Llama2-70B-OASST-SFT-v10-AWQ

<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end -->

Llama2 70B SFT v10 - AWQ

• Model creator: OpenAssistant
• Original model: Llama2 70B SFT v10

<!-- description start -->

Description

This repo contains AWQ model files for OpenAssistant's Llama2 70B SFT v10.

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.

It is also now supported by continuous batching server vLLM, allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.

<!-- description end --> <!-- repositories-available start -->

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
• OpenAssistant's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

<!-- repositories-available end --> <!-- prompt-template start -->

Prompt template: ChatML

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

<!-- prompt-template end --> <!-- README_AWQ.md-provided-files start -->

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.

<!-- README_AWQ.md-provided-files end --> <!-- README_AWQ.md-use-from-vllm start -->

Serving this model from vLLM

Documentation on installing and using vLLM can be found here.

• When using vLLM as a server, pass the --quantization awq parameter, for example:

python3 python -m vllm.entrypoints.api_server --model TheBloke/Llama2-70B-OASST-SFT-v10-AWQ --quantization awq

When using vLLM from Python code, pass the quantization=awq parameter, for example:

from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/Llama2-70B-OASST-SFT-v10-AWQ", quantization="awq")

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}")

<!-- README_AWQ.md-use-from-vllm start --> <!-- README_AWQ.md-use-from-python start -->

How to use this AWQ model from Python code

Install the necessary packages

Requires: AutoAWQ 0.0.2 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 .

You can then try the following example code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_name_or_path = "TheBloke/Llama2-70B-OASST-SFT-v10-AWQ"

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

prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

'''

print("\n\n*** Generate:")

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

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

print("Output: ", tokenizer.decode(generation_output[0]))

# Inference can also be done using transformers' pipeline
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'])

<!-- README_AWQ.md-use-from-python end --> <!-- README_AWQ.md-compatibility start -->

Compatibility

The files provided are tested to work with AutoAWQ, and vLLM.

Huggingface Text Generation Inference (TGI) is not yet compatible with AWQ, but a PR is open which should bring support soon: TGI PR #781.

<!-- README_AWQ.md-compatibility end --> <!-- footer start --> <!-- 200823 -->

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: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

<!-- footer end -->

Original model card: OpenAssistant's Llama2 70B SFT v10

Open-Assistant Llama2 70B SFT v10

This model is an Open-Assistant fine-tuning of Meta's Llama2 70B LLM. It was fine-tuned in two stages, first on a mix of synthetic instrunctions and coding tasks and then in a "polishing" stage on the best human demonstrations collected at open-assistant.io up to July 23, 2023 (see Configuration Details below).

Model Details

• Finetuned from: meta-llama/Llama-2-70b via epfLLM/Megatron-LLM
• Model type: Causal decoder-only transformer language model
• Language: English (and limited capabilities in German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish)
• Weights & Biases training logs: Stage 1 (1 epoch pretrain-mix, 12k steps), Stage 2 (3 epochs oasst top-1, 519 steps)
• Demo: Continuations for 250 random prompts (TGI, 4bit nf4 quantization)
• Evaluation FastEval-OpenAssistant Overview (using FastEval & vLLM)
• License: LLAMA 2 COMMUNITY LICENSE AGREEMENT
• Contact: Open-Assistant Discord

Prompting / Prompt Template

Due to public demand (see survey) we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's chatml standard prompt format. We hope that this leads to greater compatibility with chat inference/frontend applications.

Prompt dialogue template:

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

The model input can contain multiple conversation turns between user and assistant, e.g.

<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)

The model was partly trained with orca system messages.
For inference we recommend to use the official Llama2 system message:

<|im_start|>system
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<|im_end|>

Credits & Special Thanks

• Thanks to Meta AI for training and releasing the Llama2 model.
• Distributed training support was provided by EPFL's Machine Learning and Optimization Laboratory, and Natural Language Processing Lab.
• The open-source epfLLM/Megatron-LLM trainer was used for fine-tuning.
• rombodawg curated the LosslessMegaCodeTrainingV2_1m_Evol_Uncensored dataset.
• ehartford generated and published the ehartford/dolphin and the ehartford/oa_leet10k datasets.
• Argilla curated and published the argilla/databricks-dolly-15k-curated-multilingual dataset.
• shahules786 de-duped and filtered the Dolphin dataset with a cluster-center approach and generated the orca-best (ocra-chat) dataset.
• andreaskoepf prepared & orchestrated the training.

We want to especially thank everyone who contributed in the crowed-sourced Open-Assistant dataset creation on https://open-assistant.io/ - without you this project would not have been possible.

Ethical Considerations and Limitations

Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, the potential outputs of llama2-70b-oasst-sft-v10 cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of llama2-70b-oasst-sft-v10, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see Meta's Responsible Use Guide.

Note regarding inference with TGI

During evaluation we noticed that this 70B model produced extremely poor outputs when loaded it was loaded in 16 bit precision sharded in TGI. In contrast the model could be evaluated without problem using vLLM. The model also worked decently well when loaded with TGI on a single GPPU nf4 quantized via TimDettmers/bitsandbytes. Will will get it touch with the TGI authors to find out why sharded 16-bit inference doesn't work as expected.

Configuration Details

The "pretokenizer" utility used to tokenize the datamix is part of the Open-Assistant github repository and can be found here: model/pretokenizer.

Stage 1 Pretokenizer Configuration

Entries of the dataset with assistant replies shorter than 25 tokens were excluded from training.

oasst_pre10_min25:
  datasets:
    - megacode2:
        fraction: 0.5
        val_split: 0.01
        max_val_set: 1000
    - orca-chat:
        val_split: 0.01
        max_val_set: 1000
    - dolly15k_multilingual:
        val_split: 0.05
        max_val_set: 300
    - oa_leet10k:
        val_split: 0.05
        max_val_set: 250
  output_dir: "output/oasst_pre10_min25"
  filename_prefix: "oasst_pre10"
  min_assistant_tokens: 25

Stage 1 dataset statistics:

# Stats for output/oasst_pre10_min25_llama2

## Stats for 'Subset of InstructionDataset (megacode2)' (466364 samples (50.0%))
-----------------
  Accepted: 398223/466364 (85.4%)
  Accepted tokens: 167676873
  Skipped: 68141 (14.6%)
  Min tokens per sample: 36
  Max tokens per sample: 11810
  Avg tokens per sample: 421.063
-----------------

## Stats for 'Subset of OrcaChat (orca-chat)' (325616 samples (100.0%))
-----------------
  Accepted: 325616/325616 (100.0%)
  Accepted tokens: 178307574
  Skipped: 0 (0.0%)
  Min tokens per sample: 105
  Max tokens per sample: 10408
  Avg tokens per sample: 547.601
-----------------

## Stats for 'Subset of Dolly15kMultilingual' (57020 samples (100.0%))
-----------------
  Accepted: 47494/57020 (83.3%)
  Accepted tokens: 13883177
  Skipped: 9526 (16.7%)
  Min tokens per sample: 34
  Max tokens per sample: 9172
  Avg tokens per sample: 292.314
-----------------

## Stats for 'Subset of InstructionDataset (oa_leet10k)' (22236 samples (100.0%))
-----------------
  Accepted: 22236/22236 (100.0%)
  Accepted tokens: 15905296
  Skipped: 0 (0.0%)
  Min tokens per sample: 168
  Max tokens per sample: 10588
  Avg tokens per sample: 715.295
-----------------

## Stats for 'total' (871236 samples (100.0%))
-----------------
  Accepted: 793569/871236 (91.1%)
  Accepted tokens: 375772920
  Skipped: 77667 (8.9%)
  Min tokens per sample: 34
  Max tokens per sample: 11810
  Avg tokens per sample: 473.523
-----------------

Stage 2 Pretokenizer Configuration

oasst_top1:
  datasets:
    - oasst_export:
        lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
        input_file_path: 2023-07-23_oasst_ready.tar.gz
        top_k: 1
        val_split: 0.05
  output_dir: "output/oasst_top1_2023-07-23"
  filename_prefix: "oasst_top1"

Stage 2 dataset statistics:

# Stats for output/oasst_top1_2023-07-23_llama2

## Stats for 'ListDataset' (11441 samples (100.0%))
-----------------
  Accepted: 11441/11441 (100.0%)
  Accepted tokens: 5315368
  Skipped: 0 (0.0%)
  Min tokens per sample: 20
  Max tokens per sample: 5407
  Avg tokens per sample: 464.58945896337735
-----------------

## Stats for 'total' (11441 samples (100.0%))
-----------------
  Accepted: 11441/11441 (100.0%)
  Accepted tokens: 5315368
  Skipped: 0 (0.0%)
  Min tokens per sample: 20
  Max tokens per sample: 5407
  Avg tokens per sample: 464.58945896337735
-----------------

Megatron Fine-Tuning Arguments for Stage 1 (Instruction Tuning):

--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10/logging
--data_path ./data/oasst_pre10_min25_llama2/oasst_sft10-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 500
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.0
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 12000
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--wandb_logger

Megatron Fine-Tuning Arguments for Stage 2 (OASST Polishing, LIMA Dropout):

--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10/logging
--data_path ./data/oasst_top1_2023-07-23_llama2/oasst_top1-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 346
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.25
--lima_dropout
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 519
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--finetune
--wandb_logger