TheBlokeAI

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


Beyonder 4X7B v2 - AWQ

Description

This repo contains AWQ model files for Maxime Labonne's Beyonder 4X7B v2.

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

MIXTRAL AWQ

This is a Mixtral AWQ model.

For AutoAWQ inference, please install AutoAWQ 0.1.8 or later.

Support via Transformers is also available, but currently requires installing Transformers from Github: pip3 install git+https://github.com/huggingface/transformers.git

vLLM: version 0.2.6 is confirmed to support Mixtral AWQs.

TGI: I tested version 1.3.3 and it loaded the model fine, but I was not able to get any output back. Further testing/debug is required. (Let me know if you get it working!)

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.

AWQ models are supported by (note that not all of these may support Mixtral models yet - see above):

Repositories available

Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

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 8192 12.94 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/Beyonder-4x7B-v2-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: Beyonder-4x7B-v2-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 -m vllm.entrypoints.api_server --model TheBloke/Beyonder-4x7B-v2-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'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''

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

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

llm = LLM(model="TheBloke/Beyonder-4x7B-v2-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/Beyonder-4x7B-v2-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'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''

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

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/Beyonder-4x7B-v2-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'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''

# 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:

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.

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: Maxime Labonne's Beyonder 4X7B v2

Beyonder-4x7B-v2

This model is a Mixture of Experts (MoE) made with mergekit (mixtral branch). It uses the following base models:

🏆 Evaluation

Beyonder-4x7B-v2 is competitive with Mixtral-8x7B-Instruct-v0.1 on the Open LLM Leaderboard, while only having 4 experts instead of 8.

It also displays a significant improvement over the individual experts.

It also performs very well compared to other models on Nous benchmark suite. It's almost as good as the best Yi-34B fine-tune, which is a much bigger model: 24.2B parameters + only two experts are selected during inference (so ~12B) vs. 34B param.

Model AGIEval GPT4All TruthfulQA Bigbench Average
Beyonder-4x7B-v2 45.29 75.95 60.86 46.4 57.13
NeuralHermes-2.5-Mistral-7B 43.67 73.24 55.37 41.76 53.51
OpenHermes-2.5-Mistral-7B 42.75 72.99 52.99 40.94 52.42
Nous-Hermes-2-SOLAR-10.7B 47.79 74.69 55.92 44.84 55.81
Nous-Hermes-2-Yi-34B 50.27 76.00 60.34 46.69 58.33

AGIEval

Task Version Metric Value Stderr
agieval_aqua_rat 0 acc 23.62 ± 2.67
acc_norm 23.62 ± 2.67
agieval_logiqa_en 0 acc 41.47 ± 1.93
acc_norm 43.01 ± 1.94
agieval_lsat_ar 0 acc 23.04 ± 2.78
acc_norm 23.48 ± 2.80
agieval_lsat_lr 0 acc 51.57 ± 2.22
acc_norm 52.94 ± 2.21
agieval_lsat_rc 0 acc 64.31 ± 2.93
acc_norm 64.68 ± 2.92
agieval_sat_en 0 acc 79.13 ± 2.84
acc_norm 79.13 ± 2.84
agieval_sat_en_without_passage 0 acc 43.20 ± 3.46
acc_norm 43.20 ± 3.46
agieval_sat_math 0 acc 34.55 ± 3.21
acc_norm 32.27 ± 3.16

GPT4All

Task Version Metric Value Stderr
arc_challenge 0 acc 61.86 ± 1.42
acc_norm 64.51 ± 1.40
arc_easy 0 acc 85.06 ± 0.73
acc_norm 82.45 ± 0.78
boolq 1 acc 88.35 ± 0.56
hellaswag 0 acc 68.04 ± 0.47
acc_norm 85.12 ± 0.36
openbookqa 0 acc 37.80 ± 2.17
acc_norm 48.60 ± 2.24
piqa 0 acc 83.08 ± 0.87
acc_norm 83.95 ± 0.86
winogrande 0 acc 78.69 ± 1.15

TruthfulQA

Task Version Metric Value Stderr
truthfulqa_mc 1 mc1 44.55 ± 1.74
mc2 60.86 ± 1.57

Bigbench

Task Version Metric Value Stderr
bigbench_causal_judgement 0 multiple_choice_grade 58.95 ± 3.58
bigbench_date_understanding 0 multiple_choice_grade 66.40 ± 2.46
bigbench_disambiguation_qa 0 multiple_choice_grade 48.84 ± 3.12
bigbench_geometric_shapes 0 multiple_choice_grade 22.56 ± 2.21
exact_str_match 13.37 ± 1.80
bigbench_logical_deduction_five_objects 0 multiple_choice_grade 30.40 ± 2.06
bigbench_logical_deduction_seven_objects 0 multiple_choice_grade 20.57 ± 1.53
bigbench_logical_deduction_three_objects 0 multiple_choice_grade 52.00 ± 2.89
bigbench_movie_recommendation 0 multiple_choice_grade 44.40 ± 2.22
bigbench_navigate 0 multiple_choice_grade 52.10 ± 1.58
bigbench_reasoning_about_colored_objects 0 multiple_choice_grade 69.75 ± 1.03
bigbench_ruin_names 0 multiple_choice_grade 55.36 ± 2.35
bigbench_salient_translation_error_detection 0 multiple_choice_grade 23.65 ± 1.35
bigbench_snarks 0 multiple_choice_grade 77.35 ± 3.12
bigbench_sports_understanding 0 multiple_choice_grade 73.02 ± 1.41
bigbench_temporal_sequences 0 multiple_choice_grade 46.80 ± 1.58
bigbench_tracking_shuffled_objects_five_objects 0 multiple_choice_grade 22.08 ± 1.17
bigbench_tracking_shuffled_objects_seven_objects 0 multiple_choice_grade 19.03 ± 0.94
bigbench_tracking_shuffled_objects_three_objects 0 multiple_choice_grade 52.00 ± 2.89

🧩 Configuration

base_model: mlabonne/Marcoro14-7B-slerp
experts:
  - source_model: openchat/openchat-3.5-1210
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
    positive_prompts:
    - "code"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
  - source_model: maywell/PiVoT-0.1-Starling-LM-RP
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "story"
    - "character"
  - source_model: WizardLM/WizardMath-7B-V1.1
    positive_prompts:
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"

💻 Usage

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Beyonder-4x7B-v2"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Downloads last month
23
Safetensors
Model size
3.46B params
Tensor type
I32
·
FP16
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for TheBloke/Beyonder-4x7B-v2-AWQ

Quantized
(5)
this model