TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

---

SciPhi Self RAG Mistral 7B 32K - AWQ

• Model creator: SciPhi-AI
• Original model: SciPhi Self RAG Mistral 7B 32K

Description

This repo contains AWQ model files for SciPhi-AI's SciPhi Self RAG Mistral 7B 32K.

These files were quantised using hardware kindly provided by Massed Compute.

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.

It is supported by:

• Text Generation Webui - using Loader: AutoAWQ
• vLLM - Llama and Mistral models only
• Hugging Face Text Generation Inference (TGI)
• AutoAWQ - for use from Python code

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
• SciPhi-AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: SciPhi

### System:
{system_message}

### Instruction:
{prompt}

### Response:

Provided files, and AWQ parameters

For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.

Models are released as sharded safetensors files.

Branch	Bits	GS	AWQ Dataset	Seq Len	Size
main	4	128	wikitext	4096	4.15 GB

How to easily download and use this model in text-generation-webui

Please make sure you're using the latest version of text-generation-webui.

It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.

1. Click the Model tab.
2. Under Download custom model or LoRA, enter TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ.
3. Click Download.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to Model.
6. In the Model dropdown, choose the model you just downloaded: SciPhi-Self-RAG-Mistral-7B-32k-AWQ
7. Select Loader: AutoAWQ.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.
10. Once you're ready, click the Text Generation tab and enter a prompt to get started!

Multi-user inference server: vLLM

Documentation on installing and using vLLM can be found here.

• Please ensure you are using vLLM version 0.2 or later.
• When using vLLM as a server, pass the --quantization awq parameter.

For example:

python3 python -m vllm.entrypoints.api_server --model TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ --quantization awq

• When using vLLM from Python code, again set quantization=awq.

For example:

from vllm import LLM, SamplingParams

prompts = [
    "Tell me about AI",
    "Write a story about llamas",
    "What is 291 - 150?",
    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''### System:
{system_message}

### Instruction:
{prompt}

### Response:
'''

prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]

sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ", quantization="awq", dtype="auto")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Multi-user inference server: Hugging Face Text Generation Inference (TGI)

Use TGI version 1.1.0 or later. The official Docker container is: ghcr.io/huggingface/text-generation-inference:1.1.0

Example Docker parameters:

--model-id TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096

Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):

pip3 install huggingface-hub

from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''### System:
{system_message}

### Instruction:
{prompt}

### Response:
'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: ", response)

Inference from Python code using AutoAWQ

Install the AutoAWQ package

Requires: AutoAWQ 0.1.1 or later.

pip3 install autoawq

If you have problems installing AutoAWQ using the pre-built wheels, install it from source instead:

pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .

AutoAWQ example code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_name_or_path = "TheBloke/SciPhi-Self-RAG-Mistral-7B-32k-AWQ"

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
                                          trust_remote_code=False, safetensors=True)

prompt = "Tell me about AI"
prompt_template=f'''### System:
{system_message}

### Instruction:
{prompt}

### Response:
'''

print("*** Running model.generate:")

token_input = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

# Generate output
generation_output = model.generate(
    token_input,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    max_new_tokens=512
)

# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("LLM output: ", text_output)

"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])
"""

Compatibility

The files provided are tested to work with:

• text-generation-webui using Loader: AutoAWQ.
• vLLM version 0.2.0 and later.
• Hugging Face Text Generation Inference (TGI) version 1.1.0 and later.
• AutoAWQ version 0.1.1 and later.

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute

Thanks to the chirper.ai team!

Thanks to Clay from gpus.llm-utils.org!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: SciPhi-AI's SciPhi Self RAG Mistral 7B 32K

SciPhi-Self-RAG-Mistral-7B-32k Model Card

SciPhi-Self-RAG-Mistral-7B-32k is a Large Language Model (LLM) fine-tuned from Mistral-7B-v0.1. This model underwent the fine-tuning process described in the SciPhi-Mistral-7B-32k model card. It then underwent further fine-tuning on the recently released self-rag dataset. Other RAG-related instruct datasets were mixed in during this process in an effort to keep the tone of the current model. This model benchmarks well, but it needs further tuning to be an excellent conversationalist.

Benchmark Results:

SciPhi-AI is available via a free hosted API, though the exposed model can vary. Currently, SciPhi-Self-RAG-Mistral-7B-32k is available. More details can be found in the docs here.

Recommended Chat Formatting

We recommend mapping such that

messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]

goes to --->

### System:
You are a friendly chatbot who always responds in the style of a pirate

### Instruction:
How many helicopters can a human eat in one sitting?

### Response:
...

Here is a sample implementation that does this and combines with RAG context retrieval.

def get_chat_completion(
    self, conversation: list[dict], generation_config: GenerationConfig
) -> str:
    self._check_stop_token(generation_config.stop_token)
    prompt = ""
    added_system_prompt = False
    for message in conversation:
        if message["role"] == "system":
            prompt += f"### System:\n{SciPhiLLMInterface.ALPACA_CHAT_SYSTEM_PROMPT}. Further, the assistant is given the following additional instructions - {message['content']}\n\n"
            added_system_prompt = True
        elif message["role"] == "user":
            last_user_message = message["content"]
            prompt += f"### Instruction:\n{last_user_message}\n\n"
        elif message["role"] == "assistant":
            prompt += f"### Response:\n{message['content']}\n\n"

    if not added_system_prompt:
        prompt = f"### System:\n{SciPhiLLMInterface.ALPACA_CHAT_SYSTEM_PROMPT}.\n\n{prompt}"

    context = self.rag_interface.get_contexts([last_user_message])[0]
    prompt += f"### Response:\n{SciPhiFormatter.RETRIEVAL_TOKEN} {SciPhiFormatter.INIT_PARAGRAPH_TOKEN}{context}{SciPhiFormatter.END_PARAGRAPH_TOKEN}"
    latest_completion = self.model.get_instruct_completion(
        prompt, generation_config
    ).strip()

    return SciPhiFormatter.remove_cruft(latest_completion)

Model Architecture

Base Model: Mistral-7B-v0.1

Architecture Features:

• Transformer-based model
• Grouped-Query Attention
• Sliding-Window Attention
• Byte-fallback BPE tokenizer

References

1. Asai, A., Wu, Z., Wang, Y., Sil, A., & Hajishirzi, H. (2023). Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. arXiv preprint arXiv:2310.11511.
2. Lian, W., Goodson, B., Wang, G., Pentland, E., Cook, A., Vong, C., & Teknium. (2023). MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset. HuggingFace repository. Link
3. Mukherjee, S., Mitra, A., Jawahar, G., Agarwal, S., Palangi, H., & Awadallah, A. (2023). Orca: Progressive Learning from Complex Explanation Traces of GPT-4. arXiv preprint arXiv:2306.02707.
4. Longpre, S., Hou, L., Vu, T., Webson, A., Chung, H. W., Tay, Y., Zhou, D., Le, Q. V., Zoph, B., Wei, J., & Roberts, A. (2023). The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. arXiv preprint arXiv:2301.13688.
5. Mistral AI. (2023). Model Card for Mistral-7B-v0.1. The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks tested. For full details, please refer to the paper and release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. Link

Acknowledgements

Thank you to the AI Alignment Lab, vikp, jph00 and others who contributed to this work.