+* Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
+* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [[email protected]](mailto:[email protected])
+

app-kanji-local-llama.py

@@ -0,0 +1,295 @@
+import argparse
+import os
+from queue import SimpleQueue
+from threading import Thread
+from typing import Iterator
+
+import gradio as gr
+import spaces
+import torch
+from gradio import Chatbot
+from image_utils import ImageStitcher
+from transformers import (AutoModelForCausalLM, AutoTokenizer,
+                          TextIteratorStreamer)
+
+from StreamDiffusionIO import LatentConsistencyModelStreamIO
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+DESCRIPTION = """\
+# Kanji-Streaming Chat
+
+🌍 This Space is adapted from [Llama-2-7b-chat](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat) space, demonstrating how to "chat" with LLM with [Kanji-Streaming](https://github.com/AgainstEntropy/kanji).
+
+🔨 The technique behind Kanji-Streaming is [StreamDiffusionIO](https://github.com/AgainstEntropy/StreamDiffusionIO), which is based on [StreamDiffusion](https://github.com/cumulo-autumn/StreamDiffusion), *but especially allows to render text streams into image streams*.
+
+🔎 For more details about Kanji-Streaming, take a look at the [github repository](https://github.com/AgainstEntropy/kanji).
+"""
+
+LICENSE = """
+<p/>
+
+---
+As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
+this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
+"""
+
+
+parser = argparse.ArgumentParser(description="Gradio launcher for Streaming-Kanji.")
+parser.add_argument(
+    "--llama_model_id_or_path",
+    type=str,
+    default="meta-llama/Llama-2-7b-chat-hf",
+    required=False,
+    help="Path to downloaded llama-chat-hf model or model identifier from huggingface.co/models.",
+)
+parser.add_argument(
+    "--sd_model_id_or_path",
+    type=str,
+    default="runwayml/stable-diffusion-v1-5",
+    required=False,
+    help="Path to downloaded sd-1-5 model or model identifier from huggingface.co/models.",
+)
+parser.add_argument(
+    "--lora_path",
+    type=str,
+    default="AgainstEntropy/kanji-lora-sd-v1-5",
+    required=False,
+    help="Path to downloaded LoRA weight or model identifier from huggingface.co/models.",
+)
+parser.add_argument(
+    "--lcm_lora_path",
+    type=str,
+    default="AgainstEntropy/kanji-lcm-lora-sd-v1-5",
+    required=False,
+    help="Path to downloaded LCM-LoRA weight or model identifier from huggingface.co/models.",
+)
+parser.add_argument(
+    "--img_res",
+    type=int,
+    default=64,
+    required=False,
+    help="Image resolution for displaying Kanji characters in ChatBot.",
+)
+parser.add_argument(
+    "--img_per_line",
+    type=int,
+    default=16,
+    required=False,
+    help="Number of Kanji characters to display in a single line.",
+)
+parser.add_argument(
+    "--tmp_dir",
+    type=str,
+    default="./tmp",
+    required=False,
+    help="Path to save temporary images generated by StreamDiffusionIO.",
+)
+
+args = parser.parse_args()
+
+if torch.cuda.is_available():
+    device = "cuda"
+else:
+    device = "cpu"
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo works best on GPU.</p>"
+
+DESCRIPTION += "\n<p>This demo will get the best kanji streaming experience in localhost (or SSH forward), instead of shared link generated by Gradio.</p>"
+
+model = AutoModelForCausalLM.from_pretrained(args.llama_model_id_or_path, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(args.llama_model_id_or_path)
+tokenizer.use_default_system_prompt = False
+streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+lcm_stream = LatentConsistencyModelStreamIO(
+    model_id_or_path=args.sd_model_id_or_path,
+    lcm_lora_path=args.lcm_lora_path,
+    lora_dict={args.lora_path: 1},
+    resolution=128,
+    device=device,
+    use_xformers=True,
+    verbose=True,
+)
+
+tmp_dir_template = f"{args.tmp_dir}/%d"
+response_num = 0
+
+stitcher = ImageStitcher(
+    tmp_dir=tmp_dir_template % response_num,
+    img_res=args.img_res,
+    img_per_line=args.img_per_line,
+    verbose=True,
+)
+
+
+@spaces.GPU
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    show_original_response: bool,
+    seed: int,
+    system_prompt: str = '',
+    max_new_tokens: int = 1024,
+    temperature: float = 0.6,
+    top_p: float = 0.9,
+    top_k: int = 50,
+    repetition_penalty: float = 1.2,
+) -> Iterator[str]:
+    
+    conversation = []
+    if system_prompt:
+        conversation.append({"role": "system", "content": system_prompt})
+    for user, assistant in chat_history:
+        if isinstance(assistant, tuple):
+            assistant = assistant[1]
+        else:
+            assistant = str(assistant)
+        conversation.extend([
+            {"role": "user", "content": user}, 
+            {"role": "assistant", "content": assistant},
+        ])
+    conversation.append({"role": "user", "content": message})
+    print(conversation)
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
+        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
+        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = input_ids.to(model.device)
+
+    generate_kwargs = dict(
+        {"input_ids": input_ids},
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    prompt_queue = SimpleQueue()
+
+    lcm_stream.reset(seed)
+    stitcher.reset()
+
+    global response_num
+    response_num += 1
+    stitcher.update_tmp_dir(tmp_dir_template % response_num)
+
+    def append_to_queue():
+        for text in streamer:
+            outputs.append(text)
+            prompt = text.strip()
+            if prompt:
+                if prompt.endswith("."): prompt = prompt[:-1]
+                prompt_queue.put(prompt)
+        prompt_queue.put(None)
+
+    append_thread = Thread(target=append_to_queue)
+    append_thread.start()
+
+    def show_image(prompt: str = None):
+        image, text = lcm_stream(prompt)
+        img_path = None
+        if image is not None:
+            img_path = stitcher.add(image, text)
+        return img_path
+
+    while True:
+        prompt = prompt_queue.get()
+        if prompt is None:
+            break
+        img_path = show_image(prompt)
+        if img_path is not None:
+            yield (img_path, )
+
+    # Continue to display the remaining images
+    while True:
+        img_path = show_image()
+        if img_path is not None:
+            yield (img_path, ''.join(outputs))
+        if lcm_stream.stop():
+            break
+
+    print(outputs)
+    if show_original_response:
+        yield ''.join(outputs)
+
+
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    chatbot=Chatbot(height=400),
+    additional_inputs=[
+        gr.Checkbox(
+            label="Show original response",
+            value=False,
+        ),
+        gr.Number(
+            label="Seed",
+            info="Random Seed for Kanji Generation (maybe some kind of accent 🤔)",
+            step=1,
+            value=1026,
+        ),
+        gr.Textbox(label="System prompt", lines=4),
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.6,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.2,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["Hello there! How are you doing?"],
+        ["Can you explain briefly to me what is the Python programming language?"],
+        ["Explain the plot of Cinderella in a sentence."],
+        ["How many hours does it take a man to eat a Helicopter?"],
+        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+    ],
+)
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    chat_interface.render()
+    gr.Markdown(LICENSE)
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch(server_name="0.0.0.0", share=False)

app-llama.py

@@ -0,0 +1,159 @@
+import argparse
+import os
+from threading import Thread
+from typing import Iterator
+
+import gradio as gr
+import spaces
+import torch
+from gradio import Chatbot
+from transformers import (AutoModelForCausalLM, AutoTokenizer,
+                          TextIteratorStreamer)
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+DESCRIPTION = """\
+# Llama-2 7B Chat
+
+This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
+
+🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
+
+🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
+"""
+
+LICENSE = """
+<p/>
+
+---
+As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
+this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
+"""
+
+parser = argparse.ArgumentParser(description="Gradio launcher for Streaming-Kanji.")
+parser.add_argument(
+    "--llama_model_id_or_path",
+    type=str,
+    default="meta-llama/Llama-2-7b-chat-hf",
+    required=False,
+    help="Path to downloaded llama-chat-hf model or model identifier from huggingface.co/models.",
+)
+args = parser.parse_args()
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+
+if torch.cuda.is_available():
+    model_id = args.llama_model_id_or_path
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.use_default_system_prompt = False
+
+
+@spaces.GPU
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int = 1024,
+    temperature: float = 0.6,
+    top_p: float = 0.9,
+    top_k: int = 50,
+    repetition_penalty: float = 1.2,
+) -> Iterator[str]:
+    conversation = []
+    if system_prompt:
+        conversation.append({"role": "system", "content": system_prompt})
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
+        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
+        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = input_ids.to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        {"input_ids": input_ids},
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
+
+
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    chatbot=Chatbot(height=400),
+    additional_inputs=[
+        gr.Textbox(label="System prompt", lines=6),
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.6,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.2,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["Hello there! How are you doing?"],
+        ["Can you explain briefly to me what is the Python programming language?"],
+        ["Explain the plot of Cinderella in a sentence."],
+        ["How many hours does it take a man to eat a Helicopter?"],
+        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+    ],
+)
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    chat_interface.render()
+    gr.Markdown(LICENSE)
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch(server_name="0.0.0.0", share=False)

app.py → app-mixtral.py

@@ -88,17 +88,19 @@ else:
     device = "cpu"
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo works best on GPU.</p>"
 
-DESCRIPTION += "\n<p>This demo will get the best kanji streaming experience in localhost (or SSH forward), instead of shared link generated by Gradio.</p>"
-
 client = InferenceClient(
     model="mistralai/Mixtral-8x7B-Instruct-v0.1",
 )
 
-def format_prompt(message, history):
-    prompt = "<s>"
+def format_prompt(message, history, system_prompt=''):
+    prompt = f"<s> {system_prompt}"
     for user_prompt, bot_response in history:
         prompt += f"[INST] {user_prompt} [/INST]"
-        prompt += f" {bot_response}</s> "
+        if isinstance(bot_response, tuple):
+            bot_response = bot_response[1]
+        if not bot_response.endswith("</s>"):
+            bot_response += "</s>"
+        prompt += f" {bot_response} "
     prompt += f"[INST] {message} [/INST]"
     return prompt
 
@@ -114,7 +116,6 @@ lcm_stream = LatentConsistencyModelStreamIO(
 
 tmp_dir_template = f"{args.tmp_dir}/%d"
 response_num = 0
-response_cache = ""
 
 stitcher = ImageStitcher(
     tmp_dir=tmp_dir_template % response_num,
@@ -128,8 +129,9 @@ stitcher = ImageStitcher(
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
+    show_original_response: bool,
     seed: int,
-    system_prompt: str,
+    system_prompt: str = '',
     max_new_tokens: int = 1024,
     temperature: float = 0.6,
     top_p: float = 0.9,
@@ -140,8 +142,6 @@ def generate(
     if temperature < 1e-2:
         temperature = 1e-2
     
-    global response_cache
-
     generate_kwargs = dict(
         max_new_tokens=max_new_tokens,
         do_sample=True,
@@ -150,11 +150,11 @@ def generate(
         temperature=temperature,
         repetition_penalty=repetition_penalty,
     )
-    formatted_prompt = format_prompt(f"{system_prompt}, {message}", chat_history)
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    formatted_prompt = format_prompt(message, chat_history, system_prompt)
+    print(formatted_prompt)
+    streamer = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
 
-    global outputs
-    outputs = ""
+    outputs = []
     prompt_queue = SimpleQueue()
 
     lcm_stream.reset(seed)
@@ -165,14 +165,13 @@ def generate(
     stitcher.update_tmp_dir(tmp_dir_template % response_num)
 
     def append_to_queue():
-        for response in stream:
+        for response in streamer:
             text = response.token.text
-            global outputs
-            outputs += text
-            text = text.strip()
-            if text and text not in ['</s>']:
-                if text.endswith("."): text = text[:-1]
-                prompt_queue.put(text)
+            outputs.append(text)
+            prompt = text.strip()
+            if prompt and prompt not in ['</s>']:
+                if prompt.endswith("."): prompt = prompt[:-1]
+                prompt_queue.put(prompt)
         prompt_queue.put(None)
 
     append_thread = Thread(target=append_to_queue)
@@ -197,26 +196,33 @@ def generate(
     while True:
         img_path = show_image()
         if img_path is not None:
-            yield (img_path, )
+            yield (img_path, ''.join(outputs))
         if lcm_stream.stop():
             break
 
-    response_cache = outputs
     print(outputs)
-    return outputs
+    if show_original_response:
+        yield ''.join(outputs)
 
 
 chat_interface = gr.ChatInterface(
     fn=generate,
     chatbot=Chatbot(height=400),
     additional_inputs=[
+        gr.Checkbox(
+            label="Show original response",
+            value=False,
+        ),
         gr.Number(
             label="Seed",
             info="Random Seed for Kanji Generation (maybe some kind of accent 🤔)",
             step=1,
             value=1026,
         ),
-        gr.Textbox(label="System prompt", lines=4),
+        gr.Textbox(
+            label="System prompt", 
+            value="",
+            lines=4),
         gr.Slider(
             label="Max new tokens",
             minimum=1,
@@ -270,5 +276,4 @@ with gr.Blocks(css="style.css") as demo:
     gr.Markdown(LICENSE)
 
 if __name__ == "__main__":
-    # demo.queue(max_size=20).launch(show_api=False)
-    demo.queue(max_size=20).launch(server_name="0.0.0.0", share=False)
+    demo.queue(max_size=20).launch(server_name="0.0.0.0", share=False, show_api=False)

run-app-mixtral.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+source $VAST/miniconda3/bin/activate kanji
+
+python app-mixtral.py \
+    --sd_model_id_or_path="$VAST/models/stable-diffusion-v1-5"  \
+    --lora_path="$VAST/codes/kanji/lora_weights/kanji-lora-sd-v1-5" \
+    --lcm_lora_path="$VAST/codes/kanji/lora_weights/kanji-lcm-lora-sd-v1-5" \
+    --tmp_dir="./tmp"

run-kanji-local_llama.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+source $VAST/miniconda3/bin/activate kanji
+
+python app-kanji-local-llama.py \
+    --llama_model_id_or_path="$VAST/models/meta-llama/llama-2-7b-chat-hf" \
+    --sd_model_id_or_path="$VAST/models/stable-diffusion-v1-5"  \
+    --lora_path="$VAST/codes/kanji/lora_weights/kanji-lora-sd-v1-5" \
+    --lcm_lora_path="$VAST/codes/kanji/lora_weights/kanji-lcm-lora-sd-v1-5" \
+    --tmp_dir="./tmp"

run-llama.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+source $VAST/miniconda3/bin/activate kanji
+
+python app-llama.py \
+    --llama_model_id_or_path="$VAST/models/meta-llama/llama-2-7b-chat-hf"