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)

GreenNodeLM 7B V4Leo - AWQ

Model creator: GreenNode.ai
Original model: GreenNodeLM 7B V4Leo

Description

This repo contains AWQ model files for GreenNode.ai's GreenNodeLM 7B V4Leo.

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.

AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.

It is supported by:

Text Generation Webui - using Loader: AutoAWQ
vLLM - version 0.2.2 or later for support for all model types.
Hugging Face Text Generation Inference (TGI)
Transformers version 4.35.0 and later, from any code or client that supports Transformers
AutoAWQ - for use from Python code

Repositories available

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Provided files, and AWQ parameters

I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.

Models are released as sharded safetensors files.

Branch	Bits	GS	AWQ Dataset	Seq Len	Size
main	4	128	VMware Open Instruct	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.

Click the Model tab.
Under Download custom model or LoRA, enter TheBloke/GreenNodeLM-7B-v4leo-AWQ.
Click Download.
The model will start downloading. Once it's finished it will say "Done".
In the top left, click the refresh icon next to Model.
In the Model dropdown, choose the model you just downloaded: GreenNodeLM-7B-v4leo-AWQ
Select Loader: AutoAWQ.
Click Load, and the model will load and is now ready for use.
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.
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 -m vllm.entrypoints.api_server --model TheBloke/GreenNodeLM-7B-v4leo-AWQ --quantization awq --dtype auto

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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### 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/GreenNodeLM-7B-v4leo-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/GreenNodeLM-7B-v4leo-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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### 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 Transformers

Install the necessary packages

Requires: Transformers 4.35.0 or later.
Requires: AutoAWQ 0.1.6 or later.

pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"

Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.

If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:

pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl

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 .

Transformers example code (requires Transformers 4.35.0 and later)

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_name_or_path = "TheBloke/GreenNodeLM-7B-v4leo-AWQ"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
    model_name_or_path,
    low_cpu_mem_usage=True,
    device_map="cuda:0"
)

# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:
'''

# Convert prompt to tokens
tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

generation_params = {
    "do_sample": True,
    "temperature": 0.7,
    "top_p": 0.95,
    "top_k": 40,
    "max_new_tokens": 512,
    "repetition_penalty": 1.1
}

# Generate streamed output, visible one token at a time
generation_output = model.generate(
    tokens,
    streamer=streamer,
    **generation_params
)

# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
    tokens,
    **generation_params
)

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

# Inference is also possible via Transformers' pipeline
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    **generation_params
)

pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)

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.
Transformers version 4.35.0 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: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Original model card: GreenNode.ai's GreenNodeLM 7B V4Leo

How to use

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
from peft import PeftModel
import torch
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "7"


model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto").eval()
tokenizer = AutoTokenizer.from_pretrained(model_path)
model.config.pad_token_id = tokenizer.eos_token_id


prompts = [
    "Explain QKV in Transformer.",
    "Can coughing effectively stop a heart attack?",
    "Who is the president of the United States?",
    "A farmer has a rectangular field with a length of 150 meters and a width of 100 meters. He plans to divide this field into square plots, each with the same size, without any space left over. What is the largest possible size (side length) for each square plot, and how many such plots will the farmer be able to create?",
    "A farmer has a certain number of chickens and rabbits in her farmyard. One day, she counts a total of 72 heads and 200 feet among them. How many chickens and how many rabbits are in the farmer's farmyard?",
    "What items is it legal to carry for anyone in the US?",
    "A man lives on the 10th floor of a building. Every day, he takes the elevator down to the ground floor to go to work. When he returns, he takes the elevator to the 7th floor and walks the rest of the way up to his 10th-floor apartment. However, on rainy days, he goes straight to the 10th floor. Why does he do this?",
    "Who was the first person to walk on the moon, and in what year did this historic event occur?",
    "The trophy doesn’t fit into the brown suitcase because it’s too large. What does 'it' refer to?",
    "Which element makes up most of the air we breathe? (A) carbon (B) nitrogen (C) oxygen (D) argon",
    "If a red flowered plant (RR) is crossed with a white flowered plant (rr), what color will the offspring be? (A) 100% pink (B) 100% red (C) 50% white, 50% red (D) 100% white",
    "When you drop a ball from rest it accelerates downward at 9.8 m/s². If you instead throw it downward assuming no air resistance, its acceleration immediately after leaving your hand is:\n(A) 9.8 m/s²\n(B) more than 9.8 m/s²\n(C) less than 9.8 m/s²\n(D) Cannot say unless the speed of throw is given.",
    "A snail is at the bottom of a 10-meter deep well. Every day, the snail climbs up 3 meters. However, at night, while the snail sleeps, it slides down 2 meters. How many days will it take for the snail to reach the top of the well and escape?",
    "Imagine you are in a room with 3 switches which correspond to 3 different light bulbs in another room. You cannot see the bulbs from the first room. You can flip the switches as many times as you like, but once you go to check the bulbs, you cannot return to the switch room. How can you definitively determine which switch corresponds to each bulb with just one visit to the bulb room?",
    "Translate from English to Vietnamese:\n\"Imagine you are in a room with 3 switches which correspond to 3 different light bulbs in another room. You cannot see the bulbs from the first room. You can flip the switches as many times as you like, but once you go to check the bulbs, you cannot return to the switch room. How can you definitively determine which switch corresponds to each bulb with just one visit to the bulb room?\""
]

system = """Below is an instruction that describes a task. 
Write a response that appropriately completes the request."""

template_format = """{system}

### Instruction:
{prompt}

### Response:
"""

for prompt in prompts:
    template = template_format.format(system=system, prompt=prompt)

    input_ids = tokenizer([template], return_tensors="pt").to("cuda")
    print(input_ids)
    print(tokenizer.decode(input_ids["input_ids"][0]))

    outputs = model.generate(
        **input_ids,
        max_new_tokens=1024,
        do_sample=True,
        repetition_penalty=1.1,
        temperature=0.3,
        top_k=10,
        top_p=0.95,

    )

    response = tokenizer.decode(outputs[0])

    print(response)

    print('*'*20)

TheBloke
/

GreenNodeLM-7B-v4leo-AWQ